Detection method and control method of intelligent driving vehicle and processor

文档序号：635420 发布日期：2021-05-11 浏览：6次中文

阅读说明：本技术 智能驾驶车辆的检测方法、控制方法和处理器 (Detection method and control method of intelligent driving vehicle and processor ) 是由赵祈杰李德聆陈泽佳刘炜铭周筠于 2021-01-13 设计创作，主要内容包括：本申请提供了一种智能驾驶车辆的检测方法、控制方法和处理器,智能驾驶车辆的检测方法包括：接收控制中心发送的施工区域的语义地图,施工区域的语义地图包括第一障碍物信息,第一障碍物信息包括第一障碍物的位置信息,第一障碍物为施工区域中的障碍物；实时检测第二障碍物信息,第二障碍物信息包括第二障碍物的位置信息,第二障碍物为预定区域的障碍物；对第一障碍物信息进行去冗余,得到第一目标障碍物信息,第一目标障碍物信息为第一目标障碍物的位置信息,第一目标障碍物为与第二障碍物相匹配的第一障碍物；将第一目标障碍物信息与第二障碍物信息匹配,得到第二目标障碍物信息,第二目标障碍物信息至少包括第一目标障碍物信息。(The application provides a detection method, a control method and a processor of an intelligent driving vehicle, wherein the detection method of the intelligent driving vehicle comprises the following steps: receiving a semantic map of a construction area sent by a control center, wherein the semantic map of the construction area comprises first obstacle information, the first obstacle information comprises position information of a first obstacle, and the first obstacle is an obstacle in the construction area; detecting second obstacle information in real time, wherein the second obstacle information comprises position information of a second obstacle, and the second obstacle is an obstacle in a preset area; removing redundancy of the first obstacle information to obtain first target obstacle information, wherein the first target obstacle information is position information of a first target obstacle, and the first target obstacle is a first obstacle matched with a second obstacle; and matching the first target obstacle information with the second obstacle information to obtain second target obstacle information, wherein the second target obstacle information at least comprises the first target obstacle information.)

1. A detection method for a smart-driving vehicle, comprising:

receiving a semantic map of a construction area sent by a control center, wherein the semantic map of the construction area comprises first obstacle information, the first obstacle information comprises position information of a first obstacle, and the first obstacle is an obstacle in the construction area;

detecting second obstacle information in real time, wherein the second obstacle information comprises position information of a second obstacle, and the second obstacle is an obstacle in a preset area;

removing redundancy of the first obstacle information to obtain first target obstacle information, wherein the first target obstacle information is position information of a first target obstacle, and the first target obstacle is the first obstacle matched with the second obstacle;

and matching the first target obstacle information with the second obstacle information to obtain second target obstacle information, wherein the second target obstacle information at least comprises the first target obstacle information.

2. The method of claim 1, wherein the de-redundancy of the first obstacle information to obtain first target obstacle information comprises:

matching the first obstacle information and the second obstacle information to determine whether the first obstacle matching the second obstacle exists;

and in the case that the first obstacle matched with the second obstacle exists, determining the first obstacle matched with the second obstacle as the first target obstacle, and obtaining the first target obstacle information in the semantic map.

3. The method according to claim 2, wherein the position information of the first obstacle is position information of a grid where the first obstacle is located, the position information of the second obstacle is position information of a grid where the second obstacle is located, and the matching of the first obstacle information and the second obstacle information is performed to determine whether the first obstacle matching the second obstacle exists, includes:

comparing the position information of the grid where the first obstacle is located with the position information of the grid where the second obstacle is located;

determining that the first obstacle matched with the second obstacle exists under the condition that the grid where the first obstacle is located and the grid where the second obstacle is located have more than a preset number of same grids.

4. The method according to any one of claims 1 to 3, wherein matching the first target obstacle information with the second obstacle information, resulting in second target obstacle information, comprises:

acquiring the first target obstacle information;

determining whether the second obstacle that does not match the first obstacle is present;

in the presence of the second obstacle that does not match the first obstacle, determining that the second obstacle that does not match the first obstacle is a third target obstacle, and acquiring the third target obstacle information in the second obstacle information, the second target obstacle information including the third target obstacle information and the first target obstacle information.

5. The method of claim 4, wherein the position information of the first obstacle is position information of a grid where the first obstacle is located, and the position information of the second obstacle is position information of a grid where the second obstacle is located, and the determining whether the second obstacle that does not match the first obstacle exists comprises:

comparing the position information of the grid where the first obstacle is located with the position information of the grid where the second obstacle is located;

determining that there is the second obstacle that does not match the first obstacle if the grid where the first obstacle is located and the grid where the second obstacle is located have less than or equal to a predetermined number of the same grids.

6. The method of claim 1, wherein after the first obstacle information is de-redundant to obtain first target obstacle information, the method further comprises:

and sending the first target obstacle information to the control center, and updating the semantic map by the control center according to the first target obstacle information.

7. The method of claim 1, wherein detecting second obstacle information in real-time comprises:

acquiring a 2D map in a preset area in real time;

implementing acquisition of a 3D point cloud map of the predetermined area;

and determining the second obstacle information according to the 2D map and the 3D point cloud map.

8. The method of claim 1, wherein the map of the semantic map is a high-precision map.

9. A control method of an intelligent driving vehicle, characterized by comprising:

a target vehicle receives a semantic map of a construction area sent by a control center, wherein the semantic map of the construction area comprises first obstacle information, the first obstacle information comprises position information of a first obstacle, and the first obstacle is an obstacle in the construction area;

the target vehicle detects second obstacle information in real time, wherein the second obstacle information comprises position information of a second obstacle, and the second obstacle is an obstacle in a preset area;

the target vehicle performs redundancy elimination on the first obstacle information to obtain first target obstacle information, wherein the first target obstacle information is position information of a first target obstacle, and the first target obstacle is the first obstacle matched with the second obstacle;

the target vehicle matches the first target obstacle information with the second obstacle information to obtain second target obstacle information, wherein the second target obstacle information at least comprises the first target obstacle information;

and the target vehicle controls the running of the vehicle according to the second target obstacle information.

10. The method of claim 9, wherein the target vehicle de-redundantly locating the first obstacle information to obtain first target obstacle information comprises:

matching the first obstacle information and the second obstacle information to determine whether the first obstacle matching the second obstacle exists;

and under the condition that the first obstacle matched with the second obstacle exists, determining the first obstacle matched with the second obstacle as the first target obstacle, and obtaining the first target obstacle information in the semantic map.

11. The method of any one of claims 8 to 10, wherein the target vehicle matching the first target obstacle information with the second obstacle information resulting in second target obstacle information, comprises:

acquiring the first target obstacle information;

determining whether the second obstacle that does not match the first obstacle is present;

12. A detection device for a smart-driving vehicle, comprising:

the system comprises a first receiving unit, a second receiving unit and a control center, wherein the first receiving unit is used for receiving a semantic map of a construction area sent by the control center, the semantic map of the construction area comprises first obstacle information, the first obstacle information comprises position information of a first obstacle, and the first obstacle is an obstacle in the construction area;

the first detection unit is used for detecting second obstacle information in real time, wherein the second obstacle information comprises position information of a second obstacle, and the second obstacle is an obstacle in a preset area;

a first redundancy removing unit, configured to remove redundancy from the first obstacle information to obtain first target obstacle information, where the first target obstacle information is position information of a first target obstacle, and the first target obstacle is the first obstacle matched with the second obstacle;

and the first matching unit is used for matching the first target obstacle information with the second obstacle information to obtain second target obstacle information, and the second target obstacle information at least comprises the first target obstacle information.

13. A control apparatus of a vehicle, characterized by comprising:

the second receiving unit is used for receiving a semantic map of a construction area sent by a control center by a target vehicle, wherein the semantic map of the construction area comprises first obstacle information, the first obstacle information comprises position information of a first obstacle, and the first obstacle is an obstacle in the construction area;

the second detection unit is used for detecting second obstacle information in real time by the target vehicle, wherein the second obstacle information comprises position information of a second obstacle, and the second obstacle is an obstacle in a preset area;

a second redundancy removing unit, configured to remove redundancy from the first obstacle information by the target vehicle to obtain first target obstacle information, where the first target obstacle information is position information of a first target obstacle, and the first target obstacle is the first obstacle that matches the second obstacle;

a second matching unit, configured to match the first target obstacle information with the second obstacle information by the target vehicle to obtain second target obstacle information, where the second target obstacle information at least includes the first target obstacle information;

and the control unit is used for controlling the running of the vehicle by the target vehicle according to the second target obstacle information.

14. A computer-readable storage medium, characterized in that the storage medium comprises a stored program, wherein the program performs the method of any one of claims 1 to 11.

15. A processor, characterized in that the processor is configured to run a program, wherein the program when running performs the method of any of claims 1 to 11.

16. A vehicle, characterized by comprising: one or more processors, memory, and one or more programs stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for performing the method of any of claims 1-11.

Technical Field

The application relates to the field of automatic driving, in particular to a detection method, a detection device, a control method, a control device, a computer readable storage medium, a processor and an intelligent driving vehicle of the intelligent driving vehicle.

Background

In the prior art, the automatic driving vehicle often has driving faults in a construction area, and the reason is mainly that the result of detecting obstacles in the construction area by the automatic driving vehicle is inaccurate.

Therefore, a method capable of accurately detecting an obstacle in a construction area is required.

The above information disclosed in this background section is only for enhancement of understanding of the background of the technology described herein and, therefore, certain information may be included in the background that does not form the prior art that is already known in this country to a person of ordinary skill in the art.

Disclosure of Invention

The application mainly aims to provide a detection method, a detection device, a control method, a control device, a computer readable storage medium, a processor and an intelligent driving vehicle for the intelligent driving vehicle, so as to solve the problem that the result of detecting an obstacle in a construction area by an automatic driving vehicle is inaccurate in the prior art.

According to an aspect of an embodiment of the present invention, there is provided a detection method of an intelligent driving vehicle, including: receiving a semantic map of a construction area sent by a control center, wherein the semantic map of the construction area comprises first obstacle information, the first obstacle information comprises position information of a first obstacle, and the first obstacle is an obstacle in the construction area; detecting second obstacle information in real time, wherein the second obstacle information comprises position information of a second obstacle, and the second obstacle is an obstacle in a preset area; removing redundancy of the first obstacle information to obtain first target obstacle information, wherein the first target obstacle information is position information of a first target obstacle, and the first target obstacle is the first obstacle matched with the second obstacle; and matching the first target obstacle information with the second obstacle information to obtain second target obstacle information, wherein the second target obstacle information at least comprises the first target obstacle information.

Optionally, performing redundancy removal on the first obstacle information to obtain first target obstacle information, including: matching the first obstacle information and the second obstacle information to determine whether the first obstacle matching the second obstacle exists; and in the case that the first obstacle matched with the second obstacle exists, determining the first obstacle matched with the second obstacle as the first target obstacle, and obtaining the first target obstacle information in the semantic map.

Optionally, the determining, by matching the first obstacle information with the second obstacle information to determine whether the first obstacle matched with the second obstacle exists includes: comparing the position information of the grid where the first obstacle is located with the position information of the grid where the second obstacle is located; determining that the first obstacle matched with the second obstacle exists under the condition that the grid where the first obstacle is located and the grid where the second obstacle is located have more than a preset number of same grids.

Optionally, matching the first target obstacle information with the second obstacle information to obtain second target obstacle information, including: acquiring the first target obstacle information; determining whether the second obstacle that does not match the first obstacle is present; in the presence of the second obstacle that does not match the first obstacle, determining that the second obstacle that does not match the first obstacle is a third target obstacle, and acquiring the third target obstacle information in the second obstacle information, the second target obstacle information including the third target obstacle information and the first target obstacle information.

Optionally, the determining whether the second obstacle that does not match the first obstacle exists includes: comparing the position information of the grid where the first obstacle is located with the position information of the grid where the second obstacle is located; determining that there is the second obstacle that does not match the first obstacle if the grid where the first obstacle is located and the grid where the second obstacle is located have less than or equal to a predetermined number of the same grids.

Optionally, after performing redundancy elimination on the first obstacle information to obtain first target obstacle information, the method further includes: and sending the first target obstacle information to the control center, and updating the semantic map by the control center according to the first target obstacle information.

Optionally, detecting second obstacle information in real time includes: acquiring a 2D map in a preset area in real time; implementing acquisition of a 3D point cloud map of the predetermined area; and determining the second obstacle information according to the 2D map and the 3D point cloud map.

According to another aspect of the embodiments of the present invention, there is also provided a control method of an intelligent driving vehicle, including: a target vehicle receives a semantic map of a construction area sent by a control center, wherein the semantic map of the construction area comprises first obstacle information, the first obstacle information comprises position information of a first obstacle, and the first obstacle is an obstacle in the construction area; the target vehicle detects second obstacle information in real time, wherein the second obstacle information comprises position information of a second obstacle, and the second obstacle is an obstacle in a preset area; the target vehicle performs redundancy elimination on the first obstacle information to obtain first target obstacle information, wherein the first target obstacle information is position information of a first target obstacle, and the first target obstacle is the first obstacle matched with the second obstacle; the target vehicle matches the first target obstacle information with the second obstacle information to obtain second target obstacle information, wherein the second target obstacle information at least comprises the first target obstacle information; and the target vehicle controls the running of the vehicle according to the second target obstacle information.

Optionally, the performing, by the target vehicle, redundancy removal on the first obstacle information to obtain first target obstacle information includes: matching the first obstacle information and the second obstacle information to determine whether the first obstacle matching the second obstacle exists; and under the condition that the first obstacle matched with the second obstacle exists, determining the first obstacle matched with the second obstacle as the first target obstacle, and obtaining the first target obstacle information in the semantic map.

Optionally, the matching, by the target vehicle, the first target obstacle information and the second obstacle information to obtain second target obstacle information includes: acquiring the first target obstacle information; determining whether the second obstacle that does not match the first obstacle is present; in the presence of the second obstacle that does not match the first obstacle, determining that the second obstacle that does not match the first obstacle is a third target obstacle, and acquiring the third target obstacle information in the second obstacle information, the second target obstacle information including the third target obstacle information and the first target obstacle information.

According to another aspect of the embodiment of the present invention, there is provided a detection apparatus for an intelligent driving vehicle, including a first receiving unit, a first detecting unit, a first redundancy removing unit, and a first matching unit, where the first receiving unit is configured to receive a semantic map of a construction area sent by a control center, the semantic map of the construction area includes first obstacle information, the first obstacle information includes position information of a first obstacle, and the first obstacle is an obstacle in the construction area; the first detection unit is used for detecting second obstacle information in real time, wherein the second obstacle information comprises position information of a second obstacle, and the second obstacle is an obstacle in a preset area; the first redundancy removing unit is used for removing redundancy of the first obstacle information to obtain first target obstacle information, wherein the first target obstacle information is position information of a first target obstacle, and the first target obstacle is the first obstacle matched with the second obstacle; the first matching unit is used for matching the first target obstacle information with the second obstacle information to obtain second target obstacle information, and the second target obstacle information at least comprises the first target obstacle information.

According to another aspect of the embodiment of the present invention, there is further provided a control device for an intelligent driving vehicle, including a second receiving unit, a second detecting unit, a second redundancy removing unit, a second matching unit and a control unit, wherein the second receiving unit is configured to receive, by a target vehicle, a semantic map of a construction area sent by a control center, the semantic map of the construction area includes first obstacle information, the first obstacle information includes position information of a first obstacle, and the first obstacle is an obstacle in the construction area; the second detection unit is used for detecting second obstacle information in real time by the target vehicle, wherein the second obstacle information comprises position information of a second obstacle, and the second obstacle is an obstacle in a preset area; the second redundancy removing unit is used for removing redundancy of the first obstacle information by the target vehicle to obtain first target obstacle information, wherein the first target obstacle information is position information of a first target obstacle, and the first target obstacle is the first obstacle matched with the second obstacle; the second matching unit is used for the target vehicle to match the first target obstacle information with the second obstacle information to obtain second target obstacle information, and the second target obstacle information at least comprises the first target obstacle information; and the control unit is used for controlling the running of the vehicle by the target vehicle according to the second target obstacle information.

According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium including a stored program, wherein the program executes any one of the methods.

According to another aspect of the embodiments of the present invention, there is also provided a processor, configured to execute a program, where the program executes any one of the methods.

There is also provided, in accordance with yet another aspect of an embodiment of the present invention, a smart driving vehicle, including one or more processors, memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for performing any of the methods described herein.

The application provides a detection method of an intelligent driving vehicle, which firstly receives a semantic map of a construction area sent by a control center, the semantic map of the construction area comprises first obstacle information, the first obstacle information comprises position information of a first obstacle, the first obstacle is an obstacle in the construction area and detects second obstacle information in real time, the second obstacle information comprises position information of a second obstacle, the second obstacle is an obstacle in a preset area and removes redundancy of the first obstacle information, first target obstacle information is obtained after the redundancy is removed, the first target obstacle information is the position information of a first target obstacle, and the first target obstacle is the first obstacle matched with the second obstacle, and finally, matching the first target obstacle information with the second obstacle information to obtain second target obstacle information, wherein the second target obstacle information at least comprises the first target obstacle information. The method comprises the steps of removing redundancy of first obstacle information according to the first obstacle information and the second obstacle information to obtain first target obstacle information, matching the first target obstacle information with the second obstacle information to obtain second target obstacle information, ensuring that the obtained second target obstacle information is more accurate and basically matched with the position of an obstacle in an actual construction area, and ensuring that the obtained obstacle information is the second target obstacle information and comprises the first target obstacle information in a semantic map, wherein the first target obstacle information in the semantic map is more accurate and stable relative to the second obstacle information detected in real time, the second target obstacle information is further ensured to be more accurate, and the problem that the result of detecting the obstacle in the construction area by the existing automatic driving vehicle is inaccurate is solved, the influence of the obstacles in the construction area on driving is avoided better according to the obtained information of the second target obstacles, and the driving safety is ensured.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application. In the drawings:

FIG. 1 shows a schematic flow diagram generated by a detection method of a smart-driving vehicle according to an embodiment of the present application;

FIG. 2 shows a flow diagram generated by a control method of a smart driving vehicle according to an embodiment of the present application;

FIG. 3 shows a schematic diagram of a detection arrangement of a smart driving vehicle according to an embodiment of the present application;

fig. 4 shows a schematic diagram of a control device of a smart driving vehicle according to an embodiment of the application.

Detailed Description

It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

As described in the background art, in order to solve the above-mentioned problems, in the prior art, in which the result of detecting an obstacle in a construction area by an autonomous vehicle is inaccurate, in an exemplary embodiment of the present application, a detection method, a detection apparatus, a control method, a control apparatus, a computer-readable storage medium, a processor, and an intelligent driving vehicle are provided.

According to an embodiment of the present application, a detection method of an intelligent driving vehicle is provided.

Fig. 1 is a flowchart of a detection method of an intelligent driving vehicle according to an embodiment of the present application. As shown in fig. 1, the method comprises the steps of:

step S101, receiving a semantic map of a construction area sent by a control center, wherein the semantic map of the construction area comprises first obstacle information, the first obstacle information comprises position information of a first obstacle, and the first obstacle is an obstacle in the construction area;

step S102, detecting second obstacle information in real time, wherein the second obstacle information comprises position information of a second obstacle, and the second obstacle is an obstacle in a preset area;

step S103, removing redundancy from the first obstacle information to obtain first target obstacle information, where the obstacle is a real obstacle, the first target obstacle information is position information of a first target obstacle, and the first target obstacle is the first obstacle matched with the second obstacle, and may be specifically matched by position and shape;

step S104 is to match the first target obstacle information with the second obstacle information to obtain second target obstacle information, where the second target obstacle information at least includes the first target obstacle information.

The detection method of the intelligent driving vehicle comprises the steps of firstly receiving a semantic map of a construction area sent by a control center, wherein the semantic map of the construction area comprises first obstacle information, the first obstacle information comprises position information of a first obstacle, the first obstacle is an obstacle in the construction area, and real-time detection is carried out on second obstacle information, the second obstacle information comprises position information of a second obstacle, the second obstacle is an obstacle in a preset area, redundancy removal is carried out on the first obstacle information, first target obstacle information is obtained after the redundancy removal, the first target obstacle information is the position information of a first target obstacle, the first target obstacle is the first obstacle matched with the second obstacle, and finally the first target obstacle information is matched with the second obstacle information, and obtaining second target obstacle information, wherein the second target obstacle information at least comprises the first target obstacle information. The method comprises the steps of removing redundancy of first obstacle information according to the first obstacle information and the second obstacle information to obtain first target obstacle information, matching the first target obstacle information with the second obstacle information to obtain second target obstacle information, ensuring that the obtained second target obstacle information is more accurate and basically matched with the position of an obstacle in an actual construction area, and ensuring that the finally obtained obstacle information is the second target obstacle information and comprises the first target obstacle information in a semantic map, wherein the first target obstacle information in the semantic map is more accurate and stable relative to the second obstacle information detected in real time, the obtained second target obstacle information is further ensured to be more accurate, and the problem that the result of detecting the obstacle in the construction area by the existing automatic driving vehicle is inaccurate is solved, the influence of the obstacles in the construction area on driving is avoided better according to the obtained information of the second target obstacles, and the driving safety is ensured.

It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.

The execution subject of the method is the vehicle or a processor in the vehicle. Moreover, the vehicles in the application are all intelligent driving vehicles.

In a specific embodiment of the application, the control center can push map updating information including semantic information such as certain road closure and obstacles to automatic driving vehicles (intelligent driving vehicles) in a certain range area, and after the vehicle identifies semantics, the route can be avoided when planning the route.

In an actual application process, a person skilled in the art may use an existing construction method to implement the construction of the semantic map of the construction area, and in a specific embodiment, in the control center, the construction method of the semantic map of the construction area includes: determining a construction obstacle area in a 3D point cloud map, wherein the construction obstacle area is an obstacle area related to a construction area and comprises the first obstacle; acquiring and storing position information of a plurality of obstacle points of the construction obstacle area in a 3D point cloud map, wherein the position information comprises position information of the first obstacle, and the obstacle points are points in the construction obstacle area; and generating a semantic map of the construction area according to the position information of the plurality of obstacle points when the construction obstacle area is not detected within a preset time period.

According to a specific embodiment of the present application, the performing redundancy removal on the first obstacle information to obtain first target obstacle information includes: matching the first obstacle information with the second obstacle information to determine whether the first obstacle matching the second obstacle exists; when the first obstacle matching the second obstacle exists, the first obstacle matching the second obstacle is determined as the first target obstacle, and the first target obstacle information in the semantic map is obtained. According to the method, the first obstacle information and the second obstacle information are matched, and the first obstacle matched with the second obstacle is determined to be the first target obstacle under the condition that the first obstacle matched with the second obstacle exists, so that the obtained first target obstacle is accurate, the obstacle information of an actual construction area is more fit, and an accurate data basis is provided for obtaining the second target obstacle according to the first target obstacle subsequently.

In order to further ensure that the obtained first target obstacle is accurate, and further ensure that the obstacle of the construction area can be accurately determined, and the driving fault is avoided, according to another specific embodiment of the present application, the position information of the first obstacle is the position information of the grid where the first obstacle is located, the position information of the second obstacle is the position information of the grid where the second obstacle is located, and the first obstacle information and the second obstacle information are matched to determine whether the first obstacle matched with the second obstacle exists, the method includes: comparing the position information of the grid where the first obstacle is located with the position information of the grid where the second obstacle is located; and determining that the first obstacle matched with the second obstacle exists under the condition that the grids where the first obstacle is located and the grids where the second obstacle is located have more than a preset number of same grids. This further ensures that the determined first obstacle, i.e. the first target obstacle, matches the second obstacle more accurately.

Of course, in practical application, other methods may be used to perform redundancy elimination on the first obstacle information, and those skilled in the art may select an appropriate method to perform redundancy elimination according to practical situations.

In an actual application process, due to a difference between a time for constructing a semantic map and a current driving time of a vehicle, the first target obstacle information obtained through redundancy elimination may be different from obstacle information of a current construction area, and in order to determine obstacle information more accurately and further ensure driving safety in this case, in an embodiment of the present application, the matching of the first target obstacle information and the second obstacle information to obtain second target obstacle information includes: acquiring the first target obstacle information; determining whether there is the second obstacle that does not match the first obstacle; in a case where there is the second obstacle that does not match the first obstacle, determining that the second obstacle that does not match the first obstacle is a third target obstacle, and acquiring the third target obstacle information in the second obstacle information, the second target obstacle information including the third target obstacle information and the first target obstacle information. In the method, when the second obstacle which is not matched with the first obstacle exists, the second obstacle which is not matched with the first obstacle is determined as a third target obstacle, and the third target obstacle information and the first target obstacle information form the second target obstacle information, so that the obtained second target obstacle information is more accurate, the information is basically matched with the position of the obstacle in the current construction area, and the driving safety is further ensured.

Specifically, the second obstacle information is matched with the first obstacle information (first target obstacle information) after redundancy removal, the matched first obstacle is output for the second obstacle which can be successfully matched, and the part of second obstacle information, namely the third target obstacle information, is directly output for the second obstacle information which cannot be matched.

In order to further ensure that the obtained third target obstacle is accurate, and further ensure that the obstacle in the construction area can be accurately determined, and the driving fault is avoided, in another specific embodiment of the present application, the position information of the first obstacle is the position information of the grid where the first obstacle is located, the position information of the second obstacle is the position information of the grid where the second obstacle is located, and whether the second obstacle that is not matched with the first obstacle exists is determined, including: comparing the position information of the grid where the first obstacle is located with the position information of the grid where the second obstacle is located; and determining that the second obstacle which does not match the first obstacle exists when the grid where the first obstacle is located and the grid where the second obstacle is located have the same number of grids which is less than or equal to a predetermined number.

In another specific embodiment of the present application, after performing redundancy elimination on the first obstacle information to obtain first target obstacle information, the method further includes: and sending the first target obstacle information to the control center, and updating the semantic map by the control center according to the first target obstacle information. The first target obstacle information obtained by redundancy removal is sent to the control center, so that the control center updates the semantic map according to the first target obstacle information, the obstacle information in the semantic map after updating is further ensured to be basically consistent with the obstacle information of an actual construction area, the obstacle information of the construction area can be accurately determined according to the semantic map after updating, and the driving fault of a vehicle in the construction area is further avoided.

In order to obtain the second obstacle information more accurately and efficiently, in an actual application process, the detecting the second obstacle information in real time includes: acquiring a 2D map in a preset area in real time; acquiring a 3D point cloud map of the preset area; and determining the second obstacle information according to the 2D map and the 3D point cloud map. The second obstacle information is determined by acquiring the 2D map and the 3D point cloud map in a preset area in real time and according to the 2D map and the 3D point cloud map, and the acquired second obstacle information is ensured to be accurate. The predetermined area may be in an area 40m from the vehicle.

Of course, in practical application, the second obstacle information may also be obtained in other manners, and a person skilled in the art may select an appropriate manner to obtain the second obstacle area information according to the practical situation, which is not described herein again.

According to another exemplary embodiment of the present application, as shown in fig. 2, there is provided a control method of an intelligent driving vehicle, the method including the steps of:

step S201, a target vehicle receives a semantic map of a construction area sent by a control center, wherein the semantic map of the construction area comprises first obstacle information, the first obstacle information comprises position information of a first obstacle, and the first obstacle is an obstacle in the construction area;

step S202, detecting second obstacle information in real time by the target vehicle, wherein the second obstacle information comprises position information of a second obstacle, and the second obstacle is an obstacle in a preset area;

step S203, the target vehicle performs redundancy elimination on the first obstacle information to obtain first target obstacle information, where the first target obstacle information is position information of a first target obstacle, and the first target obstacle is the first obstacle matched with the second obstacle;

step S204, the target vehicle matches the first target obstacle information with the second obstacle information to obtain second target obstacle information, where the second target obstacle information at least includes the first target obstacle information;

in step S205, the target vehicle controls the traveling of the vehicle based on the second target obstacle information.

In the method for controlling the intelligent driving vehicle, the target vehicle firstly receives a semantic map of a construction area sent by a control center, the semantic map of the construction area comprises first obstacle information, the first obstacle information comprises position information of a first obstacle, the first obstacle is an obstacle in the construction area, the target vehicle detects second obstacle information in real time, the second obstacle information comprises position information of a second obstacle, the second obstacle is an obstacle in a preset area, the target vehicle performs redundancy removal on the first obstacle information to obtain first target obstacle information, the first target obstacle information is the position information of a first target obstacle, and the first target obstacle is the first obstacle matched with the second obstacle, the target vehicle matches the first target obstacle information with the second obstacle information to obtain second target obstacle information, the second target obstacle information including at least the first target obstacle information, and finally, the target vehicle controls the vehicle to travel according to the second target obstacle information. In the control method of the intelligent driving vehicle, the target vehicle performs redundancy elimination on the first obstacle information according to the first obstacle information and the second obstacle information to obtain the first target obstacle information, then matches the first target obstacle information with the second obstacle information to obtain the second target obstacle information, controls the driving of the vehicle according to the second target obstacle information to ensure that the obtained second target obstacle information is more accurate and basically matched with the position of an obstacle in an actual construction area, ensures that the vehicle can better regulate the influence of the obstacle in the construction area on the driving according to the obtained second target obstacle information, and finally obtains the obstacle information as the first target obstacle information in a semantic map included in the second target obstacle information, compared with the second obstacle information detected in real time, the first target obstacle information in the semantic map is more accurate and stable, the second target obstacle information is further ensured to be more accurate, the problem that the result of detecting the obstacle in the construction area by the existing automatic driving vehicle is inaccurate is solved, and the driving safety is ensured.

According to another specific embodiment of the present application, the redundancy elimination of the first obstacle information by the target vehicle to obtain the first target obstacle information includes: matching the first obstacle information with the second obstacle information to determine whether the first obstacle matching the second obstacle exists; when the first obstacle matching the second obstacle exists, the first obstacle matching the second obstacle is determined as the first target obstacle, and the first target obstacle information in the semantic map is obtained. In the method, the target vehicle determines that the first obstacle matched with the second obstacle is the first target obstacle by matching the first obstacle information with the second obstacle information under the condition that the first obstacle matched with the second obstacle exists, so that the obtained first target obstacle is more accurate and is more suitable for the obstacle information of an actual construction area, a more accurate data basis is provided for controlling the vehicle to run according to the second target obstacle, and the running safety of the vehicle is ensured.

In order to further ensure that the obtained first target obstacle is accurate, and further ensure that the obstacle of the construction area can be determined accurately, and the driving fault is avoided, according to another specific embodiment of the present application, the position information of the first obstacle is the position information of the grid where the first obstacle is located, and the position information of the second obstacle is the position information of the grid where the second obstacle is located, and the first obstacle information and the second obstacle information are matched to determine whether the first obstacle matched with the second obstacle exists, the method includes: comparing the position information of the grid where the first obstacle is located with the position information of the grid where the second obstacle is located; and determining that the first obstacle matched with the second obstacle exists under the condition that the grids where the first obstacle is located and the grids where the second obstacle is located have more than a preset number of same grids. This further ensures that the determined first obstacle, i.e. the first target obstacle, matches the second obstacle more accurately.

In an actual application process, due to a difference between a time for constructing a semantic map and a driving time of a current vehicle, the first target obstacle information obtained through redundancy elimination may be different from obstacle information of a current construction area, and in order that, in such a case, a vehicle can more accurately avoid the obstacle information of the construction area, and driving safety is further ensured, in an embodiment of the present application, the obtaining, by the target vehicle, second target obstacle information by matching the first target obstacle information with the second obstacle information includes: acquiring the first target obstacle information; determining whether there is the second obstacle that does not match the first obstacle; in a case where there is the second obstacle that does not match the first obstacle, determining that the second obstacle that does not match the first obstacle is a third target obstacle, and acquiring the third target obstacle information in the second obstacle information, the second target obstacle information including the third target obstacle information and the first target obstacle information. In the method, when the second obstacle which is not matched with the first obstacle exists, the second obstacle which is not matched with the first obstacle is determined as a third target obstacle, and the third target obstacle information and the first target obstacle information form the second target obstacle information, so that the obtained second target obstacle information is more accurate, the vehicle which runs according to the second target obstacle information is further ensured, the obstacle in a construction area can be better avoided, and the running safety is further ensured.

The embodiment of the present application further provides a detection device for an intelligent driving vehicle, and it should be noted that the detection device for an intelligent driving vehicle according to the embodiment of the present application may be used to execute the detection method for an intelligent driving vehicle according to the embodiment of the present application. The following describes a detection device for an intelligent driving vehicle provided in an embodiment of the present application.

Fig. 3 is a schematic diagram of a detection device of an intelligent driving vehicle according to an embodiment of the application. As shown in fig. 3, the apparatus includes a first receiving unit 10, a first detecting unit 20, a first redundancy removing unit 30 and a first matching unit 40, wherein the first receiving unit 10 is configured to receive a semantic map of a construction area sent by a control center, the semantic map of the construction area includes first obstacle information, the first obstacle information includes position information of a first obstacle, and the first obstacle is an obstacle in the construction area; the first detection unit 20 is configured to detect second obstacle information in real time, where the second obstacle information includes position information of a second obstacle, and the second obstacle is an obstacle in a predetermined area; the first redundancy elimination unit 30 is configured to eliminate redundancy of the first obstacle information to obtain first target obstacle information, where the first target obstacle information is position information of a first target obstacle, and the first target obstacle is the first obstacle matching the second obstacle; the first matching means 40 is configured to match the first target obstacle information with the second obstacle information to obtain second target obstacle information, where the second target obstacle information at least includes the first target obstacle information.

The detection device of the intelligent driving vehicle receives the semantic map of the construction area sent by the control center through the first receiving unit, the semantic map of the construction area includes first obstacle information including position information of a first obstacle that is an obstacle in the construction area, detecting second obstacle information in real time by the first detection unit, the second obstacle information including position information of a second obstacle, the second obstacle being an obstacle in a predetermined area, the first obstacle information is subjected to redundancy removal through the first redundancy removing unit, first target obstacle information is obtained after redundancy removal, the first target obstacle information is position information of a first target obstacle, and the first target obstacle is the first obstacle matching the second obstacle; and obtaining second target obstacle information by matching the first target obstacle information with the second obstacle information by the first matching means, wherein the second target obstacle information at least includes the first target obstacle information. The device performs redundancy removal on the first obstacle information according to the first obstacle information and the second obstacle information to obtain the first target obstacle information, then matches the first target obstacle information with the second obstacle information to obtain the second target obstacle information, ensures that the obtained second target obstacle information is more accurate and basically matched with the position of an obstacle in an actual construction area, and finally obtains the obstacle information which is the second target obstacle information and comprises the first target obstacle information in a semantic map, wherein the first target obstacle information in the semantic map is more accurate and stable relative to the second obstacle information detected in real time, further ensures that the obtained second target obstacle information is more accurate, and solves the problem that the result of detecting the obstacle in the construction area by the existing automatic driving vehicle is inaccurate, the influence of the obstacles in the construction area on driving is avoided better according to the obtained information of the second target obstacles, and the driving safety is ensured.

In an actual application process, a person skilled in the art may use an existing building device to implement building of a semantic map of a construction area, and in a specific embodiment, in a control center, a method for building a semantic map of a construction area includes: determining a construction obstacle area in a 3D point cloud map, wherein the construction obstacle area is an obstacle area related to a construction area and comprises the first obstacle; acquiring and storing position information of a plurality of obstacle points of the construction obstacle area in a 3D point cloud map, wherein the position information comprises position information of the first obstacle, and the obstacle points are points in the construction obstacle area; and generating a semantic map of the construction area according to the position information of the plurality of obstacle points when the construction obstacle area is not detected within a preset time period.

According to a specific embodiment of the present application, the first redundancy removing unit includes a first matching module and a first determining module, wherein the first matching module is configured to match the first obstacle information with the second obstacle information to determine whether the first obstacle matching with the second obstacle exists; the first determining module is configured to determine that the first obstacle matching the second obstacle is the first target obstacle and obtain the first target obstacle information in the semantic map, when the first obstacle matching the second obstacle exists. The device determines the first obstacle matched with the second obstacle as the first target obstacle by matching the first obstacle information with the second obstacle information under the condition that the first obstacle matched with the second obstacle exists, so that the obtained first target obstacle is more accurate and is more suitable for the obstacle information of an actual construction area, and more accurate data basis is provided for obtaining the second target obstacle according to the first target obstacle subsequently.

In order to further ensure that the obtained first target obstacle is accurate, and further ensure that the obstacle of the construction area can be accurately determined, and the driving fault is avoided, according to another specific embodiment of the present application, the position information of the first obstacle is the position information of the grid where the first obstacle is located, the position information of the second obstacle is the position information of the grid where the second obstacle is located, the first matching module includes a first comparison submodule and a first determination submodule, wherein the first comparison submodule is configured to compare the position information of the grid where the first obstacle is located and the position information of the grid where the second obstacle is located; the first determination submodule is configured to determine that the first obstacle matching the second obstacle exists when the grid where the first obstacle is located and the grid where the second obstacle is located have more than a predetermined number of the same grids. This further ensures that the determined first obstacle, i.e. the first target obstacle, matches the second obstacle more accurately.

In an actual application process, due to a difference between a time for constructing a semantic map and a driving time of a current vehicle, the first target obstacle information obtained through redundancy removal may be different from obstacle information of a current construction area, and in order to determine obstacle information more accurately and further ensure driving safety in such a case, in an embodiment of the present application, the first matching unit includes a first obtaining module, a second determining module, and a third determining module, where the first obtaining module is configured to obtain the first target obstacle information; the second determining module is configured to determine whether the second obstacle that does not match the first obstacle exists; the third determining module is configured to determine, when the second obstacle that does not match the first obstacle exists, that the second obstacle that does not match the first obstacle is a third target obstacle, and acquire the third target obstacle information in the second obstacle information, where the second target obstacle information includes the third target obstacle information and the first target obstacle information. In the case that the second obstacle that does not match the first obstacle exists, the apparatus determines the second obstacle that does not match the first obstacle as a third target obstacle, and combines the third target obstacle information and the first target obstacle information into the second target obstacle information, thereby further ensuring that the obtained second target obstacle information is accurate, further ensuring that the information substantially matches the position of the obstacle in the current construction area, and further ensuring the driving safety.

In order to further ensure that the obtained third target obstacle is accurate, and further ensure that the obstacle of the construction area can be accurately determined, and the driving fault is avoided, in yet another specific embodiment of the present application, the position information of the first obstacle is the position information of the grid where the first obstacle is located, the position information of the second obstacle is the position information of the grid where the second obstacle is located, the second determining module includes a second comparing submodule and a second determining submodule, wherein the second comparing submodule is configured to compare the position information of the grid where the first obstacle is located and the position information of the grid where the second obstacle is located; the second determination submodule is configured to determine that the second obstacle that does not match the first obstacle exists, when the number of the same grids is smaller than or equal to a predetermined number in the grid where the first obstacle is located and the number of the same grids in the grid where the second obstacle is located.

In another specific embodiment of the present application, the apparatus further includes a sending unit, where the sending unit is configured to perform redundancy elimination on the first obstacle information to obtain first target obstacle information, and then send the first target obstacle information to the control center, where the control center updates the semantic map according to the first target obstacle information. The first target obstacle information obtained by redundancy removal is sent to the control center, so that the control center updates the semantic map according to the first target obstacle information, the obstacle information in the semantic map after updating is further ensured to be basically consistent with the obstacle information of an actual construction area, the obstacle information of the construction area can be accurately determined according to the semantic map after updating, and the driving fault of a vehicle in the construction area is further avoided.

In order to acquire the second obstacle information more accurately and efficiently, in an actual application process, the first detection unit includes a second acquisition module, a third acquisition module and a fourth determination module, wherein the second acquisition module is configured to acquire a 2D map in a predetermined area in real time; the third acquisition module is used for acquiring the 3D point cloud map of the preset area; the fourth determining module is configured to determine the second obstacle information according to the 2D map and the 3D point cloud map. The second obstacle information is determined by acquiring the 2D map and the 3D point cloud map in a preset area in real time and according to the 2D map and the 3D point cloud map, and the acquired second obstacle information is ensured to be accurate. The predetermined area may be in an area 40m from the vehicle.

According to still another exemplary embodiment of the present application, there is provided a control apparatus of a vehicle, as shown in fig. 4, the apparatus includes a second receiving unit 50, a second detecting unit 60, a second redundancy removing unit 70, a second matching unit 80, and a control unit 90, wherein the second receiving unit 50 is configured to receive, by a target vehicle, a semantic map of a construction area transmitted by a control center, the semantic map of the construction area includes first obstacle information, the first obstacle information includes position information of a first obstacle, and the first obstacle is an obstacle in the construction area; the second detecting unit 60 is configured to detect second obstacle information in real time by the target vehicle, where the second obstacle information includes position information of a second obstacle, and the second obstacle is an obstacle in a predetermined area; the second redundancy elimination unit 70 is configured to eliminate redundancy of the first obstacle information by the target vehicle to obtain first target obstacle information, where the first target obstacle information is position information of a first target obstacle, and the first target obstacle is the first obstacle matching the second obstacle; the second matching means 80 is configured to match the first target obstacle information with the second obstacle information by the target vehicle to obtain second target obstacle information, where the second target obstacle information includes at least the first target obstacle information; the control unit 90 is configured to control the traveling of the vehicle by the target vehicle based on the second target obstacle information.

The vehicle control device receives, by a second receiving means, a semantic map of a construction area transmitted from a control center by a target vehicle, the semantic map of the construction area including first obstacle information, the first obstacle information including position information of a first obstacle, the first obstacle being an obstacle in the construction area, the target vehicle detects second obstacle information in real time by the second detecting means, the second obstacle information including position information of a second obstacle, the second obstacle being an obstacle in a predetermined area, the target vehicle performs redundancy elimination on the first obstacle information by the second redundancy eliminating means, and first target obstacle information is obtained after the redundancy elimination, the first target obstacle information being position information of a first target obstacle, the first target obstacle being the first obstacle matching the second obstacle, the target vehicle matches the first target obstacle information with the second obstacle information by the second matching means to obtain second target obstacle information, the second target obstacle information including at least the first target obstacle information, and the target vehicle controls the traveling of the vehicle based on the second target obstacle information by the control means. In the control device of the vehicle, the target vehicle performs redundancy elimination on the first obstacle information according to the first obstacle information and the second obstacle information to obtain the first target obstacle information, then matches the first target obstacle information with the second obstacle information to obtain the second target obstacle information, controls the running of the vehicle according to the second target obstacle information, ensures that the obtained second target obstacle information is more accurate and basically matched with the position of an obstacle in an actual construction area, ensures that the vehicle can better avoid the influence of the obstacle in the construction area on the running according to the obtained second target obstacle information, and the finally obtained obstacle information is the second target obstacle information which comprises the first target obstacle information in a semantic map and is relative to the second obstacle information detected in real time, the first target obstacle information in the semantic map is more accurate and stable, the second target obstacle information is further ensured to be more accurate, the problem that the result of detecting obstacles in a construction area by the existing automatic driving vehicle is inaccurate is solved, and the driving safety is ensured.

According to another specific embodiment of the present application, the second redundancy removing unit includes a second matching module and a fifth determining module, wherein the second matching module is configured to match the first obstacle information with the second obstacle information to determine whether the first obstacle matching with the second obstacle exists; the fifth determining module is configured to determine that the first obstacle matching the second obstacle is the first target obstacle and obtain the first target obstacle information in the semantic map, if the first obstacle matching the second obstacle exists. According to the device, the target vehicle determines that the first obstacle matched with the second obstacle is the first target obstacle by matching the first obstacle information with the second obstacle information under the condition that the first obstacle matched with the second obstacle exists, so that the obtained first target obstacle is accurate and is more suitable for the obstacle information of an actual construction area, an accurate data basis is provided for controlling the vehicle to run according to the second target obstacle, and the running safety of the vehicle is guaranteed.

In order to further ensure that the obtained first target obstacle is accurate, and further ensure that the obstacle of the construction area can be determined accurately, and the driving fault is avoided, according to another specific embodiment of the present application, the position information of the first obstacle is the position information of the grid where the first obstacle is located, the position information of the second obstacle is the position information of the grid where the second obstacle is located, the second matching module includes a third comparison submodule and a third determination submodule, wherein the third comparison submodule is configured to compare the position information of the grid where the first obstacle is located and the position information of the grid where the second obstacle is located; the third determination submodule is configured to determine that the first obstacle matching the second obstacle exists when the grid where the first obstacle is located and the grid where the second obstacle is located have more than a predetermined number of the same grids. This further ensures that the determined first obstacle, i.e. the first target obstacle, matches the second obstacle more accurately.

In an actual application process, due to a difference between a time for constructing a semantic map and a driving time of a current vehicle, the first target obstacle information obtained through redundancy removal may be different from obstacle information of a current construction area, and in order that the vehicle can more accurately avoid the obstacle information of the construction area in such a situation, driving safety is further ensured, in an embodiment of the present application, the second matching unit includes a third obtaining module, a sixth determining module, and a seventh determining module, where the third obtaining module is configured to obtain the first target obstacle information; the sixth determining module is configured to determine whether the second obstacle that does not match the first obstacle exists; the seventh determining module is configured to determine, when the second obstacle that does not match the first obstacle exists, that the second obstacle that does not match the first obstacle is a third target obstacle, and acquire the third target obstacle information in the second obstacle information, where the second target obstacle information includes the third target obstacle information and the first target obstacle information. In the device, when the second obstacle which is not matched with the first obstacle exists, the second obstacle which is not matched with the first obstacle is determined as a third target obstacle, and the third target obstacle information and the first target obstacle information form the second target obstacle information, so that the obtained second target obstacle information is more accurate, the vehicle which runs according to the second target obstacle information is further ensured, the obstacle in a construction area can be better avoided, and the running safety is further ensured.

In order to further ensure that the obtained third target obstacle is accurate, and further ensure that the obstacle of the construction area can be accurately determined, and the driving fault is avoided, in another specific embodiment of the present application, the position information of the first obstacle is the position information of the grid where the first obstacle is located, the position information of the second obstacle is the position information of the grid where the second obstacle is located, the sixth determining module includes a fourth comparing submodule and a fourth determining submodule, wherein the fourth comparing submodule is configured to compare the position information of the grid where the first obstacle is located and the position information of the grid where the second obstacle is located; the fourth determination submodule is configured to determine that the second obstacle that does not match the first obstacle exists, when the number of the same grids is smaller than or equal to a predetermined number in the grid where the first obstacle is located and the number of the same grids in the grid where the second obstacle is located.

The detection device of the intelligent driving vehicle comprises a processor and a memory, wherein the first receiving unit, the first detection unit, the first redundancy removing unit, the first matching unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.

The second receiving unit, the second detecting unit, the second redundancy removing unit, the second matching unit, the control unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.

The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more than one, and the problem that the result of detecting the obstacle in the construction area by the automatic driving vehicle in the prior art is inaccurate is solved by adjusting the kernel parameters.

The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.

An embodiment of the present invention provides a storage medium having a program stored thereon, the program implementing the detection method of the above-described intelligent driving vehicle and the control method of the above-described intelligent driving vehicle when executed by a processor.

The embodiment of the invention provides a processor, wherein the processor is used for running a program, and the detection method of the intelligent driving vehicle and the control method of the intelligent driving vehicle are executed when the program runs.

The embodiment of the invention provides equipment, which comprises a processor, a memory and a program which is stored on the memory and can run on the processor, wherein when the processor executes the program, at least the following steps are realized:

step S103 of removing redundancy from the first obstacle information to obtain first target obstacle information, where the first target obstacle information is position information of a first target obstacle, and the first target obstacle is the first obstacle that matches the second obstacle;

step S104, matching the first target obstacle information with the second obstacle information to obtain second target obstacle information, wherein the second target obstacle information at least comprises the first target obstacle information,

and the processor, when executing the program, implements at least the following steps:

in step S205, the target vehicle controls the traveling of the vehicle based on the second target obstacle information.

The device herein may be a server, a PC, a PAD, a mobile phone, etc.

The present application further provides a computer program product adapted to perform a program of initializing at least the following method steps when executed on a data processing device:

and adapted to perform a procedure initialized with at least the following method steps:

in step S205, the target vehicle controls the traveling of the vehicle based on the second target obstacle information.

In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

There is also provided, in accordance with yet another exemplary embodiment of the present application, a vehicle including one or more processors, memory, and one or more programs stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for performing any of the above-described methods.

The vehicle comprises one or more processors, a memory and one or more programs, wherein the one or more programs comprise a program for executing any one of the methods, and by the method, the vehicle can accurately detect the obstacle information of the construction area, and the vehicle is controlled to run according to the obstacle information, so that the vehicle can effectively avoid the influence of the obstacle of the construction area on the driving, the driving fault is avoided, and the running safety of the vehicle is ensured.

In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the above-described division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit may be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as a separate product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the above methods according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

From the above description, it can be seen that the above-described embodiments of the present application achieve the following technical effects:

1) the detection method of the intelligent driving vehicle comprises the steps of firstly receiving a semantic map of a construction area sent by a control center, wherein the semantic map of the construction area comprises first obstacle information, the first obstacle information comprises position information of a first obstacle, the first obstacle is an obstacle in the construction area, and detecting second obstacle information in real time, the second obstacle information comprises position information of a second obstacle, the second obstacle is an obstacle in a preset area, and the first obstacle information is subjected to redundancy removal to obtain first target obstacle information, the first target obstacle information is position information of a first target obstacle, and the first target obstacle is the first obstacle matched with the second obstacle, and finally, matching the first target obstacle information with the second obstacle information to obtain second target obstacle information, wherein the second target obstacle information at least comprises the first target obstacle information. The method comprises the steps of removing redundancy of first obstacle information according to the first obstacle information and the second obstacle information to obtain first target obstacle information, matching the first target obstacle information with the second obstacle information to obtain second target obstacle information, ensuring that the obtained second target obstacle information is more accurate and basically matched with the position of an obstacle in an actual construction area, and ensuring that the finally obtained obstacle information is the second target obstacle information and comprises the first target obstacle information in a semantic map, wherein the first target obstacle information in the semantic map is more accurate and stable relative to the second obstacle information detected in real time, the obtained second target obstacle information is further ensured to be more accurate, and the problem that the result of detecting the obstacle in the construction area by the existing automatic driving vehicle is inaccurate is solved, the influence of the obstacles in the construction area on driving is avoided better according to the obtained information of the second target obstacles, and the driving safety is ensured.

2) The application also provides a control method of the intelligent driving vehicle, wherein the target vehicle firstly receives a semantic map of a construction area sent by a control center, the semantic map of the construction area comprises first obstacle information, the first obstacle information comprises position information of a first obstacle, the first obstacle is an obstacle in the construction area, the target vehicle detects second obstacle information in real time, the second obstacle information comprises position information of a second obstacle, the second obstacle is an obstacle in a preset area, the target vehicle performs redundancy removal on the first obstacle information to obtain first target obstacle information, the first target obstacle information is the position information of a first target obstacle, the first target obstacle is the first obstacle matched with the second obstacle, the target vehicle matches the first target obstacle information with the second obstacle information to obtain second target obstacle information, the second target obstacle information including at least the first target obstacle information, and finally, the target vehicle controls the vehicle to travel according to the second target obstacle information. In the control method of the intelligent driving vehicle, the target vehicle performs redundancy elimination on the first obstacle information according to the first obstacle information and the second obstacle information to obtain the first target obstacle information, then matches the first target obstacle information with the second obstacle information to obtain the second target obstacle information, controls the driving of the vehicle according to the second target obstacle information to ensure that the obtained second target obstacle information is more accurate and basically matched with the position of an obstacle in an actual construction area, ensures that the vehicle can better regulate the influence of the obstacle in the construction area on the driving according to the obtained second target obstacle information, and finally obtains the obstacle information as the first target obstacle information in a semantic map included in the second target obstacle information, compared with the second obstacle information detected in real time, the first target obstacle information in the semantic map is more accurate and stable, the second target obstacle information is further ensured to be more accurate, the problem that the result of detecting the obstacle in the construction area by the existing automatic driving vehicle is inaccurate is solved, and the driving safety is ensured.

3) The application also provides a detection device of the intelligent driving vehicle, the detection device of the intelligent driving vehicle receives a semantic map of a construction area sent by a control center through the first receiving unit, the semantic map of the construction area comprises first obstacle information, the first obstacle information comprises position information of a first obstacle, the first obstacle is an obstacle in the construction area, the first detection unit detects second obstacle information in real time, the second obstacle information comprises position information of a second obstacle, the second obstacle is an obstacle in a preset area, the first obstacle information is subjected to redundancy removal through the first redundancy removing unit, first target obstacle information is obtained after redundancy removal, and the first target obstacle information is the position information of a first target obstacle, the first target obstacle is the first obstacle matching the second obstacle; and obtaining second target obstacle information by matching the first target obstacle information with the second obstacle information by the first matching means, wherein the second target obstacle information at least includes the first target obstacle information. The device performs redundancy removal on the first obstacle information according to the first obstacle information and the second obstacle information to obtain the first target obstacle information, then matches the first target obstacle information with the second obstacle information to obtain the second target obstacle information, ensures that the obtained second target obstacle information is more accurate and basically matched with the position of an obstacle in an actual construction area, and finally obtains the obstacle information which is the second target obstacle information and comprises the first target obstacle information in a semantic map, wherein the first target obstacle information in the semantic map is more accurate and stable relative to the second obstacle information detected in real time, further ensures that the obtained second target obstacle information is more accurate, and solves the problem that the result of detecting the obstacle in the construction area by the existing automatic driving vehicle is inaccurate, the influence of the obstacles in the construction area on driving is avoided better according to the obtained information of the second target obstacles, and the driving safety is ensured.

4) The application also provides a control device of a vehicle, the control device of the vehicle receives a semantic map of a construction area sent by a control center through a target vehicle of a second receiving unit, the semantic map of the construction area comprises first obstacle information, the first obstacle information comprises position information of a first obstacle, the first obstacle is an obstacle in the construction area, the target vehicle detects second obstacle information in real time through a second detecting unit, the second obstacle information comprises position information of a second obstacle, the second obstacle is an obstacle in a preset area, the target vehicle performs redundancy removal on the first obstacle information through a second redundancy removing unit, first target obstacle information is obtained after the redundancy removal, and the first target obstacle information is the position information of a first target obstacle, the first target obstacle is the first obstacle matched with the second obstacle, the target vehicle matches the first target obstacle information with the second obstacle information by the second matching means to obtain second target obstacle information, the second target obstacle information includes at least the first target obstacle information, and the target vehicle controls the traveling of the vehicle based on the second target obstacle information by the control means. In the control device of the vehicle, the target vehicle performs redundancy elimination on the first obstacle information according to the first obstacle information and the second obstacle information to obtain the first target obstacle information, then matches the first target obstacle information with the second obstacle information to obtain the second target obstacle information, controls the running of the vehicle according to the second target obstacle information, ensures that the obtained second target obstacle information is more accurate and basically matched with the position of an obstacle in an actual construction area, ensures that the vehicle can better avoid the influence of the obstacle in the construction area on the running according to the obtained second target obstacle information, and the finally obtained obstacle information is the second target obstacle information which comprises the first target obstacle information in a semantic map and is relative to the second obstacle information detected in real time, the first target obstacle information in the semantic map is more accurate and stable, the second target obstacle information is further ensured to be more accurate, the problem that the result of detecting obstacles in a construction area by the existing automatic driving vehicle is inaccurate is solved, and the driving safety is ensured.

5) The vehicle comprises one or more processors, a memory and one or more programs, wherein the one or more programs comprise a program for executing any one of the methods, the vehicle can accurately detect the obstacle information of the construction area through the method, and the vehicle is controlled to run according to the obstacle information, so that the vehicle can effectively avoid the influence of the obstacle of the construction area on the driving, the driving fault is avoided, and the driving safety of the vehicle is ensured.

The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

26页详细技术资料下载

上一篇：一种医用注射器针头装配设备

下一篇：一种档案管理系统

Detection method and control method of intelligent driving vehicle and processor

相关技术

网友询问留言