阅读说明：本技术 车载激光雷达的清洗方法、装置、电子设备及存储介质 (Cleaning method and device for vehicle-mounted laser radar, electronic equipment and storage medium ) 是由 余松显 石鑫 于 2021-07-27 设计创作，主要内容包括：本发明提供一种车载激光雷达的清洗方法、装置、电子设备及存储介质,该方法包括：获取车载激光雷达扫描得到的点云数据,根据点云数据确定激光雷达视窗上的障碍物类型；根据障碍物类型确定对应于障碍物类型的清洗方式,根据清洗方式控制清洗设备对激光雷达视窗进行清洗。本发明提供的车载激光雷达的清洗方法、装置、电子设备及存储介质,通过对激光雷达视窗上的障碍物进行类型识别,采用相对应的清洗方式进行清洗,避免清洗方式不合理造成清洗效果不好,影响对车辆前方路况的精确识别,使车辆智能驾驶产生潜在危险。(The invention provides a method and a device for cleaning a vehicle-mounted laser radar, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring point cloud data obtained by scanning of a vehicle-mounted laser radar, and determining the type of an obstacle on a laser radar window according to the point cloud data; and determining a cleaning mode corresponding to the type of the obstacle according to the type of the obstacle, and controlling a cleaning device to clean the laser radar window according to the cleaning mode. According to the cleaning method and device for the vehicle-mounted laser radar, the electronic equipment and the storage medium, the type of the obstacle on the laser radar window is identified, and the obstacle is cleaned in a corresponding cleaning mode, so that the condition that the cleaning effect is poor due to unreasonable cleaning mode, the accurate identification of the road condition in front of the vehicle is influenced, and the vehicle is driven intelligently to generate potential danger is avoided.)

1. A cleaning method for a vehicle-mounted laser radar is characterized by comprising the following steps:

acquiring point cloud data obtained by scanning of a vehicle-mounted laser radar, and determining the type of an obstacle on a laser radar window according to the point cloud data;

and determining a cleaning mode corresponding to the type of the obstacle according to the type of the obstacle, and controlling a cleaning device to clean the laser radar window according to the cleaning mode.

2. The method for cleaning the vehicle-mounted laser radar as claimed in claim 1, wherein the determining the type of the obstacle on the laser radar window according to the point cloud data comprises:

determining the regional characteristics of the obstacle region on the laser radar window according to the point cloud data;

inputting the region characteristics into an identification model to obtain an identification result output by the identification model, wherein the identification result is used for representing the type of an obstacle in an obstacle region;

the identification model is obtained through machine learning training by taking the area characteristics determined according to the point cloud data samples and the obstacle types corresponding to the area characteristics as input, and is used for identifying the point cloud data.

3. The method for cleaning the vehicle-mounted laser radar as claimed in claim 1 or 2, wherein the laser radar window is divided into a plurality of visual field areas, and correspondingly, the type of the obstacle on the laser radar window is determined according to the point cloud data, and the method comprises the following steps:

determining the regional characteristics of the obstacle region on the laser radar window according to the point cloud data;

determining a visual field area where the obstacle area is located;

and determining the type of the obstacle corresponding to the view area on the laser radar window according to the area characteristics of the obstacle area.

4. The method of cleaning a vehicle lidar according to claim 1, further comprising:

and determining the cleaning times corresponding to the same barrier type in a preset time period, and giving a warning when the cleaning times are greater than the preset times.

5. The method according to claim 1, wherein the cleaning mode includes a water cleaning mode, a gas cleaning mode or a water-gas mixing mode.

6. A cleaning device for a vehicle-mounted laser radar is characterized by comprising:

the identification module is used for acquiring point cloud data obtained by scanning of the vehicle-mounted laser radar and determining the type of an obstacle on a laser radar window according to the point cloud data;

and the processing module is used for determining a cleaning mode corresponding to the type of the obstacle according to the type of the obstacle and controlling a cleaning device to clean the laser radar window according to the cleaning mode.

7. The cleaning device for the vehicle-mounted lidar according to claim 6, wherein the identification module is specifically configured to, during the processing of determining the type of the obstacle on the lidar window according to the point cloud data:

determining the regional characteristics of the obstacle region on the laser radar window according to the point cloud data;

inputting the region characteristics into an identification model to obtain an identification result output by the identification model, wherein the identification result is used for representing the type of an obstacle in an obstacle region;

the identification model is obtained through machine learning training by taking the area characteristics determined according to the point cloud data samples and the obstacle types corresponding to the area characteristics as input, and is used for identifying the point cloud data.

8. The cleaning device for the vehicle-mounted lidar according to claim 5 or 6, wherein the lidar window is divided into a plurality of view areas, and accordingly, the identification module is specifically configured to, during the process of determining the type of the obstacle on the lidar window according to the point cloud data:

determining the regional characteristics of the obstacle region on the laser radar window according to the point cloud data;

determining a visual field area where the obstacle area is located;

and determining the type of the obstacle corresponding to the view area on the laser radar window according to the area characteristics of the obstacle area.

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method for cleaning a vehicle lidar according to any of claims 1 to 5 when executing the program.

10. A non-transitory readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for cleaning a vehicle lidar according to any one of claims 1 to 5.

Technical Field

The invention relates to the technical field of intelligent vehicles, in particular to a method and a device for cleaning a vehicle-mounted laser radar, electronic equipment and a storage medium.

Background

The driving process of the intelligent vehicle requires the laser radar to identify the road condition in front of the vehicle.

Due to the high-precision, high-environment-adaptability and high-reliability target detection capability of the laser radar, the laser radar becomes one of indispensable sensor types in the field of automatic driving perception. The occupancy will be higher and higher as the cost of the individual pieces decreases. In the actual use environment, the surface of the laser radar window can be damaged by obstacles such as dust accumulation, muddy water, winged insect residues, feathers, animal excrement and the like. For this reason, the laser radar cannot accurately recognize the road condition, and may affect safe driving.

Disclosure of Invention

Aiming at the problems in the prior art, the invention provides a method and a device for cleaning a vehicle-mounted laser radar, electronic equipment and a storage medium.

The invention provides a cleaning method of a vehicle-mounted laser radar, which comprises the steps of obtaining point cloud data obtained by scanning the vehicle-mounted laser radar, and determining the type of an obstacle on a laser radar window according to the point cloud data;

and determining a cleaning mode corresponding to the type of the obstacle according to the type of the obstacle, and controlling a cleaning device to clean the laser radar window according to the cleaning mode.

According to the cleaning method of the vehicle-mounted laser radar provided by the invention, the method for determining the type of the obstacle on the laser radar window according to the point cloud data comprises the following steps:

determining the regional characteristics of the obstacle region on the laser radar window according to the point cloud data;

inputting the region characteristics into an identification model to obtain an identification result output by the identification model, wherein the identification result is used for representing the type of an obstacle in an obstacle region;

the identification model is obtained through machine learning training by taking the area characteristics determined according to the point cloud data samples and the obstacle types corresponding to the area characteristics as input, and is used for identifying the point cloud data.

According to the cleaning method of the vehicle-mounted laser radar, the laser radar window is divided into a plurality of visual field areas, correspondingly, the type of the obstacle on the laser radar window is determined according to the point cloud data, and the method comprises the following steps:

determining the regional characteristics of the obstacle region on the laser radar window according to the point cloud data;

determining a visual field area where the obstacle area is located;

and determining the type of the obstacle corresponding to the view area on the laser radar window according to the area characteristics of the obstacle area.

According to the cleaning method of the vehicle-mounted laser radar provided by the invention, the method further comprises the following steps:

and determining the cleaning times corresponding to the same barrier type in a preset time period, and giving a warning when the cleaning times are greater than the preset times.

According to the cleaning method of the vehicle-mounted laser radar, the cleaning mode comprises a water washing mode, a gas washing mode or a water-gas mixing mode.

The invention also provides a cleaning device for the vehicle-mounted laser radar, which comprises:

the identification module is used for acquiring point cloud data obtained by scanning of the vehicle-mounted laser radar and determining the type of an obstacle on a laser radar window according to the point cloud data;

and the processing module is used for determining a cleaning mode corresponding to the type of the obstacle according to the type of the obstacle and controlling a cleaning device to clean the laser radar window according to the cleaning mode.

The invention also provides an electronic device, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the program to realize the steps of the vehicle-mounted laser radar cleaning method.

The invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method for cleaning a vehicle-mounted lidar as defined in any of the above.

According to the cleaning method and device for the vehicle-mounted laser radar, the electronic equipment and the storage medium, the type of the obstacle on the laser radar window is identified, and the obstacle is cleaned in a corresponding cleaning mode, so that the condition that the cleaning effect is poor due to unreasonable cleaning mode, the accurate identification of the road condition in front of the vehicle is influenced, and the vehicle is driven intelligently to generate potential danger is avoided.

Drawings

In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.

FIG. 1 is a schematic flow chart of a cleaning method for a vehicle-mounted laser radar provided by the invention;

FIG. 2 is a schematic structural diagram of a cleaning device for a vehicle-mounted laser radar provided by the invention;

fig. 3 is a schematic structural diagram of an electronic device provided in the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. 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 invention.

The following describes, with reference to fig. 1 to fig. 3, a debugging method for an intelligent vehicle-mounted internet terminal motherboard, an intelligent vehicle-mounted internet terminal, a vehicle, and a multimedia device provided by the present invention.

Fig. 1 shows a schematic flow chart of a cleaning method of a vehicle-mounted laser radar provided by the invention, and referring to fig. 1, the method comprises the following steps:

11. acquiring point cloud data obtained by scanning of a vehicle-mounted laser radar, and determining the type of an obstacle on a laser radar window according to the point cloud data;

12. and determining a cleaning mode corresponding to the type of the obstacle according to the type of the obstacle, and controlling a cleaning device to clean the laser radar window according to the cleaning mode.

With respect to step 11 and step 12, it should be noted that in the present invention, the driving process of the intelligent vehicle requires the laser radar to identify the road condition in front of the vehicle.

Due to the high-precision, high-environment-adaptability and high-reliability target detection capability of the laser radar, the laser radar becomes one of indispensable sensor types in the field of automatic driving perception. The occupancy will be higher and higher as the cost of the individual pieces decreases. In the actual use environment, the surface of the laser radar window can be damaged by obstacles such as dust accumulation, muddy water, winged insect residues, feathers, animal excrement and the like. Therefore, the laser radar window needs to be cleaned, and the laser radar can accurately identify the road condition in front of the vehicle conveniently.

In the invention, the cleaning mode can be different for different kinds of objects on the surface of the laser radar window. For example, dust, water washing can be used; air washing feather; the winged insect residue can be blown away by air washing, and then washed by water.

Therefore, when the surface of the laser radar window is judged to have an obstacle, the type of the obstacle needs to be identified. Then the obstacle can be cleaned by a suitable cleaning method (such as water washing, air washing or air-water mixing) according to the type.

In the invention, the vehicle-mounted laser radar is adopted for scanning to obtain point cloud data, and the point cloud data comprises point cloud data fed back when an obstacle exists on the surface of the window. Therefore, the vehicle-mounted system obtains point cloud data obtained by scanning of the vehicle-mounted laser radar, and can determine the type of the obstacle on the laser radar window according to the point cloud data. The obstacle type includes an air washing type (e.g., feather, fly-wadding, etc.), a water washing type (e.g., dust, muddy water trace, etc.), a water-air mixing type (e.g., winged insect residue, animal waste, etc.), and in addition, the name of the object may also be directly used as the obstacle type, and at this time, a plurality of obstacle types may be corresponding to one cleaning manner. For example, for the obstacle types such as feather, flying floc and the like, the cleaning is carried out by adopting an air washing mode.

And then determining a cleaning mode corresponding to the type of the obstacle according to the type of the obstacle, and controlling a cleaning device to clean the laser radar window according to the cleaning mode.

In the vehicle-mounted system, the corresponding relation between the obstacle type and the cleaning mode is configured in advance, and after the obstacle type is determined, the obstacle type and the cleaning mode are matched to obtain the corresponding cleaning mode.

Different washing modes are performed by washing equipment installed on the vehicle.

Therefore, after the cleaning mode is determined, the vehicle-mounted system sends a control instruction to the corresponding cleaning equipment so that the cleaning equipment can clean the vehicle-mounted laser radar window. The control instruction comprises information such as cleaning force, cleaning time, cleaning times and the like.

For example, in the water washing mode, a control command is sent to the water spraying device installed on the vehicle, and the water spraying device performs the washing operation.

In the air washing mode, a control command is sent to air injection equipment installed on a vehicle, and the air injection equipment executes washing work.

And in a water-air mixing mode, a control command can be sent to water spraying equipment and air spraying equipment which are installed on a vehicle, and the two equipment jointly execute cleaning work.

According to the cleaning method of the vehicle-mounted laser radar, the type of the obstacle on the laser radar window is identified, and the obstacle is cleaned in a corresponding cleaning mode, so that the condition that the cleaning effect is poor due to unreasonable cleaning mode, the accurate identification of the road condition in front of the vehicle is influenced, and the intelligent driving of the vehicle generates potential danger is avoided.

In the further invention of the above-mentioned vehicle-mounted laser radar cleaning method, the explanation is mainly given to the processing procedure of determining the type of the obstacle on the laser radar window according to the point cloud data, specifically as follows:

determining the regional characteristics of the obstacle region on the laser radar window according to the point cloud data;

inputting the regional characteristics into the recognition model to obtain a recognition result output by the recognition model, wherein the recognition result is used for representing the type of the obstacle in the obstacle region;

the identification model is obtained through machine learning training by taking the area characteristics determined according to the point cloud data samples and the obstacle types corresponding to the area characteristics as input, and is used for identifying the point cloud data.

In the invention, historically stored point cloud data of a laser radar window is collected, the point cloud data is analyzed to obtain an obstacle area of each point cloud data, the area characteristics of the obstacle area are obtained, and the obstacle type corresponding to the area characteristics is marked. And then training by adopting a neural network model, and adjusting the parameters of the model according to the regional characteristics and the types of the obstacles each time to obtain a model for identifying the point cloud data.

And then, identifying the regional characteristics of the point cloud data acquired at the current time by using the trained model to obtain the type of the obstacle corresponding to the obstacle region. In the invention, as the data characteristics of the corresponding obstacle areas in the point cloud data are obvious, the image recognition model obtained by training can be used for better recognition performance.

In the further invention of the cleaning method for the vehicle-mounted laser radar, the laser radar window is large in size and may be adhered with obstacles in a small area, and at this time, if the whole laser radar window is cleaned, the collected information of road conditions in other directions may be missed, so that driving accidents are caused.

Therefore, the laser radar window is divided into a plurality of view areas, and the processing process of the type of the obstacle on the laser radar window is determined according to the point cloud data at the moment, specifically comprising the following steps:

determining the regional characteristics of the obstacle region on the laser radar window according to the point cloud data;

determining a visual field area where the obstacle area is located;

and determining the type of the obstacle corresponding to the visual field area on the laser radar window according to the area characteristics of the obstacle area.

In this regard, it should be noted that, the processing procedures for determining the area characteristics of the obstacle area on the lidar window according to the point cloud data and determining the corresponding obstacle type according to the area characteristics of the obstacle area are the same as the above principle, and are not described herein again.

In the invention, the laser radar window is divided into a plurality of view areas, so that the view area in which the obstacle area is located needs to be judged, and the type of the obstacle corresponding to the view area with the obstacle area can be determined.

According to the invention, the laser radar window is divided into areas, only the area with the obstacle can be cleaned, and driving accidents caused by filtering point cloud data of all the areas are avoided.

In the further invention of the above-mentioned vehicle-mounted laser radar cleaning method, in a practical situation, due to the intractable adhesion of the obstacle, the obstacle of the same type or the same area cannot be cleaned for many times in a short time, and at this time, the identification of the vehicle conditions around the vehicle is certainly influenced. This warning can inform the driver, and the driver can change intelligent driving into manual driving, waits to follow-up after rinsing barrier by hand, just arranges subsequent intelligent driving, guarantees to drive safety.

Fig. 2 shows a schematic structural diagram of a vehicle-mounted laser radar cleaning device according to an embodiment of the present invention, and referring to fig. 2, the device includes an identification module 21 and a processing module 22, where:

the identification module 21 is used for acquiring point cloud data obtained by scanning of the vehicle-mounted laser radar and determining the type of an obstacle on a laser radar window according to the point cloud data;

and the processing module 22 is configured to determine a cleaning manner corresponding to the type of the obstacle according to the type of the obstacle, and control a cleaning device to clean the laser radar window according to the cleaning manner.

The identification module is specifically used for determining the type of the obstacle on the laser radar window according to the point cloud data in the processing process:

determining the regional characteristics of the obstacle region on the laser radar window according to the point cloud data;

inputting the region characteristics into an identification model to obtain an identification result output by the identification model, wherein the identification result is used for representing the type of an obstacle in an obstacle region;

the identification model is obtained through machine learning training by taking the area characteristics determined according to the point cloud data samples and the obstacle types corresponding to the area characteristics as input, and is used for identifying the point cloud data.

In a further aspect of the above vehicle-mounted laser radar cleaning apparatus, the laser radar window is divided into a plurality of view areas, and accordingly, the identification module is specifically configured to, during a process of determining a type of an obstacle on the laser radar window according to the point cloud data:

determining the regional characteristics of the obstacle region on the laser radar window according to the point cloud data;

determining a visual field area where the obstacle area is located;

and determining the type of the obstacle corresponding to the view area on the laser radar window according to the area characteristics of the obstacle area.

In a further invention of the above vehicle-mounted laser radar cleaning apparatus, the identification module is specifically configured to, in a process of determining the type of the obstacle on the laser radar window according to the point cloud data:

determining the regional characteristics of the obstacle region on the laser radar window according to the point cloud data;

inputting the region characteristics into an identification model to obtain an identification result output by the identification model, wherein the identification result is used for representing the type of an obstacle in an obstacle region;

the identification model is obtained through machine learning training by taking the area characteristics determined according to the point cloud data samples and the obstacle types corresponding to the area characteristics as input, and is used for identifying the point cloud data.

In a further invention of the above vehicle-mounted lidar cleaning device, the device further comprises a warning module configured to:

and determining the cleaning times corresponding to the same barrier type in a preset time period, and giving a warning when the cleaning times are greater than the preset times.

Since the principle of the apparatus according to the embodiment of the present invention is the same as that of the method according to the above embodiment, further details are not described herein for further explanation.

It should be noted that, in the embodiment of the present invention, the relevant functional module may be implemented by a hardware processor (hardware processor).

According to the cleaning device for the vehicle-mounted laser radar, the type of the obstacle on the laser radar window is identified, and the obstacle is cleaned in a corresponding cleaning mode, so that the condition that the cleaning effect is poor due to unreasonable cleaning mode, the accurate identification of the road condition in front of the vehicle is influenced, and the vehicle is driven intelligently to generate potential danger is avoided.

Fig. 3 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 3: a processor (processor)31, a communication Interface (communication Interface)32, a memory (memory)33 and a communication bus 34, wherein the processor 31, the communication Interface 32 and the memory 33 are communicated with each other via the communication bus 34. The processor 31 may call logic instructions in the memory 33 to perform a washing method comprising: acquiring point cloud data obtained by scanning of a vehicle-mounted laser radar, and determining the type of an obstacle on a laser radar window according to the point cloud data; and determining a cleaning mode corresponding to the type of the obstacle according to the type of the obstacle, and controlling a cleaning device to clean the laser radar window according to the cleaning mode.

In addition, the logic instructions in the memory 33 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. 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 method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform a washing method comprising: acquiring point cloud data obtained by scanning of a vehicle-mounted laser radar, and determining the type of an obstacle on a laser radar window according to the point cloud data; and determining a cleaning mode corresponding to the type of the obstacle according to the type of the obstacle, and controlling a cleaning device to clean the laser radar window according to the cleaning mode.

In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a cleaning method comprising: acquiring point cloud data obtained by scanning of a vehicle-mounted laser radar, and determining the type of an obstacle on a laser radar window according to the point cloud data; and determining a cleaning mode corresponding to the type of the obstacle according to the type of the obstacle, and controlling a cleaning device to clean the laser radar window according to the cleaning mode.

The above-described embodiments of the apparatus are merely illustrative, and 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 network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.

Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.