阅读说明：本技术 一种障碍物的感知方法、感知装置和无人驾驶清扫车 (Obstacle sensing method and device and unmanned sweeper ) 是由 骆嫚 蔡营 曹恺 杨小鸣 于 2020-06-10 设计创作，主要内容包括：本申请公开一种障碍物的感知方法、感知装置和无人驾驶清扫车,涉及车辆自动驾驶技术领域,感知方法包括：视觉相机采集车辆周边的图像信息；多个同侧分布的固态激光雷达根据各自的探测范围获取所述车辆同侧不同远近区域的障碍物的激光云点信息,同时,探测较近区域的固态激光雷达的分辨率高于探测较远区域的固态激光雷达；处理器接收所述图像信息和多个所述激光云点信息并进行融合处理,得到所述车辆同侧的障碍物的感知信息。本申请对车辆同侧的环境分区域获取并进行融合处理,提高对障碍物的感知能力。(The application discloses perception method, perception device and unmanned motor sweeper of barrier relates to vehicle automatic driving technical field, and the perception method includes: the method comprises the steps that a visual camera collects image information of the periphery of a vehicle; the method comprises the following steps that a plurality of solid-state laser radars distributed on the same side acquire laser cloud point information of obstacles in different far and near areas on the same side of a vehicle according to respective detection ranges, and meanwhile, the resolution of the solid-state laser radar for detecting a near area is higher than that of the solid-state laser radar for detecting a far area; and the processor receives the image information and the laser cloud point information and performs fusion processing to obtain the perception information of the obstacles on the same side of the vehicle. According to the method and the device, the environments on the same side of the vehicle are obtained in different areas and are subjected to fusion processing, and the sensing capability of the vehicle to the barrier is improved.)

1. A method for sensing an obstacle, the method comprising the steps of:

the method comprises the steps that a visual camera collects image information of the periphery of a vehicle;

the method comprises the following steps that a plurality of solid-state laser radars distributed on the same side acquire laser cloud point information of obstacles in different far and near areas on the same side of a vehicle according to respective detection ranges, and meanwhile, the resolution of the solid-state laser radar for detecting a near area is higher than that of the solid-state laser radar for detecting a far area;

and the processor receives the image information and the laser cloud point information and performs fusion processing to obtain the perception information of the obstacles on the same side of the vehicle.

2. The method for sensing the obstacle according to claim 1, wherein the step of receiving the image information and the plurality of laser cloud point information by the processor and performing fusion processing to obtain the sensing information of the obstacle on the same side of the vehicle comprises the specific steps of:

receiving image information of the periphery of the vehicle and receiving a plurality of laser cloud point information on the same side of the vehicle, wherein the image information comprises a collected boundary frame area of an obstacle;

converting the three-dimensional coordinates of the laser cloud point information into two-dimensional coordinates corresponding to the image information, determining the laser cloud point information of the obstacle according to the corresponding two-dimensional coordinates and the boundary frame region, and performing rasterization clustering on the laser cloud point information of the obstacle to obtain perception information of the obstacle, wherein the perception information comprises the type, the outline size, the spatial position and the speed of the obstacle.

3. An obstacle sensing device, comprising:

a vision camera for acquiring image information of the vehicle surroundings;

the system comprises a plurality of solid-state laser radars arranged on the same side, a plurality of sensors and a controller, wherein the solid-state laser radars are used for acquiring laser cloud point information of obstacles in different far and near areas on the same side of a vehicle according to respective detection ranges, and meanwhile, the resolution of the solid-state laser radar for detecting a near area is higher than that of the solid-state laser radar for detecting a far area;

and the processor is connected with the vision camera and the plurality of solid-state laser radars and is used for receiving the image information and the plurality of laser cloud point information and carrying out fusion processing to obtain perception information of the obstacles on the same side of the vehicle.

4. An obstacle sensing apparatus according to claim 3, wherein the solid state lidar is a solid state embedded lidar.

5. The obstacle sensing apparatus of claim 3, wherein the number of solid state lidar is three, wherein one solid state lidar is a first solid state lidar and the other two solid state lidar are second solid state lidar, and wherein the first solid state lidar has a greater horizontal viewing angle than the second solid state lidar; at the same time, the user can select the desired position,

the two second solid-state laser radars are distributed on two sides of the first solid-state laser radar, are lower in arrangement height than the first solid-state laser radar and are used for detecting short and short obstacles and road edge information in a short distance, and the first solid-state laser radar is used for detecting long-distance obstacles.

6. An obstacle sensing apparatus as claimed in claim 5, wherein the first solid state lidar supports laser instant positioning and mapping.

7. The apparatus for sensing an obstacle as recited in claim 1, further comprising:

and the ultrasonic radar is connected with the processor and used for acquiring distance data of obstacles around the vehicle and sending the distance data to the processor.

8. The apparatus for sensing an obstacle according to claim 1, wherein the processor comprises:

the receiving module is used for receiving image information of the periphery of the vehicle and receiving a plurality of laser cloud point information on the same side of the vehicle, wherein the image information comprises a boundary frame area of the acquired barrier;

and the fusion module is used for converting the three-dimensional coordinates of the laser cloud point information into two-dimensional coordinates corresponding to the image information, jointly determining the laser cloud point information of the obstacle according to the corresponding two-dimensional coordinates and the border frame area, and performing rasterization clustering on the laser cloud point information of the obstacle to obtain the perception information of the obstacle, wherein the perception information comprises the type, the contour size, the spatial position and the speed of the obstacle.

9. An unmanned sweeper vehicle, the unmanned sweeper vehicle comprising:

a vehicle body;

a sensing device mounted on the vehicle body, the sensing device being the obstacle sensing device according to any one of claims 3 to 8.

10. The unmanned sweeper of claim 9, wherein the number of the solid state lidar is three, one of the solid state lidar is a first solid state lidar, the other two of the solid state lidar is a second solid state lidar, the first solid state lidar has a larger horizontal viewing angle than the second solid state lidar, the first solid state lidar is mounted on a front side of the sweeper body, the two second solid state lidar are respectively mounted on front sides of the sweeper body, and the second solid state lidar is disposed at a lower elevation than the first solid state lidar.

Technical Field

The application relates to the technical field of automatic driving of vehicles, in particular to a sensing method and a sensing device for obstacles and an unmanned sweeper.

Background

In recent years, unmanned automatic driving of an automatic driving vehicle is not really realized on a completely open road due to limitations of technology and regulations, but the automatic driving vehicle is applied to a special scene in the fields of transportation, article transportation, park cleaning and the like.

The unmanned sweeper in the park scene needs to meet the requirement of higher sensing capability on the surrounding environment of the sweeper so as to achieve a good sweeping effect. And the poor perception of unmanned sweeper directly leads to poor cleaning effect.

At present, most of the sensing devices of the sweeper on the market for the environment are arranged on the top of the sweeper and use a single mechanical laser radar as a core sensing sensor, but the mechanical laser radar is high in price, rapid in reliability reduction and incapable of considering low obstacles around the sweeper body.

Disclosure of Invention

The embodiment of the application provides a sensing method and a sensing device for obstacles and an unmanned sweeper, which are used for obtaining and fusing environments on the same side of a vehicle in different areas and improving sensing capability for the obstacles.

In a first aspect, an embodiment of the present application provides a method for sensing an obstacle, where the method includes:

the method comprises the steps that a visual camera collects image information of the periphery of a vehicle;

the method comprises the following steps that a plurality of solid-state laser radars distributed on the same side acquire laser cloud point information of obstacles in different far and near areas on the same side of a vehicle according to respective detection ranges, and meanwhile, the resolution of the solid-state laser radar for detecting a near area is higher than that of the solid-state laser radar for detecting a far area;

and the processor receives the image information and the laser cloud point information and performs fusion processing to obtain the perception information of the obstacles on the same side of the vehicle.

In this embodiment, preferably, the step of receiving the image information and the plurality of laser cloud point information by the processor and performing fusion processing to obtain the perception information of the obstacle on the same side of the vehicle includes:

receiving image information of the periphery of the vehicle and receiving a plurality of laser cloud point information on the same side of the vehicle, wherein the image information comprises a collected boundary frame area of an obstacle;

converting the three-dimensional coordinates of the laser cloud point information into two-dimensional coordinates corresponding to the image information, determining the laser cloud point information of the obstacle according to the corresponding two-dimensional coordinates and the boundary frame region, and performing rasterization clustering on the laser cloud point information of the obstacle to obtain perception information of the obstacle, wherein the perception information comprises the type, the outline size, the spatial position and the speed of the obstacle.

In a second aspect, an embodiment of the present application further provides a sensing device for an obstacle, where the sensing device includes:

a vision camera for acquiring image information of the vehicle surroundings;

the system comprises a plurality of solid-state laser radars arranged on the same side, a plurality of sensors and a controller, wherein the solid-state laser radars are used for acquiring laser cloud point information of obstacles in different far and near areas on the same side of a vehicle according to respective detection ranges, and meanwhile, the resolution of the solid-state laser radar for detecting a near area is higher than that of the solid-state laser radar for detecting a far area;

and the processor is connected with the vision camera and the plurality of solid-state laser radars and is used for receiving the image information and the plurality of laser cloud point information and carrying out fusion processing to obtain perception information of the obstacles on the same side of the vehicle.

In this embodiment, preferably, the solid-state lidar is a solid-state embedded lidar.

Preferably, the number of the solid-state laser radars is three, one of the solid-state laser radars is a first solid-state laser radar, the other two solid-state laser radars are second solid-state laser radars, and the horizontal viewing angle of the first solid-state laser radar is greater than that of the second solid-state laser radars; at the same time, the user can select the desired position,

the two second solid-state laser radars are distributed on two sides of the first solid-state laser radar, are lower in arrangement height than the first solid-state laser radar and are used for detecting short and short obstacles and road edge information in a short distance, and the first solid-state laser radar is used for detecting long-distance obstacles.

Preferably, the first solid state lidar supports laser instant positioning and mapping.

Preferably, the sensing device further comprises:

and the ultrasonic radar is connected with the processor and used for acquiring distance data of obstacles around the vehicle and sending the distance data to the processor.

Preferably, the processor comprises:

the receiving module is used for receiving image information of the periphery of the vehicle and receiving a plurality of laser cloud point information on the same side of the vehicle, wherein the image information comprises a boundary frame area of the acquired barrier;

and the fusion module is used for converting the three-dimensional coordinates of the laser cloud point information into two-dimensional coordinates corresponding to the image information, jointly determining the laser cloud point information of the obstacle according to the corresponding two-dimensional coordinates and the border frame area, and performing rasterization clustering on the laser cloud point information of the obstacle to obtain the perception information of the obstacle, wherein the perception information comprises the type, the contour size, the spatial position and the speed of the obstacle.

In a third aspect, an embodiment of the present application further provides an unmanned sweeping vehicle, including:

a vehicle body;

the sensing device is arranged on the vehicle body and is the sensing device of the obstacle.

In this embodiment, preferably, solid-state lidar's quantity is three, and one of them solid-state lidar is first solid-state lidar, and two other solid-state lidar are second solid-state lidar, first solid-state lidar's horizontal visual angle is greater than second solid-state lidar, just first solid-state lidar installs the front side of automobile body, two second solid-state lidar installs respectively on the place ahead both sides of automobile body, second solid-state lidar arranges highly to be less than first solid-state lidar.

The beneficial effect that technical scheme that this application provided brought includes:

the embodiment of the application provides a sensing method and a sensing device for obstacles and an unmanned sweeper, wherein the sensing method uses a low-cost vision camera and a plurality of solid-state laser radars to cooperatively use to acquire and fuse obstacle information in an environment to obtain the sensing information of the obstacles; meanwhile, according to the distance of a detection area, the laser cloud point information of the obstacle is acquired by using a solid laser radar with proper precision, the environment on one side around the vehicle can be accurately sensed, safe and redundant accurate obstacle identification is carried out, and the sensing capability of the obstacle can be improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic flowchart of a method for sensing an obstacle according to an embodiment of the present disclosure;

fig. 2 is a schematic flowchart of a specific step of step S3 according to an embodiment of the present disclosure;

fig. 3 is a block diagram of a sensing device for an obstacle according to an embodiment of the present disclosure;

fig. 4 is a block diagram of a processor according to an embodiment of the present disclosure;

fig. 5 is a block diagram of an unmanned sweeping vehicle according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, 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 some 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.

Referring to fig. 1, an embodiment of the present application provides a method for sensing an obstacle, where the method includes the following steps:

step S1: the method comprises the steps that a visual camera collects image information of the periphery of a vehicle;

step S2: the method comprises the following steps that a plurality of solid-state laser radars distributed on the same side acquire laser cloud point information of obstacles in different far and near areas on the same side of a vehicle according to respective detection ranges, and meanwhile, the resolution of the solid-state laser radar for detecting a near area is higher than that of the solid-state laser radar for detecting a far area;

step S3: and the processor receives the image information and the laser cloud point information and performs fusion processing to obtain the perception information of the obstacles on the same side of the vehicle.

In this embodiment, the sensing method may occur when the vehicle travels on a road, the vision camera, the solid state lidar and the processor used in the sensing method are all mounted on the vehicle body of the vehicle, and the operating principle of the sensing method for the obstacle is as follows:

the vision camera and the solid-state laser radars move along with the vehicle to collect two kinds of information of obstacles on a road, namely image information and laser cloud point information, and the two kinds of information are fused to obtain the perception information of the obstacles on the same side of the vehicle.

Meanwhile, the laser cloud point information of the obstacles in different far and near areas on the same side of the vehicle is obtained by the solid-state laser radars according to respective detection ranges, the resolution ratio of the solid-state laser radar for detecting the near area is higher than that of the solid-state laser radar for detecting the far area, the solid-state laser radar with the suitable specification can be adopted according to actual conditions, the sensing precision can be further guaranteed on the premise of reducing the production cost, and the safe and redundant accurate obstacle identification can be carried out.

Referring to fig. 2, preferably, the specific steps of step 3 are:

receiving image information of the periphery of the vehicle and receiving a plurality of laser cloud point information on the same side of the vehicle, wherein the image information comprises a collected boundary frame area of an obstacle;

converting the three-dimensional coordinates of the laser cloud point information into two-dimensional coordinates corresponding to the image information, determining the laser cloud point information of the obstacle according to the corresponding two-dimensional coordinates and the boundary frame region, and performing rasterization clustering on the laser cloud point information of the obstacle to obtain perception information of the obstacle, wherein the perception information comprises the type, the outline size, the spatial position and the speed of the obstacle.

In the embodiment of the application, the specific process of fusion of the image information and the laser cloud point information is simple, the laser cloud point information of the obstacle is locked by using the image information, and then the laser cloud point information of the obstacle is subjected to rasterization clustering, so that the rasterized clustering object is reduced, and meanwhile, the sensing information of the obstacle can be effectively obtained.

Referring to fig. 1, an embodiment of the present application further provides a sensing device for an obstacle, where the sensing device includes a vision camera, a processor, and a plurality of solid-state lidar arranged on the same side; the vision camera is used for acquiring image information of the periphery of the vehicle; the solid-state laser radars are used for acquiring laser cloud point information of obstacles in different far and near areas on the same side of the vehicle according to respective detection ranges, and meanwhile, the resolution of the solid-state laser radar for detecting a near area is higher than that of the solid-state laser radar for detecting a far area; the processor is connected with the vision camera and the plurality of solid-state laser radars and used for receiving the image information and the plurality of laser cloud point information and carrying out fusion processing to obtain perception information of obstacles on the same side of the vehicle.

In the embodiment, the sensing device is installed on the vehicle, and the sensing device is simple in component and low in cost. When the vehicle runs on a road, the sensing device senses the environment around the vehicle, particularly senses obstacles in the environment, and the operating principle of the obstacle sensing device is as follows:

the vision camera and the solid-state laser radars are all installed on the vehicle and move along with the vehicle, two kinds of information of obstacles on a road, namely image information and laser cloud point information, are collected, the processor performs fusion processing on the two kinds of information to obtain perception information of the obstacles on the same side of the vehicle, wherein each solid-state laser radar is used for detecting and obtaining the laser cloud point information of each area, after the laser cloud point information of each area is matched with the area on the image information, the obstacle information carried on the laser cloud point information of each area is matched and fused with the obstacle information in the image information of the area, and the vision camera and the solid-state laser radars can be achieved only by using the solid-state laser radars with relatively low prices.

Meanwhile, the laser cloud point information of the obstacles in different far and near areas on the same side of the vehicle is obtained by the solid-state laser radars according to respective detection ranges, the resolution ratio of the solid-state laser radar for detecting the near area is higher than that of the solid-state laser radar for detecting the far area, the solid-state laser radar with the suitable specification can be adopted according to actual conditions, the sensing precision can be further guaranteed on the premise of reducing the production cost, and the safe and redundant accurate obstacle identification can be carried out.

Preferably, the solid-state lidar is a solid-state embedded lidar. The embedded solid-state laser radar can meet the detection requirement, and meanwhile, the solid-state laser radar is arranged in the vehicle body of the vehicle in an embedded mode and is not provided with a protruding exposed part.

Referring to fig. 5, specifically, the number of the solid-state laser radars is three, one of the solid-state laser radars is a first solid-state laser radar, the other two solid-state laser radars are second solid-state laser radars, a horizontal viewing angle of the first solid-state laser radar is greater than that of the second solid-state laser radar, the first solid-state laser radar is defined as a wide-angle laser radar according to a size of the horizontal viewing angle, and the second solid-state laser radar is defined as a narrow-angle laser radar; simultaneously, two narrow angle lidar distributes wide angle lidar's both sides, and it arranges the height and is less than wide angle lidar for survey short barrier of low coverage and road edge information, first solid-state lidar is used for surveying long distance barrier.

More specifically, in this embodiment, the wide-angle lidar has a horizontal angle of view of at least 120 °, a vertical angle of view of at least 10 °, and a resolution of at least 0.3 °. The horizontal visual angle of narrow angle laser radar is 40 at least, and the resolution ratio is 0.1 at least, narrow angle laser radar's resolution ratio is higher than wide angle laser radar. Meanwhile, the longitudinal measurable distance of the vision camera is more than 60 meters, the horizontal visual angle is at least 90 degrees, and the vertical visual angle is at least 50 degrees, so that the proper perception range is ensured, and the purpose of effectively perceiving the obstacles is achieved.

Preferably, the wide-angle lidar supports laser instant positioning and mapping. When a carrier vehicle of the sensing device is positioned on a nameless road, the inertial integrated navigation cannot position the carrier vehicle, and at the moment, the wide-angle laser radar is installed on the front side of the vehicle, can detect the environment outside the vehicle to acquire laser cloud point information so as to construct an environment map of the surrounding environment of the vehicle, and realize the auxiliary positioning capability.

Preferably, the sensing device further comprises an ultrasonic radar connected to the processor for collecting distance data of obstacles around the vehicle and sending the distance data to the processor. In this embodiment, the solid-state lidar primarily detects obstacles on one side of the vehicle, while the other side is not involved in the detection of obstacles, and there is still a need for obstacle sensing for obstacles in close proximity to the vehicle when the vehicle is started or parked. Therefore, the ultrasonic radar is arranged on the peripheral side of the vehicle, the distance from the obstacle to the vehicle is detected, the visual camera can be used for assisting the sweeper to sense the obstacle in a short distance when the sweeper is started or parked, the visual camera and the ultrasonic radar are combined to perform fusion sensing on the obstacles in different distances, the modeling of the vehicle is changed slightly, and the influence of illumination is avoided.

Referring to fig. 4, further, the processor includes a receiving module and a fusing module; the receiving module is used for receiving image information of the periphery of the vehicle and receiving a plurality of laser cloud point information on the same side of the vehicle, and the image information comprises a boundary frame area of the acquired barrier; the fusion module is used for converting the three-dimensional coordinates of the laser cloud point information into two-dimensional coordinates corresponding to the image information, determining the laser cloud point information of the obstacle according to the corresponding two-dimensional coordinates and the border frame region, and performing rasterization clustering on the laser cloud point information of the obstacle to obtain perception information of the obstacle, wherein the perception information comprises the type, the outline size, the spatial position and the speed of the obstacle. In the embodiment of the application, the processor locks the laser cloud point information of the obstacle by using the image information, and then performs rasterization clustering on the laser cloud point information of the obstacle, so that the object of rasterization clustering is reduced, and the operation load of the processor is reduced.

Referring to fig. 5, an embodiment of the present application further provides an unmanned sweeper, where the unmanned sweeper includes a sweeper body and a sensing device, the sensing device is mounted on the sweeper body, and the sensing device is a sensing device for any one of the obstacles. The description of the sensing device is not repeated herein.

In this embodiment, preferably, solid-state lidar's quantity is three, and one of them solid-state lidar is first solid-state lidar, and two other solid-state lidar are second solid-state lidar, first solid-state lidar's horizontal visual angle is greater than second solid-state lidar, just first solid-state lidar installs the front side of automobile body, two second solid-state lidar installs respectively on the place ahead both sides of automobile body, second solid-state lidar arranges highly to be less than first solid-state lidar.

Specifically, the solid-state laser radar is a solid-state embedded laser radar, the embedded solid-state laser radar can meet detection requirements, and can be arranged in the body of the sweeper, no protruding exposed part exists, and the appearance of the sweeper is not affected.

In this embodiment, the unmanned sweeping vehicle runs under a complex road environment, the speed is low, the general vehicle speed is lower than 15km/m, the main sensing direction is located in front of the vehicle and at the side of the vehicle during turning, and the more detailed working principle of the sensing device in the unmanned sweeping vehicle is as follows:

step 001: the method comprises the steps that a visual camera collects image information of the periphery of the sweeper, wherein the image information comprises a collected boundary frame area of an obstacle;

step 002: a wide-angle laser radar arranged on the vehicle body detects a long-distance obstacle in front of the sweeper and obtains laser cloud point information of the area, and two narrow-angle laser radars arranged on the vehicle body detect a short obstacle in front of the vehicle body and obtain laser cloud point information of the area; meanwhile, the wide-angle laser radar is arranged in front of the sweeper and mainly detects the range outside the front 10 of the sweeper body, the two narrow-angle laser radars are arranged on two sides in front of the sweeper, the mounting position of the narrow-angle laser radar on the sweeper is lower than that of the wide-angle laser radar, the range within 10 meters in front of the sweeper body is mainly detected, and the laser cloud point information of a front short obstacle can be conveniently acquired;

step 003: the processor receives image information of the vision camera and receives laser cloud point information of the wide-angle laser radar and the narrow-angle laser radar;

step 004: the processor converts the three-dimensional coordinates of the received laser cloud point information into two-dimensional coordinates corresponding to the image information, determines the laser cloud point information of the obstacle together according to the corresponding two-dimensional coordinates and the boundary frame area, and performs rasterization clustering on the laser cloud point information determined together to obtain the sensing information of the obstacle in front of the sweeper, wherein the sensing information comprises the type, the contour size, the spatial position and the speed of the obstacle.

Simultaneously, narrow angle laser radar detects the condition on automobile body the place ahead both sides ground when the motor sweeper turns in this application embodiment, and the motor sweeper can carry out autopilot according to the road edge information of perception. Road edge information on a road, such as road marks, is sensed, and laser cloud point information of the road edge information detected by the narrow-angle laser radar and the road edge information in the image information are fused through the processor to obtain accurate sensing information of the road edge information, such as the size, the spatial position, the type and the like of the outline of the road edge information. The embodiment of the application is suitable for complex environments of parks or irregular unstructured traffic environments, such as missing lane lines, and can accurately judge the road edge information.

As shown in fig. 5, further, the vision cameras are monocular cameras, and one vision camera is uniformly arranged around the vehicle body; the sensing device further comprises an ultrasonic radar, the ultrasonic radar is also installed on the periphery of the vehicle body, two ultrasonic radars are installed on each side, meanwhile, the ultrasonic radars on the two sides of the vehicle body are installed on the position close to the rear side of the vehicle, the acquisition distance of the ultrasonic radars is more than 3.5m, sensing and recognition of obstacles can be achieved on the side and the rear of the vehicle, detection of the distance of the obstacles in a short distance when the vehicle is started or parked is facilitated, and the ultrasonic radars and the vision camera are cooperatively used to sense the obstacles in a short distance when the vehicle is started or parked. Meanwhile, the vehicle provided by the embodiment of the application is a sweeper under a complex road environment, the speed is low, the general speed is lower than 15km/m, and the main sensing direction is positioned in front of the vehicle and on the side of the vehicle during turning, so that low-cost ultrasonic radars are mainly adopted on the side and the rear of the vehicle body, and the requirements on sensing precision can be met by matching the ultrasonic radars together.

Preferably, the sweeper further comprises an inertial combination navigation for positioning the sweeper; and the wide-angle laser radar supports laser instant positioning and map construction. When a carrier vehicle of the sensing device is positioned on a nameless road, the inertia combination navigation cannot position the sweeper, more specifically, the wide-angle laser radar is installed on the front side of the vehicle, and is used for detecting the environment outside the vehicle to acquire laser cloud point information so as to construct an environment map of the surrounding environment of the vehicle, so that the auxiliary positioning capability is realized.

In the description of the present application, it should be noted that the terms "upper", "lower", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, which are only for convenience in describing the present application and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and operate, and thus, should not be construed as limiting the present application. Unless expressly stated or limited otherwise, the terms "mounted," "connected," and "connected" are intended to be inclusive and mean, for example, that they may be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as appropriate.

It is noted that, in the present application, relational terms such as "first" and "second", and the like, are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

The above description is merely exemplary of the present application and is presented to enable those skilled in the art to understand and practice the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.