CN119428649A - Vehicle obstacle avoidance method and device - Google Patents

Abstract

The embodiment of the present application discloses a vehicle obstacle avoidance method for improving the accuracy of vehicle obstacle avoidance. The method of the embodiment of the present application includes: obtaining a first obstacle map, the first obstacle map is used to predict the position of a road obstacle area for the vehicle at a long sight distance, and the long sight distance includes a distance from the vehicle that is greater than a first threshold. When the distance between the vehicle and the road obstacle area is less than or equal to the first threshold, first road surface information is collected, and the existence of the road obstacle area is detected based on the first road surface information. When the distance between the vehicle and the road obstacle area is less than or equal to the second threshold, second road surface information is collected, and a real-time obstacle map is generated based on the second road surface information, and the second threshold is less than the first threshold; the second obstacle map is obtained, and the vehicle's driving path is determined based on the second obstacle map, and the second obstacle map is an obstacle map generated by the cloud-side device based on the real-time obstacle map.

Description

Vehicle driving obstacle avoidance method and device

Technical Field

The embodiment of the application relates to the field of vehicles, in particular to a vehicle driving obstacle avoidance method and device.

Background

The unmanned technology is a comprehensive technology based on artificial intelligence. With the development of unmanned technology, unmanned technology has been applied in many scenes, in which surface mine is one of the scenes where unmanned technology first lands. In an unmanned scene of an open mine, due to heavy vehicle load, a running road surface of the vehicle mainly comprises soft rock environments such as mudstones, rubble rocks and the like, a pothole area is easy to form, water is easy to accumulate in a rainy season, and a pothole road section is easy to cause the vehicle to overturn. Therefore, how to safely and efficiently pass through the hollow area becomes a pain spot problem of the open air mining area.

In the existing vehicle driving obstacle avoidance scheme, a vehicle acquires concave-convex state information of a road surface through a sensor and generates a concave-convex map of the road surface, and when the vehicle drives the concave-convex road surface again, the vehicle can plan a path based on the concave-convex map so as to slow down or bypass in a region where the vehicle passes through the concave-convex road surface obstacle. However, in the surface mine scene, the road surface is soft due to the soft rock environment, and the concave-convex road surface obstacle area of the road surface can also change along with the running of the vehicle and the change of weather, so that the accuracy of obstacle avoidance of the vehicle based on the concave-convex map planning path is poor.

Disclosure of Invention

The embodiment of the application provides a vehicle driving obstacle avoidance method, wherein in the method, a vehicle can acquire road surface information of a road surface obstacle area in real time and conduct path planning when approaching to the road surface obstacle area, so that the accuracy of vehicle driving obstacle avoidance is improved. The embodiment of the application also provides electronic equipment, a vehicle, a computer readable storage medium and a computer program product corresponding to the vehicle driving obstacle avoidance method.

In a first aspect, an embodiment of the present application provides a vehicle driving obstacle avoidance method, where the method may be performed by a vehicle driving obstacle avoidance device, or may be performed by a component of the vehicle driving obstacle avoidance device, such as a processor, a chip, or a chip system, or may be implemented by a logic module or software that may implement all or part of the functions of the vehicle driving obstacle avoidance device. The method provided in the first aspect includes that the vehicle driving obstacle avoidance device obtains a first obstacle map, wherein the first obstacle map is used for predicting the position of a road obstacle area for the vehicle under a far vision distance, and the far vision distance comprises a distance from the vehicle which is larger than a first threshold value. When the distance between the vehicle and the road surface obstacle area is smaller than or equal to a first threshold value, the vehicle driving obstacle avoidance device acquires first road surface information, and the existence of the road surface obstacle area is detected according to the first road surface information. When the distance between the vehicle and the road surface obstacle area is smaller than or equal to a second threshold value, the vehicle driving obstacle avoidance device acquires second road surface information and generates a real-time obstacle map according to the second road surface information, and the second threshold value is smaller than the first threshold value. The vehicle driving obstacle avoidance device acquires a second obstacle map and determines a driving path of the vehicle based on the second obstacle map, wherein the second obstacle map is an obstacle map generated by cloud side equipment based on the real-time obstacle map.

According to the vehicle driving obstacle avoidance device, when a vehicle approaches a road obstacle region, real-time road information of the road obstacle region can be acquired again, and the obstacle map is updated based on the real-time road information, so that obstacle avoidance failure caused by change of the road obstacle region is avoided.

In some possible implementations, when the vehicle determines that the road surface obstacle region exists based on the first road surface information, the vehicle is controlled to decelerate or the travel path of the vehicle is adjusted. The distance between the first threshold and the second threshold from the vehicle may be referred to as a middle vision distance, that is, when the vehicle driving obstacle avoidance device enters the middle vision distance of the vehicle in the road surface obstacle region, the vehicle driving obstacle avoidance device may determine whether the road surface obstacle region exists based on the first road surface information collected by the vehicle, and control the vehicle to slow down in advance or control the vehicle to adjust the driving path.

According to the vehicle driving obstacle avoidance device, the distance between the vehicle and the road surface obstacle area can be determined based on the first obstacle map under the far vision distance, and the vehicle is controlled to decelerate before the vehicle approaches the road surface obstacle area, so that the vehicle is prepared for acquiring real-time road surface information again under the near vision distance, the acquisition accuracy of the road surface information is improved, and meanwhile, the driving safety of the vehicle is improved.

In some possible implementations, after the vehicle driving obstacle avoidance device generates the real-time obstacle map according to the second road surface information, the real-time obstacle map is sent to the cloud-side device. The vehicle driving obstacle avoidance device receives a second obstacle map sent by cloud side equipment, wherein the second obstacle map is an obstacle map generated by the cloud side equipment based on fusion of a real-time obstacle map and a crowdsourcing obstacle map, and the crowdsourcing obstacle map is an obstacle map generated by different vehicles.

According to the embodiment of the application, the cloud side equipment generates the second obstacle map based on the fusion of the real-time obstacle map and the crowdsourcing obstacle map, so that the accuracy of the second obstacle map is improved.

In some possible implementations, in the process that the vehicle driving obstacle avoidance device acquires the first obstacle map, the vehicle driving obstacle avoidance device performs clustering operation on road surface information acquired by the vehicle based on a clustering algorithm, identifies a road surface obstacle region, the road surface obstacle region comprises a convex region and a concave region, and marks the vehicle driving obstacle avoidance device in the map according to the road surface obstacle region to obtain the first obstacle map. Further, the vehicle travel obstacle avoidance device may also identify the type of obstacle of the road surface obstacle region, such as falling rocks, ruts, and potholes, based on the clustering algorithm.

According to the vehicle driving device in the embodiment of the application, the position of the road surface obstacle area can be marked in the obstacle map, so that the distance between the vehicle and the road surface obstacle area can be accurately determined based on the pose of the vehicle, and the accuracy of obstacle avoidance of vehicle driving is further improved.

In some possible implementations, the vehicle driving obstacle avoidance device calculates risk values of different areas of the road surface based on the road surface information, the risk values are used for indicating driving difficulties of the different areas of the road surface, the vehicle driving obstacle avoidance device provides a display interface of the first obstacle map, and the display interface is used for displaying the risk values of the different areas of the road surface.

According to the vehicle driving obstacle avoidance device provided by the embodiment of the application, the display interface of the obstacle map can be provided, and the risk values of different road obstacle areas in the obstacle map are displayed through the display interface, so that the visibility of the obstacle map is improved.

In some possible implementations, the vehicle driving obstacle avoidance device converts a coordinate system of the first obstacle map into a driving coordinate system of the vehicle, the driving coordinate system of the vehicle is used for calculating a distance between the vehicle and the road surface obstacle region, and the vehicle driving obstacle avoidance device marks a laser point cloud acquired by a vehicle sensor in the driving coordinate system based on the converted first obstacle map.

According to the vehicle driving obstacle avoidance device, the marking data of the road surface obstacle area is obtained based on the vehicle sensor, and the pose of the road surface obstacle area is corrected by using the marking data, so that the accuracy of the road surface obstacle area in an obstacle map is improved.

In some possible implementations, after the vehicle driving obstacle avoidance device establishes the first obstacle map, the vehicle driving obstacle avoidance device may operate by grouping the vehicles, update the first road surface information collected by the first vehicle in the group to generate a second obstacle map, and plan a driving path of the vehicle group based on the second obstacle map.

According to the vehicle driving obstacle avoidance device, the path planning can be carried out on the vehicle grouping based on the second obstacle map, and as the vehicles are grouped, the vehicle driving obstacle avoidance device only needs to collect road surface information by configuring sensors such as a laser radar and the like on the first vehicle, so that the reduction of the distribution of the vehicle sensors is realized, and the vehicle driving obstacle avoidance cost is reduced.

In some possible implementations, in determining the driving path of the vehicle based on the second obstacle map, the vehicle driving obstacle avoidance device generates a path point of the vehicle according to the size of the road surface obstacle region in the second obstacle map and the wheel distance of the vehicle, where the path point is used to indicate coordinates that the center of the vehicle passes through. The vehicle travel obstacle avoidance device determines a travel route of the vehicle based on the waypoints.

According to the vehicle driving obstacle avoidance device provided by the embodiment of the application, the driving path planning of the vehicle can be performed according to the size of the road surface obstacle area in the obstacle map, so that the accuracy of vehicle driving obstacle avoidance is improved.

In some possible implementations, the passing point of the control vehicle is the center of the road obstacle region when the wheel spacing is capable of covering the size of the road obstacle region.

According to the vehicle driving obstacle avoidance device, the vehicle can be controlled to cross the road obstacle area, and therefore accuracy of vehicle driving obstacle avoidance is improved.

In a second aspect, an embodiment of the present application provides a vehicle driving obstacle avoidance apparatus, including an acquisition unit and a processing unit. The acquisition unit is used for acquiring a first obstacle map, wherein the first obstacle map is used for predicting the position of a road surface obstacle area for a vehicle under a far vision range, and the far vision range comprises a distance which is greater than a first threshold value from the vehicle. The processing unit is used for collecting first road surface information when the distance between the vehicle and the road surface obstacle area is smaller than or equal to a first threshold value, and detecting the existence of the road surface obstacle area according to the first road surface information. The processing unit is further used for collecting second road surface information when the distance between the vehicle and the road surface obstacle area is smaller than or equal to a second threshold value, and generating a real-time obstacle map according to the second road surface information, wherein the second threshold value is smaller than the first threshold value. The acquisition unit is also configured to acquire a second obstacle map. The processing unit is used for determining a driving path of the vehicle based on a second obstacle map, wherein the second obstacle map is an obstacle map generated by cloud side equipment based on the real-time obstacle map.

In some possible implementations, the processing unit is further configured to control the vehicle to slow down or adjust a travel path of the vehicle when the vehicle determines that the road surface obstacle region exists based on the first road surface information.

In some possible implementations, the obtaining unit is further configured to send a real-time obstacle map to the cloud-side device. The acquisition unit is specifically configured to receive a second obstacle map sent by the cloud-side device, where the second obstacle map is an obstacle map generated by the cloud-side device based on fusion of a real-time obstacle map and a crowdsourcing obstacle map, and the crowdsourcing obstacle map is an obstacle map generated by different vehicles.

In some possible implementations, the processing unit is further configured to perform a clustering operation on road surface information collected by the vehicle based on a clustering algorithm, and identify a road surface obstacle region, where the road surface obstacle region includes a convex region and a concave region. And marking in the map according to the road surface obstacle area to obtain a first obstacle map.

In some possible implementations, the processing unit is further configured to calculate a risk value of the different areas of the road surface based on the road surface information, the risk value being used to indicate a difficulty of driving the different areas of the road surface. The processing unit is also used for providing a display interface of the first obstacle map, and the display interface is used for displaying risk values of different areas of the road surface.

In some possible implementations, the processing unit is further configured to convert the coordinate system of the first obstacle map to a driving coordinate system of the vehicle. And labeling the laser point cloud acquired by the vehicle sensor in the running coordinate system based on the converted first obstacle map.

In some possible implementations, the processing unit is specifically configured to generate a route point of the vehicle according to the size of the road surface obstacle region in the second obstacle map and the wheel distance of the vehicle, where the route point is used to indicate coordinates through which the center of the vehicle passes. A travel route of the vehicle is determined based on the waypoints.

In some possible implementations, the processing unit is further configured to control the passing point of the vehicle to be a center of the road surface obstacle region when the wheel spacing is capable of covering a size of the road surface obstacle region.

In a third aspect, an embodiment of the present application provides an in-vehicle device, including a processor, where the processor is coupled to a memory, and the processor is configured to execute instructions in the memory, where the instructions are executed by the processor, to cause the in-vehicle device to perform the method according to the first aspect or any one of the possible implementation manners of the first aspect.

In a fourth aspect, an embodiment of the present application provides a vehicle configured to perform the method according to the first aspect or any one of the possible implementation manners of the first aspect.

In a fifth aspect, an embodiment of the present application provides a vehicle driving obstacle avoidance system, where the vehicle driving obstacle avoidance system includes a vehicle and a cloud side device, and the vehicle is configured to perform the method in the first aspect or any one of the possible implementation manners of the first aspect.

In a sixth aspect, an embodiment of the present application provides a computer readable storage medium, where instructions are stored, the instructions when executed cause a computer to perform the method according to the first aspect or any one of the possible implementation manners of the first aspect.

In a seventh aspect, embodiments of the present application provide a computer program product comprising instructions which, when executed, cause a computer to implement the method of the first aspect or any one of the possible implementation manners of the first aspect.

It can be appreciated that any of the above-mentioned beneficial effects achieved by the vehicle driving obstacle avoidance device, the vehicle-mounted device, the vehicle driving obstacle avoidance system, the computer readable medium or the computer program product may refer to the beneficial effects in the corresponding method, and will not be described herein.

Drawings

Fig. 1 is a schematic diagram of a system architecture of a vehicle driving obstacle avoidance system according to an embodiment of the present application;

Fig. 2 is a schematic flow chart of a vehicle driving obstacle avoidance method according to an embodiment of the present application;

FIG. 3 is a schematic flow chart of another method for avoiding obstacle during driving of a vehicle according to an embodiment of the present application;

FIG. 4 is a schematic diagram of generating an obstacle map according to an embodiment of the present application;

FIG. 5 is a schematic diagram of a laser point cloud label according to an embodiment of the present application;

FIG. 6 is a schematic diagram of updating an obstacle map according to an embodiment of the present application;

Fig. 7 is a schematic diagram of a vehicle driving path planning according to an embodiment of the present application;

FIG. 8 is a schematic diagram of a vehicle driving obstacle avoidance according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of a vehicle driving obstacle avoidance device according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of a vehicle-mounted device according to an embodiment of the present application;

fig. 11 is a schematic structural diagram of a vehicle according to an embodiment of the present application.

Detailed Description

The embodiment of the application provides a vehicle driving obstacle avoidance method, which is used for improving the accuracy of vehicle driving obstacle avoidance.

The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. 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.

In embodiments of the application, words such as "exemplary" or "such as" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "e.g." in an embodiment should not be taken as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.

First, some terms related to the embodiments of the present application are described to facilitate understanding by those skilled in the art.

The inertial measurement unit (inertial measurement unit, IMU) is a device integrated with multiple sensors, and provides accurate motion state and attitude information for the vehicle by measuring and fusing data of the multiple sensors, so as to support control, navigation and positioning functions of the vehicle. The various sensors include a three-axis accelerometer, a three-axis gyroscope, and a three-axis magnetometer. The IMU processes and fuses the measured data of the three-axis accelerometer, the three-axis gyroscope and the three-axis magnetometer, thereby providing information such as acceleration, angular speed, attitude change and the like of the vehicle.

Clustering algorithms are an unsupervised learning method for grouping data objects into similar groups or clusters. Clustering algorithms assign similar objects to the same cluster by calculating the similarity between data objects, while assigning dissimilar objects to different clusters.

The following describes an example of a scenario in which the vehicle driving obstacle avoidance method provided by the embodiment of the present application is applied.

The embodiment of the application is applied to the unmanned scene of the surface mine. The surface mine scene has high requirements on safe and efficient passage of unmanned mining vehicles, pits are easy to generate when the mining vehicles pass through a soft road, the road surface condition is complex, and the surface mine has high frequency in rainy and snowy days, so that the vehicles are easy to topple and stop production. In the unmanned scheme of the existing surface mine, cloud side equipment can acquire concave-convex state information of a road surface based on a vehicle through a sensor to generate a concave-convex map of the road surface, and a cloud server plans a running path of the vehicle based on the concave-convex map, so that the vehicle can decelerate or bypass in a region with obstacle through the concave-convex road surface. However, in the surface mine scene, the vehicle is heavy in load, the non-paved road surface is softer, the road surface is easy to sink to form a pit, so that the road surface obstacle area of the road surface is changed frequently along with the running of the vehicle, and the obstacle avoidance accuracy based on the obstacle map planning path is poor.

In view of the above, the embodiment of the application provides a vehicle driving obstacle avoidance method, and the cloud side device can establish an obstacle map based on road surface information acquired by a vehicle and plan a vehicle driving path based on the obstacle map, meanwhile, the vehicle can predict an obstacle region under a far distance based on the obstacle map to realize long-distance deceleration, acquire road surface information again in real time under a near distance, update the obstacle map based on the newly acquired real-time road surface information, adjust the driving track of the vehicle according to the updated map, and improve the accuracy of the vehicle passing through the road surface obstacle region such as a pothole.

In order to make the technical solution of the present application clearer and easier to understand, the system architecture of the present application is described below with reference to the accompanying drawings.

Referring to fig. 1, fig. 1 is a schematic diagram of a system architecture of a vehicle driving obstacle avoidance system according to an embodiment of the present application. In the example shown in fig. 1, the vehicle travel obstacle avoidance system 10 includes a vehicle end 100, a cloud-side apparatus 200, and a client 300. The vehicle end 100 comprises a radar module 101, a positioning module 102, a communication module 103 and an inertial navigation module 104. The specific functions of the various components of the vehicle travel obstacle avoidance system 10 are described in detail below.

The vehicle end 100 is configured to collect road surface information of a road surface on which the vehicle is traveling, and generate an obstacle map based on the collected road surface information. The vehicle end 100 is also configured to receive an obstacle map sent by the cloud-side apparatus 200. The vehicle side 101 is also used for planning a travel path of the vehicle based on the obstacle map.

The vehicle end 100 includes a radar module 101, a positioning module 102, a communication module 103, and an inertial navigation module 104. The radar module 101 is configured to acquire road surface information, where the road surface information includes point cloud data of a road surface, and the radar module 101 is, for example, a laser radar and a millimeter wave radar. The laser radar is a high-precision sensor of the vehicle end 100, and acquires three-dimensional point cloud data of the surrounding environment of the vehicle in real time by emitting laser beams and receiving reflections thereof.

The positioning module 102 is used to obtain the position of the vehicle in the map. The positioning module 102 fuses various technologies to achieve accurate positioning of the vehicle. Specifically, the positioning module 102 is capable of calculating accurate position, velocity, and attitude information of the vehicle by receiving global positioning system GPS satellite signals and using an inertial measurement unit IMU.

The communication module 103 is used for the vehicle end 100 to communicate with the cloud-side device 200. Specifically, the communication module 103 uploads the obstacle map generated by the vehicle end 100 to the cloud-side apparatus 200, and receives the updated obstacle map transmitted by the cloud-side apparatus 200.

The inertial navigation module 104 is used to make measurements of the body pose of the vehicle end 100. Specifically, the inertial navigation module 104 may calculate the position, velocity, and attitude information of the vehicle end 100 through the inertial measurement unit IMU, and provide the information to the positioning module 102 for accurate positioning of the vehicle.

The cloud-side device 200 is configured to receive one or more obstacle maps sent by the vehicle end 100, and fuse the obstacle maps sent by different vehicle ends to generate an updated obstacle map.

The client 300 is configured to provide a visual interaction interface for interaction with the cloud-side device 200 to a user. The user can view the obstacle map generated by the cloud-side device 200 and the driving state of the vehicle end 100 through the client 300, and can also control the vehicle end 100 in real time through the client 300.

It is understood that the client 300 may be software or an application deployed on the vehicle end 100, the cloud side device 200, or other terminal devices, and is not limited in particular.

Based on the vehicle driving obstacle avoidance system 10 shown in fig. 1, the application further provides a vehicle driving obstacle avoidance method. The following describes a vehicle driving obstacle avoidance method provided by the embodiment of the application with reference to the embodiment.

Referring to fig. 2, fig. 2 is a flow chart of a vehicle driving obstacle avoidance method according to an embodiment of the application. In the example shown in fig. 2, the method comprises the steps of:

S201, the vehicle end 100 acquires a first obstacle map, and the first obstacle map is used for predicting the position of a road surface obstacle area for the vehicle under a far vision distance.

The vehicle end 100 first collects road surface information, which is used to indicate the height difference of different positions of the road surface, and the road surface information includes point cloud data of the different positions of the road surface. In the process of acquiring the road surface information by the vehicle end 100, the vehicle end 100 scans the road surface on which the vehicle runs through a laser radar so as to obtain laser point clouds of the road surface on which the vehicle runs, and meanwhile, the vehicle end 100 acquires the pose information of the vehicle through a satellite navigation real-time dynamic positioning and Inertial Measurement Unit (IMU), and the laser point clouds and the pose information are used for analyzing the height difference of concave-convex areas at different positions of the road surface.

Referring to fig. 3, fig. 3 is a flow chart of another obstacle avoidance method for vehicle driving according to an embodiment of the application. In the example shown in fig. 3, the vehicle end 100 acquires pose information of the vehicle based on the satellite navigation real-time dynamic positioning and inertial measurement unit IMU, wherein the pose information includes a coordinate position of the vehicle end 100 in a map and a heading angle (yaw) of the vehicle.

In the example shown in fig. 3, the vehicle end 100 collects point cloud data of the road surface based on a lidar. For example, when an unmanned mine car is driven in a road surface mine, the laser radar continuously emits laser beams, and the distance and intensity between each laser beam and the surrounding environment are recorded. When the laser beam irradiates the indentations of the road surface, the laser radar detects the reflected light and measures the distance from the object, and converts the measurement data into point cloud data.

After the vehicle end 100 collects the road surface information, a first obstacle map is generated based on the collected road surface information. The first obstacle map is capable of displaying a position of the road surface obstacle region in the map such that the vehicle is able to avoid the road surface obstacle region based on the first obstacle map. The following specifically describes a process in which the vehicle end 100 generates a first obstacle map of a road surface based on road surface information acquired by the vehicle.

After the vehicle end 100 collects the road surface information, the clustering algorithm is used for carrying out clustering operation on the road surface information collected by the vehicle, a road surface obstacle region is identified, the road surface obstacle region comprises a convex region and a concave region, and the vehicle end 100 marks in a map according to the road surface obstacle region to obtain a first obstacle map.

Specifically, the vehicle end 100 projects the collected laser point cloud into a horizontal two-dimensional map, and rasterizes the two-dimensional map, and marks the height of each collected point in the grid of the horizontal two-dimensional map. The vehicle end 100 performs a clustering operation on the acquisition points in the horizontal two-dimensional map, and identifies the convex area and the concave area of the road surface. Further, the vehicle end 100 may also identify the type of obstacle of the road surface obstacle region, such as falling rocks, ruts, and potholes, based on the clustering algorithm. For example, when the collection points exhibit a small occupancy of the raised cut grid, it is identified as falling rocks. When the collection points are raised and the grid occupation is distributed in a large number along a straight line, the points are identified as ruts. When the collection points appear to exist as both bulges and hollows, the collection points are identified as pits.

The vehicle end 100 groups the laser point cloud data into different clusters through a clustering algorithm in the process of analyzing and calculating the point cloud data. Wherein each cluster has similar features or attributes, which may be location, shape, size, etc. In summary, the goal of the clustering algorithm is to aggregate similar points together while separating different points to better understand and analyze the point cloud data, identifying point cloud data features.

Referring to fig. 4, fig. 4 is a schematic diagram of a cloud side device for establishing a first obstacle map according to an embodiment of the present application. In the example shown in fig. 4, after the vehicle end 100 acquires pose information and laser point clouds of the vehicle, the vehicle end 100 analyzes the laser point clouds of different positions and clusters to generate a first obstacle map.

For example, the vehicle ends 100 are clustered by collection point height, wherein dark collection points are collection points above the road surface, i.e., raised areas of the road surface, and light collection points are collection points below the road surface, i.e., recessed areas of the road surface, in fig. 4. The vehicle end 100 marks these dark and light acquisition points in a two-dimensional horizontal map, thereby generating a first obstacle map.

In a possible implementation manner, the risk values of the different areas of the road surface are calculated based on the road surface information, the risk values are used for indicating the driving difficulty of the different areas of the road surface, and the vehicle end 100 can also provide a display interface of the first obstacle map through the client 300, where the display interface is used for displaying the risk values of the different areas of the road surface.

Specifically, in the process of calculating the risk values of different areas of the road surface by the vehicle end 100 based on the road surface information, the vehicle end 100 calculates the gradient and the roughness of the acquisition point based on the pose information and the laser point cloud, and determines the risk value of the acquisition point based on the gradient and the roughness of the acquisition point. Further, after the vehicle end 100 calculates the risk value values of the different collection points, the risk values of the different collection points may be marked on the first obstacle map, and the first obstacle map marked with the risk values may be displayed through the display interface.

The gradient θ satisfies the following formula:

θ=cos^-1(n1*ng)

Wherein θ is an included angle between n1 and ng, n1 is a normal vector of the vehicle running slope, n1= (x, y, z), and ng is a gravity direction, namely ng= (0, 1).

The above roughness calculation satisfies the following formula:

where hi is the height of the ith sampling point and h is the average height of the sampling points.

In the embodiment of the application, the gradient and the roughness of the acquisition point are positively correlated with the risk value, and the larger the gradient or the roughness is, the larger the risk value corresponding to the area in the first obstacle map is. With continued reference to fig. 4, in the example shown in fig. 4, the vehicle end 100 marks risk values of different areas of the first obstacle map with different colors, for example, a risk value of a dark area is higher and a risk value of a light area is lower in the first obstacle map. The user may view risk values for different areas in the first obstacle map through the client 300.

Note that, the process of calculating the risk value of the first obstacle map region may also be performed in the cloud-side device 200, and after the vehicle end 100 generates the first obstacle map, the first obstacle map is sent to the cloud-side device 100, and the cloud-side device 200 calculates the risk value of the different road surface regions based on the road surface information.

In a possible embodiment, after the vehicle end 100 generates the first obstacle map, the vehicle end 100 may send the first obstacle map to the cloud side device 200, where the cloud side device 200 further performs the first obstacle map according to the obstacle maps collected by different vehicles, and sends the updated first obstacle map to the vehicle end 100, so that the vehicle end 100 can predict the distance of the vehicle from the road surface obstacle area under the far distance according to the updated first obstacle map, and perform the driving path planning based on the updated first obstacle map.

In a possible implementation manner, the cloud side device 200 converts the coordinate system of the first obstacle map into the running coordinate system of the vehicle, and the cloud side device 200 marks the laser point cloud collected by the vehicle end 100 based on the converted first obstacle map, so as to obtain marking data, where the marking data is used for marking a road obstacle area corresponding to the laser point cloud. For example, the cloud-side apparatus 200 marks different areas of the laser point cloud as falling rocks, ruts, potholes, and the like based on the converted first obstacle map. The coordinate matrix T _C of the road surface obstacle area under the running coordinate system of the vehicle satisfies the following formula:

Where T _m is the coordinate matrix of the vehicle and T _p is the coordinate matrix of the road surface obstacle region.

Referring to fig. 5, fig. 5 is a schematic diagram of a laser point cloud according to an embodiment of the present application. In the example shown in fig. 5, the vehicle end 100 marks the laser point cloud collected by the vehicle, where the content marked in the marking frame in the laser point cloud is a pothole area. In the process of determining the boundary of the marking frame, the vehicle end 100 extracts point cloud data of the area, selects the point P1 with the lowest height as a reference point, calculates the boundary of the marking frame by taking the reference point as an origin, fits an x-direction straight line based on the reference point P1, simultaneously takes a straight line central point to generate a vertical vector, calculates the point closest to the x-direction as a boundary P2, determines the length of the marking frame, uniformly samples 5 equal parts of the nearest boundary point based on the connecting line of the P1 and the P2, and determines the width of the marking frame.

It should be noted that, the vehicle end 100 may determine the boundary of the labeling frame of the laser point cloud by adopting various methods, which is not limited in particular. Various bounding box boundary calculation methods such as least squares, curve fitting, contour extraction, etc. are used.

S202, when the distance between the vehicle and the road surface obstacle area is smaller than or equal to a first threshold value, the vehicle end 100 collects first road surface information, and detects the existence of the obstacle area according to the first road surface information.

After the vehicle end 100 acquires the first obstacle map, the vehicle end 100 travels on the road surface based on the first obstacle map. Specifically, the vehicle end 100 may perform vehicle path planning with respect to the first obstacle map, or may perform vehicle driving path planning based on the updated first obstacle map sent by the cloud side device 200.

In a possible embodiment, the vehicle end 100 may also receive a vehicle control instruction generated by the cloud-side apparatus 200 based on the first obstacle map, and control the travel path of the vehicle according to the vehicle control instruction.

When the distance between the vehicle and the road surface obstacle region is less than or equal to a first threshold value, the vehicle end 100 collects first road surface information and detects the existence of the obstacle region based on the first road surface information, wherein the first road surface information comprises one or more of pose information, laser point cloud or visual images.

In the embodiment of the present application, the distance from the vehicle end 100 that is greater than the first threshold is referred to as distance vision, the distance from the vehicle end 100 that is greater than the second threshold and less than or equal to the first threshold is referred to as distance vision, the distance from the vehicle end 100 that is less than the second threshold is referred to as distance vision, the first threshold is greater than the second threshold, for example, the first threshold is 50 meters, and the second threshold is 25 meters.

The vehicle driving obstacle avoidance device predicts the position of a road surface obstacle region based on an obstacle map, the camera can acquire accurate road surface information under the middle vision range, the laser radar cannot acquire the accurate road surface information, and the camera and the laser radar can acquire the accurate road surface information under the near vision range.

In a possible implementation manner, after the vehicle end 100 collects the first road surface information, when the vehicle end 100 determines that the road surface obstacle area exists based on the first road surface information, the vehicle is controlled to slow down, or the vehicle is controlled to adjust the running path of the vehicle.

In a possible embodiment, after the vehicle end 100 collects the first road surface information, the first road surface information is sent to the cloud side device 200, and after the cloud side device 200 receives the first road surface information sent by the vehicle end 100, when the cloud side device 200 determines that a road surface obstacle area exists based on the first road surface information, a deceleration instruction is sent to the vehicle end 100, and the vehicle end 100 controls the vehicle to decelerate according to the deceleration instruction sent by the cloud side device 200.

Or when the cloud-side apparatus 200 determines that the road surface obstacle region exists based on the first road surface information, a vehicle travel path adjustment instruction is transmitted to the vehicle end 100, and the vehicle end 100 controls the travel path of the vehicle according to the vehicle travel path adjustment instruction transmitted by the cloud-side apparatus 200.

S203, when the distance between the vehicle and the road surface obstacle area is smaller than or equal to a second threshold value, the vehicle end 100 collects second road surface information and generates a real-time obstacle map according to the second road surface information.

When the distance between the vehicle and the road surface obstacle area is smaller than or equal to the second threshold value, the vehicle end 100 collects second road surface information and generates a real-time obstacle map based on the second road surface information, and specifically, the second road surface information includes pose information of the vehicle and laser point clouds corresponding to the pose information.

The vehicle end 100 regenerates the real-time obstacle map based on the second road surface information for determining the real-time height difference of the road surface obstacle region. The process of the vehicle end 100 regenerating the real-time obstacle map based on the second road surface information is similar to the process of the vehicle end 100 generating the first obstacle map in the above step 201, and will not be described in detail.

With continued reference to fig. 3, in the example shown in fig. 3, during the driving of the vehicle end 100 based on the first obstacle map, the vehicle end 100 performs long-distance detection based on the first obstacle map, that is, determines a distance between the vehicle end 100 and a road obstacle region in the first obstacle map according to the first obstacle map, when the distance is less than 50m, the cloud-side device 200 controls the vehicle end 100 to decelerate, and when the distance is less than 25m, the vehicle end 100 performs short-distance detection on the road obstacle region, that is, the vehicle end 100 re-collects the second road information, and the vehicle end 100 generates a real-time obstacle map based on the second road information and sends the real-time obstacle map to the cloud-side device 200.

S204, the vehicle end 100 sends a real-time obstacle map to the cloud-side equipment 200.

The vehicle end 100 transmits a real-time obstacle map to the cloud-side apparatus 200.

S205, the cloud side equipment 200 fuses the real-time obstacle map and the crowdsourcing obstacle map to obtain a second obstacle map.

The cloud-side device 200 fuses the real-time obstacle map and the crowdsourcing obstacle map to obtain a second obstacle map. Specifically, after receiving the real-time obstacle map sent by the vehicle end 100, the cloud-side device 200 merges the crowd-sourced obstacle map meeting the fusion condition with the regenerated real-time obstacle map to obtain a second obstacle map. The fusion condition comprises that the data format of the crowdsourcing obstacle map is consistent with that of the real-time obstacle map, the acquisition state of the crowdsourcing obstacle map is consistent with that of the real-time obstacle map, or the acquisition coordinates of the crowdsourcing obstacle map and the real-time obstacle map are consistent.

Referring to fig. 6, fig. 6 is a schematic flow chart of the obstacle map fusion according to the embodiment of the application. In the example shown in fig. 6, after the cloud-side apparatus 200 receives the real-time obstacle map transmitted from the vehicle end 100, the cloud-side apparatus 200 acquires a crowdsourcing obstacle map stored in an object store (OBS) bucket, which generates an obstacle map for the cloud-side apparatus 200 based on road surface information acquired by a plurality of vehicles.

In the example shown in fig. 6, when the crowdsourcing obstacle map acquired by the cloud side device 200 meets the fusion condition, the cloud side device 200 fuses the crowdsourcing obstacle map with the real-time obstacle map to obtain a second obstacle map. The cloud-side apparatus 200 transmits the second obstacle map to the vehicle-side 100. The cloud-side device 200 performs fusion calculation on the crowdsourcing obstacle map and the real-time obstacle map to satisfy the following formula:

Wherein α ² represents a high uncertainty, s and p represent a crowdsourcing obstacle map and a real-time obstacle map, respectively, J _s represents a Jacobian matrix of the crowdsourcing obstacle map, J _p represents a Jacobian matrix of the real-time obstacle map, v _z and The mean and covariance of the heights are shown, respectively.

In the embodiment of the application, the cloud side device 200 can receive the obstacle maps sent by one or more vehicle ends 100, so as to aggregate the obstacle maps sent by different vehicles and update the confidence coefficient of the road obstacle region. For example, when the road surface information of a certain vehicle causes a false detection of a road surface obstacle region due to an environmental influence such as dust, the cloud side gradually decreases the confidence of the false detection of the road surface obstacle region by the road surface information of a plurality of vehicles. The process of calculating the confidence level is described by way of example below.

For example, the cloud-side apparatus 200 rasterizes the acquired obstacle maps, respectively, wherein the grid corresponding to the ground area is 0, and each grid corresponding to the non-ground area stores the height of the obstacle area, wherein the ground area is an area of 0.2m or less, and the non-ground area is an area of 0.2m or more. Thereafter, the cloud-side apparatus 200 calculates the number of times that the non-ground area grid and the ground area grid appear in the road surface obstacle area correspondence grid, increases the threshold s for the obstacle score if the non-ground area grid appears once, and scores-1 for the obstacle score if the ground area grid appears 1 time. The initial obstacle score is 50, and if the obstacle score is smaller than 0 or larger than 100, the obstacle score is cut off, so that the value is ensured to be in a range from 0 to 100. Wherein s satisfies the following formula:

where α1 is the variance of the height of the grid storage barrier corresponding to the non-ground area, and α2 is the variance of the height of the grid storage barrier corresponding to the ground area.

The cloud side equipment 200 loops and iterates the data for a plurality of times, calculates the confidence coefficient of the road surface obstacle region, namely the obstacle probability of the road surface obstacle region, wherein the calculation formula is the obstacle score/100, and if the confidence coefficient of the road surface obstacle region is greater than 0.6, the road surface obstacle region is reserved as the obstacle region.

S206, the cloud-side equipment 200 sends a second obstacle map to the vehicle end 100.

The cloud-side apparatus 200 transmits the second obstacle map to the vehicle end 100.

S207, the vehicle end 100 collects and determines the running path of the vehicle based on the second obstacle map.

After the vehicle end 100 receives the second obstacle map transmitted by the cloud-side device 200, the vehicle end 100 may perform path planning of the vehicle based on the second obstacle map transmitted by the cloud-side device 200.

In a possible embodiment, the vehicle end 100 may also receive a vehicle control instruction generated by the cloud-side apparatus 200 based on the second obstacle map, and control the travel path of the vehicle based on the vehicle control instruction.

It should be noted that, after the cloud-side device 200 establishes the obstacle map, the vehicle end 100 may operate through grouping, and only a sensor such as a laser radar needs to be configured on the first vehicle, so as to implement the configuration reduction of the vehicle sensor.

In some possible implementations, in determining the driving path of the vehicle based on the second obstacle map by the vehicle end 100 or the cloud-side device 200, the vehicle end 100 or the cloud-side device 200 generates a route point of the vehicle according to the size of the road surface obstacle region in the second obstacle map and the wheel-space of the vehicle, where the route point is used to indicate coordinates through which the center of the vehicle passes. The vehicle-end 100 or the cloud-side apparatus 200 determines the travel route of the vehicle based on the route points.

Referring to fig. 7, fig. 7 is a schematic diagram of an obstacle map according to an embodiment of the application. In the example shown in fig. 7, the dashed box is the wheel-space prediction range of the vehicle in the obstacle map, where the triangle indicates the running direction angle of the vehicle, and the dark box is the range of the road-surface obstacle region in the obstacle map. The vehicle-end 100 or the cloud-side apparatus 200 may determine the approach point of the vehicle based on the relative positional relationship between the wheel-space prediction range of the vehicle, the range of the road surface obstacle region, and the road surface boundary.

In some possible implementations, when the wheel spacing can cover the size of the road surface obstacle region, the vehicle end 100 or the cloud-side apparatus 200 controls the passing point of the vehicle to be the center of the road surface obstacle region.

As can be seen from the example shown in fig. 7, when the vehicle wheel-space prediction range can cover the range of the road surface obstacle region, the vehicle end 100 or the cloud-side apparatus 200 is at a path point where the center of the road surface obstacle region can be regarded as the vehicle. When the vehicle wheel-space prediction range cannot cover the range of the road surface obstacle region, the vehicle end 100 or the cloud-side apparatus 200 may cause the wheel-space prediction range of the vehicle to bypass the road surface obstacle region when determining the approach point of the vehicle.

Referring to fig. 8, fig. 8 is a schematic diagram of a driving obstacle avoidance device according to an embodiment of the present application. In the example shown in fig. 8, the vehicle end 100 controls the passing point of the vehicle to be the center of the road surface obstacle region through which the vehicle rides. For example, when the wheel spacing of the vehicle is greater than the road surface obstacle region, the vehicle can ride through the road surface obstacle region. For another example, when the wheel spacing of the vehicle exceeds the road width of the road surface, the vehicle selects another route to detour. For another example, when the height difference of the road surface obstacle area exceeds a preset height value, a parking alarm process is performed.

In the example shown in fig. 8, for example, the vehicle has a front-rear wheel base of 5.1m and a left-right wheel base of 3m, and the wheel space prediction range is 5.1×3m, and if the road surface obstacle region is 1×2.1, the vehicle can ride through the road surface obstacle region.

As can be seen from the above embodiments, in the embodiments of the present application, when the vehicle approaches the road obstacle region, the vehicle end 100 may re-collect real-time road information of the road obstacle region, and update the obstacle map based on the real-time road information, so as to avoid failure of obstacle avoidance caused by change of the road obstacle region, and improve accuracy of vehicle driving obstacle avoidance by using the vehicle driving obstacle avoidance method.

Based on the method embodiment, the embodiment of the application also provides a vehicle driving obstacle avoidance device, and the vehicle driving obstacle avoidance device provided by the embodiment of the application is specifically described below.

Referring to fig. 9, fig. 9 is a schematic structural diagram of a vehicle driving obstacle avoidance device according to an embodiment of the present application. In the example shown in fig. 9, a vehicle travel obstacle avoidance apparatus 900 is used to implement the steps performed by the cloud-side device 200 in the above embodiments, and the vehicle travel obstacle avoidance apparatus 900 includes an acquisition unit 901 and a processing unit 902.

Wherein the acquiring unit 901 is configured to acquire a first obstacle map for predicting a position of a road surface obstacle region for a vehicle at a distance of a distance including a distance from the vehicle that is greater than a first threshold value. The processing unit 902 is configured to collect first road surface information when a distance between the vehicle and the road surface obstacle region is less than or equal to a first threshold value, and detect the existence of the road surface obstacle region according to the first road surface information. The processing unit 902 is further configured to collect second road surface information when the distance between the vehicle and the road surface obstacle region is less than or equal to a second threshold, and generate a real-time obstacle map according to the second road surface information, where the second threshold is less than the first threshold. The acquisition unit 901 is also for acquiring a second obstacle map. The processing unit 902 is configured to determine a travel path of the vehicle based on a second obstacle map, which is an obstacle map generated by the cloud-side device based on the real-time obstacle map.

In some possible implementations, the processing unit 902 is further configured to control the vehicle to slow down, or adjust a travel path of the vehicle, when the vehicle determines that the road surface obstacle region exists based on the first road surface information.

In some possible implementations, the acquiring unit 901 is further configured to send a real-time obstacle map to the cloud-side device. The obtaining unit 901 is specifically configured to receive a second obstacle map sent by the cloud side device, where the second obstacle map is an obstacle map generated by the cloud side device based on fusion of a real-time obstacle map and a crowd-sourced obstacle map, and the crowd-sourced obstacle map is an obstacle map generated by different vehicles.

In some possible implementations, the processing unit 902 is further configured to perform a clustering operation on the road surface information collected by the vehicle based on a clustering algorithm, and identify a road surface obstacle region, where the road surface obstacle region includes a convex region and a concave region. And marking in the map according to the road surface obstacle area to obtain a first obstacle map.

In some possible implementations, the processing unit 902 is further configured to calculate a risk value of the different area of the road surface based on the road surface information, where the risk value is used to indicate a driving difficulty of the different area of the road surface. The processing unit 902 is further configured to provide a display interface of the first obstacle map, where the display interface is configured to display risk values of different areas of the road surface.

In some possible implementations, the processing unit 902 is further configured to convert the coordinate system of the first obstacle map to a running coordinate system of the vehicle. And labeling the laser point cloud acquired by the vehicle sensor in the running coordinate system based on the converted first obstacle map.

In some possible implementations, the processing unit 902 is specifically configured to generate a route point of the vehicle according to the size of the road surface obstacle region in the second obstacle map and the wheel-space of the vehicle, where the route point is used to indicate coordinates through which the center of the vehicle passes. A travel route of the vehicle is determined based on the waypoints.

In some possible implementations, the processing unit 902 is further configured to control the passing point of the vehicle to be the center of the road obstacle region when the wheel spacing is capable of covering the size of the road obstacle region.

It should be understood that the division of units or modules in the above apparatus is merely a division of logic functions, and may be fully or partially integrated into one physical entity or may be physically separated when actually implemented. And the units or modules in the device can be realized in the form of software which is called by the processing element, can be realized in the form of hardware, and can be realized in the form of software which is called by the processing element. For example, each unit or module may be a processing element that is set up separately, may be implemented as an integrated unit in a certain chip of the apparatus, or may be stored in a memory in the form of a program, and the function of the unit or module is called and executed by a certain processing element of the apparatus. Furthermore, all or part of these units or modules may be integrated together or may be implemented independently. The processing element described herein may in turn be a processor, which may be an integrated circuit with signal processing capabilities. In implementation, each step of the method or each unit or module above may be implemented by an integrated logic circuit of hardware in a processor element or implemented in the form of software called by a processing element.

It should be noted that, for simplicity of description, the above method embodiments are all described as a series of combinations of actions, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, and further, that the embodiments described in the specification belong to preferred embodiments, and that the actions are not necessarily required by the present application.

Other reasonable combinations of steps that can be conceived by those skilled in the art from the foregoing description are also within the scope of the application. Furthermore, those skilled in the art will be familiar with the preferred embodiments, and the description of the preferred embodiments does not necessarily require the application.

Referring to fig. 10, fig. 10 is a schematic structural diagram of an in-vehicle apparatus according to an embodiment of the present application. As shown in fig. 10, the in-vehicle apparatus 1000 includes a processor 1001, a memory 1002, a communication interface 1003, and a bus 1004, the processor 1001, the memory 1002, and the communication interface 1003 being coupled by a bus (not labeled in the figure). The memory 1002 stores instructions that, when executed in the memory 1002, the in-vehicle apparatus 1000 executes the method executed by the terminal apparatus 100 or the cloud-side apparatus 200 in the above-described method embodiment.

The in-vehicle device 1000 may be one or more integrated circuits configured to implement the above methods, such as one or more Application SPECIFIC INTEGRATED Circuits (ASICs), or one or more microprocessors (DIGITAL SIGNAL processors, DSPs), or one or more field programmable gate arrays (field programmable GATE ARRAY, FPGAs), or a combination of at least two of these integrated circuit forms. For another example, when the units in the apparatus may be implemented in the form of a scheduler of processing elements, the processing elements may be general-purpose processors, such as a central processing unit (central processing unit, CPU) or other processor that may invoke a program. For another example, the units may be integrated together and implemented in the form of a system-on-a-chip (SOC).

The processor 1001 may be a central processing unit (central processing unit, CPU), but may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL processors, DSPs), application Specific Integrated Circuits (ASICs), field programmable gate arrays (field programmable GATE ARRAY, FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combinations thereof. The general purpose processor may be a microprocessor, but in the alternative, it may be any conventional processor.

The memory 1002 may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an erasable programmable ROM (erasable PROM), an electrically erasable programmable EPROM (EEPROM), or a flash memory. The volatile memory may be random access memory (random access memory, RAM) which acts as external cache memory. By way of example, and not limitation, many forms of RAM are available, such as static random access memory (STATIC RAM, SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate synchronous dynamic random access memory (doubledata DATE SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (ENHANCED SDRAM, ESDRAM), synchronous link dynamic random access memory (SYNCHLINK DRAM, SLDRAM), and direct memory bus random access memory (direct rambus RAM, DRRAM).

The memory 1002 stores executable program codes, and the processor 1001 executes the executable program codes to realize the functions of the terminal apparatus 100 or the cloud-side apparatus 200, respectively, thereby realizing the content recommendation method described above. That is, the memory 1002 has stored thereon instructions for executing the content recommendation method described above.

The memory 1002 stores executable program codes, and the processor 1001 executes the executable program codes to implement the functions of the aforementioned acquisition unit 901 and processing unit 902, respectively, thereby implementing the aforementioned obstacle avoidance method for a vehicle. That is, the memory 1002 has instructions stored thereon for performing the vehicle obstacle avoidance method described above.

The communication interface 1003 uses a transceiver module such as, but not limited to, a network interface card, a transceiver, or the like to enable communication between the in-vehicle device 1000 and other devices or communication networks.

The bus 1004 may include a power bus, a control bus, a status signal bus, and the like in addition to a data bus. The bus may be a peripheral component interconnect express (PERIPHERAL COMPONENT INTERCONNECT EXPRESS, PCIe) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, a unified bus (unified bus, ubus or UB), a computer express link (compute express link, CXL), a cache coherent interconnect protocol (cache coherent interconnect for accelerators, CCIX), or the like. The buses may be divided into address buses, data buses, control buses, etc.

Referring to fig. 11, fig. 11 is a schematic structural diagram of a vehicle according to an embodiment of the application. As shown in fig. 11, the vehicle 1100 includes at least one processor 1101 and a communication interface 1103, the communication interface 1103 and the at least one processor 1101 are interconnected by a line, and the at least one processor 1101 is configured to execute a computer program or instructions, where the computer program or instructions, when executed, perform the method performed by the vehicle end 100 in the above-described method embodiment.

In a possible implementation, the vehicle 1100 described above further includes at least one memory 1102, where the memory 1102 stores executable program codes, and the processor 1101 executes the executable program codes to implement the functions of the acquiring unit 901 and the processing unit 902, respectively, so as to implement the vehicle driving obstacle avoidance method described above. That is, the memory 1102 stores instructions for executing the vehicle travel obstacle avoidance method described above.

In another embodiment of the present application, a computer readable storage medium is provided, where computer executable instructions are stored, and when a processor of the device executes the computer executable instructions, the device executes a method executed by the vehicle end 100 or the cloud side device 200 in the above method embodiment.

In another embodiment of the present application, there is also provided a computer program product comprising computer-executable instructions stored in a computer-readable storage medium. When the processor of the device executes the computer-executable instructions, the device executes the method executed by the vehicle-side 100 or the cloud-side device 200 in the above-described method embodiment.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.

In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown 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 units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. The storage medium includes a usb disk, a removable hard disk, a read-only memory (ROM), a random-access memory (RAM, random access memory), a magnetic disk, an optical disk, or other various media capable of storing program codes.

Claims (21)

1. A vehicle obstacle avoidance method, characterized in that it is applied to a vehicle obstacle avoidance device, comprising: Acquire a first obstacle map, where the first obstacle map is used to predict the position of a road obstacle area for the vehicle at a long sight distance, where the long sight distance includes a distance from the vehicle that is greater than a first threshold; When the distance between the vehicle and the road obstacle area is less than or equal to a first threshold, collecting first road information, and detecting the existence of the road obstacle area according to the first road information; When the distance between the vehicle and the road obstacle area is less than or equal to a second threshold, second road information is collected, and a real-time obstacle map is generated based on the second road information, and the second threshold is less than the first threshold; a second obstacle map is obtained, and a driving path of the vehicle is determined based on the second obstacle map, and the second obstacle map is an obstacle map generated by the cloud-side device based on the real-time obstacle map. 2. The method according to claim 1, characterized in that the method further comprises: When the vehicle determines that the road obstacle area exists based on the first road information, the vehicle is controlled to decelerate, or the driving path of the vehicle is adjusted. 3. The method according to claim 1 or 2, characterized in that after generating the real-time obstacle map according to the second road surface information, the method further comprises: Sending the real-time obstacle map to the cloud-side device; The obtaining of the second obstacle map comprises: Receive the second obstacle map sent by the cloud-side device, where the second obstacle map is an obstacle map generated by the cloud-side device based on the fusion of the real-time obstacle map and the crowdsourced obstacle map, and the crowdsourced obstacle map is an obstacle map generated by different vehicles. 4. The method according to any one of claims 1 to 3, characterized in that the step of obtaining the first obstacle map further comprises: Performing clustering operation on the road surface information collected by the vehicle based on a clustering algorithm to identify the road surface obstacle area, wherein the road surface obstacle area includes a raised area and a sunken area; The first obstacle map is obtained by marking the road obstacle area in a map. 5. The method according to any one of claims 1 to 4, characterized in that the method further comprises: Calculating risk values of different areas of the road surface based on the road surface information, wherein the risk values are used to indicate the driving difficulty of different areas of the road surface; A display interface of the first obstacle map is provided, wherein the display interface is used to display risk values of different areas of the road surface. 6. The method according to any one of claims 1 to 5, characterized in that the method further comprises: Converting the coordinate system of the first obstacle map to the driving coordinate system of the vehicle; The laser point cloud acquired by the vehicle sensor in the driving coordinate system is annotated based on the converted first obstacle map. 7. The method according to any one of claims 1 to 6, characterized in that determining the driving path of the vehicle based on the second obstacle map comprises: Generating a waypoint of the vehicle according to the size of the road obstacle area in the second obstacle map and the wheel spacing of the vehicle, wherein the waypoint is used to indicate the coordinates through which the center of the vehicle passes; A driving route of the vehicle is determined based on the waypoints. 8. The method according to claim 7, characterized in that the method further comprises: When the wheel spacing can cover the size of the road obstacle area, the waypoint of the vehicle is controlled to be the center of the road obstacle area. 9. A vehicle obstacle avoidance device, comprising: an acquisition unit, configured to acquire a first obstacle map, wherein the first obstacle map is used to predict a position of a road obstacle area for a vehicle at a long sight distance, wherein the long sight distance includes a distance from the vehicle that is greater than a first threshold; a processing unit, configured to collect first road surface information when the distance between the vehicle and the road surface obstacle area is less than or equal to a first threshold, and detect the existence of the road surface obstacle area according to the first road surface information; The processing unit is further configured to collect second road surface information and generate a real-time obstacle map according to the second road surface information when the distance between the vehicle and the road surface obstacle area is less than or equal to a second threshold, and the second threshold is less than the first threshold; The acquisition unit is further used to acquire a second obstacle map. The processing unit is used to determine the driving path of the vehicle based on the second obstacle map, where the second obstacle map is an obstacle map generated by the cloud-side device based on the real-time obstacle map. 10. The device according to claim 9, characterized in that the processing unit is further used for: When the vehicle determines that the road obstacle area exists based on the first road information, the vehicle is controlled to decelerate, or the driving path of the vehicle is adjusted. 11. The device according to claim 9 or 10, characterized in that the acquisition unit is further used for: Sending the real-time obstacle map to the cloud-side device; The acquisition unit is specifically used for: Receive the second obstacle map sent by the cloud-side device, where the second obstacle map is an obstacle map generated by the cloud-side device based on the fusion of the real-time obstacle map and the crowdsourced obstacle map, and the crowdsourced obstacle map is an obstacle map generated by different vehicles. 12. The device according to any one of claims 9 to 11, characterized in that the processing unit is further used for: Performing clustering operation on the road surface information collected by the vehicle based on a clustering algorithm to identify the road surface obstacle area, wherein the road surface obstacle area includes a raised area and a sunken area; The first obstacle map is obtained by marking the road obstacle area in a map. 13. The device according to any one of claims 9 to 12, characterized in that the processing unit is further used for: Calculating risk values of different areas of the road surface based on the road surface information, wherein the risk values are used to indicate the driving difficulty of different areas of the road surface; A display interface of the first obstacle map is provided, wherein the display interface is used to display risk values of different areas of the road surface. 14. The device according to any one of claims 9 to 13, characterized in that the processing unit is further used for: Converting the coordinate system of the first obstacle map to the driving coordinate system of the vehicle; The laser point cloud acquired by the vehicle sensor in the driving coordinate system is annotated based on the converted first obstacle map. 15. The device according to any one of claims 9 to 14, characterized in that the processing unit is specifically used for: Generating a waypoint of the vehicle according to the size of the road obstacle area in the second obstacle map and the wheel spacing of the vehicle, wherein the waypoint is used to indicate the coordinates through which the center of the vehicle passes; A driving route of the vehicle is determined based on the waypoints. 16. The device according to claim 15, characterized in that the processing unit is further used for: When the wheel spacing can cover the size of the road obstacle area, the waypoint of the vehicle is controlled to be the center of the road obstacle area. 17. An in-vehicle device, characterized in that it comprises a processor, the processor is coupled to a memory, the processor is used to execute instructions in the memory, and when the instructions are executed by the processor, the in-vehicle device executes the method according to any one of claims 1 to 8. 18. A vehicle, characterized in that the vehicle is used to execute the method according to any one of claims 1 to 8. 19. A vehicle obstacle avoidance system, characterized in that it comprises a vehicle and a cloud-side device, wherein the vehicle is used to execute the method described in any one of claims 1 to 8. 20. A computer-readable storage medium having instructions stored thereon, wherein when the instructions are executed, a computer is caused to execute the method according to any one of claims 1 to 8. 21. A computer program product, comprising instructions, wherein when the instructions are executed, a computer implements the method according to any one of claims 1 to 8.