A method and corresponding device for automatically handling traffic accidents of an automatic driving vehicle

Abstract

The present application discloses a method for automatically handling traffic accidents of an autonomous driving vehicle and a related device. The method includes: after a traffic accident occurs to an autonomous driving vehicle, determining the driving trajectory of the autonomous driving vehicle within a set time period before and after the traffic accident based on a point cloud map; determining the movement trajectory of at least one target object involved in the traffic accident within a set time period based on the point cloud map and the image information within the set time period; fusing the driving trajectory of the autonomous driving vehicle and the movement trajectory of at least one target object with time and space coordinates to restore the collision trajectory of the traffic accident; based on the collision trajectory, making a judgment on the traffic accident, and executing an accident handling decision based on the judgment result. In this way, the collision trajectory is accurately restored, the responsibility judgment of the traffic accident is objectively and accurately made, and the accident handling decision is promptly executed based on the judgment result, so as to avoid traffic congestion and improve the efficiency of accident handling.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, specifically to technical fields such as intelligent transportation and image processing, and in particular to a method for automatically handling traffic accidents of an autonomous driving vehicle and related devices. Background Art

[0002] As autonomous driving technology matures, more and more autonomous vehicles are allowed on the road. When autonomous vehicles, as traffic participants, directly or indirectly cause traffic accidents, they lack a mechanism to handle accidents, causing the vehicles to stay at their original locations for a long time waiting for processing, greatly increasing traffic congestion.

[0003] Moreover, even if people come to handle the case, they often use non-site law enforcement to determine the responsibility for the traffic accident for minor accidents. That is, both parties take photos at the scene for a short time to keep evidence, report the case to the traffic police and the insurance company at the same time, and quickly move the vehicle away from the accident scene to avoid further traffic congestion. However, the above operations are limited by the photography level of the two parties involved in the accident and their different descriptions of the accident, which may lead to the risk of errors or insufficient data support in the subsequent accident determination.

[0004] Therefore, it is urgent to find a traffic accident handling solution for autonomous driving vehicles to solve the above-mentioned problems of untimely accident handling, incomplete accident data, and inaccurate accident judgment. Summary of the invention

[0005] The present application provides a method and related devices for automatically handling traffic accidents of an autonomous driving vehicle to solve the problems in the prior art of untimely accident handling, incomplete accident data, and inaccurate accident judgment after a traffic accident occurs with an autonomous driving vehicle.

[0006] The technical solution is as follows:

[0007] In a first aspect, a method for automatically handling a traffic accident of an autonomous driving vehicle is provided, comprising:

[0008] After a traffic accident occurs with an autonomous vehicle, the driving trajectory of the autonomous vehicle within a set time period before and after the traffic accident is determined based on the point cloud map;

[0009] Determine, based on the point cloud map and the image information within the set time period, a movement trajectory of at least one target object involved in the traffic accident within the set time period;

[0010] The driving trajectory of the autonomous driving vehicle and the movement trajectory of the at least one target object are integrated in time and space coordinates to restore the collision trajectory of the traffic accident;

[0011] Based on the collision trajectory, the traffic accident is judged, and the accident handling decision is executed according to the judgment result.

[0012] In a possible implementation, determining the driving trajectory of the autonomous driving vehicle within a set time period before and after the traffic accident based on the point cloud map specifically includes:

[0013] constructing a point cloud map based on driving data of the autonomous driving vehicle within a set time period before and after the traffic accident occurs, identifying multiple contours of the autonomous driving vehicle from the point cloud map, and determining a first driving trajectory of the autonomous driving vehicle based on the multiple contours;

[0014] Based on the center of mass of the autonomous driving vehicle, a motion control model constructed using kinematic principles is used to simulate a second driving trajectory of the autonomous driving vehicle within the set time period;

[0015] The first driving trajectory is compared and integrated with the second driving trajectory to obtain the driving trajectory of the autonomous driving vehicle within the set time period.

[0016] In a possible implementation, based on the point cloud map and the image information within the set time period, determining the movement trajectory of at least one target object involved in the traffic accident within the set time period specifically includes:

[0017] For a stationary target object, based on the image information of the target object during the collision process collected by the camera and combined with the shape change of the target object in the point cloud space in the point cloud map, the collision deformation of the target object is determined as the movement trajectory of the target object within the set time period; and / or;

[0018] For a moving target object, the target object is identified from the image information collected by the camera within the set time period, and the movement trajectory of the target object within the set time period is determined by combining the point cloud centroid of the target object calculated by the point cloud map.

[0019] In a possible implementation, the target object is identified from the image information collected by the camera within the set time period, and the movement trajectory of the target object within the set time period is determined in combination with the point cloud centroid of the target object calculated by the point cloud map, specifically including:

[0020] An object recognition model trained based on a convolutional neural network identifies a target object from image information collected by a camera within the set time period;

[0021] According to the spatial distribution of the target object in the image, the point cloud changes of the target object are determined in the point cloud map based on the density clustering algorithm, and the point cloud contour of the target object is segmented in combination with the image contour to calculate the point cloud centroid of the target object;

[0022] The centroids of all point clouds belonging to the same target object are counted to obtain the movement trajectory of the target object within the set time period.

[0023] In a possible implementation, the determination result includes the accident level; then executing the accident handling decision according to the determination result specifically includes:

[0024] The determination result is reported; and a decision is made based on the accident level whether to automatically leave the accident scene immediately after the determination is completed or to wait for rescue.

[0025] In a second aspect, a traffic accident automatic handling device for an autonomous driving vehicle is provided, comprising:

[0026] A first determination module is used to determine the driving trajectory of the autonomous driving vehicle within a set time period before and after the traffic accident occurs based on the point cloud map after the autonomous driving vehicle occurs a traffic accident;

[0027] A second determination module is used to determine the movement trajectory of at least one target object involved in the traffic accident within the set time period based on the point cloud map and the image information within the set time period;

[0028] A restoration module, used to fuse the driving trajectory of the autonomous driving vehicle and the movement trajectory of the at least one target object in time and space coordinates to restore the collision trajectory of the traffic accident;

[0029] The determination module is used to determine the traffic accident based on the collision trajectory and to make an accident handling decision according to the determination result.

[0030] In a third aspect, a computer-readable storage medium is provided, wherein at least one instruction is stored in the storage medium, and the at least one instruction is loaded and executed by a processor to implement the method of the above-mentioned aspect and any possible implementation manner.

[0031] In a fourth aspect, an electronic device is provided, including:

[0032] at least one processor; and

[0033] a memory communicatively connected to the at least one processor; wherein,

[0034] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any possible implementation manner and the aspects described above.

[0035] According to a fifth aspect, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the above-mentioned aspects and any possible implementation method.

[0036] In a sixth aspect, an autonomous driving vehicle is provided, comprising the electronic device as described above.

[0037] The beneficial effects of the technical solution provided by this application include at least:

[0038] It can be seen from the above technical solutions that the embodiment of the present application can determine the driving trajectory of the autonomous driving vehicle within a set time period before and after the traffic accident occurs based on the point cloud map; determine the movement trajectory of at least one target object involved in the traffic accident within the set time period based on the point cloud map and the image information within the set time period; fuse the driving trajectory of the autonomous driving vehicle and the movement trajectory of at least one target object with time and space coordinates to restore the collision trajectory of the traffic accident; judge the traffic accident based on the collision trajectory, and execute the accident handling decision according to the judgment result. In this way, the collision trajectory can be accurately restored, the responsibility for the traffic accident can be determined more objectively and accurately, and the accident handling decision can be executed in a timely manner according to the judgment result, thereby avoiding traffic congestion caused by minor accidents and improving the efficiency of accident handling.

[0039] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 It is a schematic diagram of the steps of a method for automatically handling traffic accidents of an autonomous driving vehicle provided in an embodiment of the present application.

[0042] Figure 2 It is a flow chart of a method for automatically handling traffic accidents of an autonomous driving vehicle provided in an embodiment of the present application.

[0043] Figure 3 This is a structural block diagram of an automatic traffic accident handling device for an autonomous driving vehicle provided in yet another embodiment of the present application.

[0044] Figure 4 It is a block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0046] Obviously, the described embodiments are only part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0047] It should be noted that the terminal devices involved in the embodiments of the present application may include but are not limited to mobile phones, personal digital assistants (PDAs), wireless handheld devices, tablet computers and other smart devices; display devices may include but are not limited to personal computers, televisions and other devices with display functions.

[0048] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0049] In view of the problems of time-consuming, traffic jams, and inaccurate accident judgments when handling ordinary traffic accidents in the prior art, the above problems will also exist when the accident vehicle is upgraded from an ordinary vehicle to an autonomous driving vehicle. Moreover, due to the characteristics of autonomous driving vehicles, when there is no one driving, after an accident occurs with an autonomous driving vehicle, it is necessary to notify vehicle maintenance personnel to come to the scene of the accident to check and handle the matter. This will result in a longer stay time, and untimely handling will lead to more serious traffic jams.

[0050] In view of this, the present application provides an automatic traffic accident handling solution for an autonomous driving vehicle, and the inventive concept thereof is that: it does not require on-site participation of vehicle maintenance personnel or other insurance personnel, etc., and only requires that after a traffic accident occurs in an autonomous driving vehicle, the autonomous driving vehicle determines the driving trajectory of the vehicle within a set time period before and after the traffic accident occurs, as well as the movement trajectory of one or more other target objects involved in the traffic accident, and then restores the collision trajectory of the traffic accident by means of trajectory fusion. Afterwards, based on the collision trajectory, the autonomous driving vehicle automatically determines the traffic accident and executes the accident handling decision according to the determination result. In this way, the collision trajectory can be accurately restored, the responsibility for the traffic accident can be determined more objectively and accurately, and the accident handling decision can be executed in a timely manner according to the determination result, thereby avoiding traffic congestion caused by minor accidents and improving the efficiency of accident handling.

[0051] Reference Figure 1 As shown, it is a schematic diagram of the steps of a method for automatically handling traffic accidents of an autonomous driving vehicle provided in an embodiment of the present application. It should be noted that the executor of the method for automatically handling traffic accidents may be an automatic traffic accident handling device of an autonomous driving vehicle. In the present application, the automatic traffic accident handling device may be a software module with computing and data processing capabilities, or an electronic device integrated with a similar software module. Optionally, the automatic traffic accident handling device in the present application may be an autonomous driving vehicle, or a module installed and integrated on an autonomous driving vehicle, or a vehicle networking platform that provides vehicle services for autonomous driving vehicles. The autonomous driving vehicle in the present application may be, for example, an electric truck, an unmanned delivery vehicle, an unmanned taxi, and other types of vehicles.

[0052] like Figure 1 As shown, the method for automatically handling a traffic accident of an autonomous driving vehicle may include the following steps:

[0053] Step 102: After the autonomous driving vehicle is involved in a traffic accident, the driving trajectory of the autonomous driving vehicle within a set time period before and after the traffic accident is determined based on the point cloud map.

[0054] Typically, autonomous vehicles are equipped with various sensors to obtain environmental information, such as the most common lidar and cameras, to sense whether there are vehicles, pedestrians, or other obstacles around.

[0055] As an important component of the autonomous driving system, LiDAR uses laser technology to obtain and process environmental information in real time, providing vehicles with high-precision perception and positioning capabilities, and can provide good information on the location and distance of obstacles. Cameras have relatively rich color and texture information, and are good at judging the type of obstacles, but they cannot give too accurate information on the location and distance. The perception system of autonomous driving requires the cooperation of LiDAR and cameras to perceive the location and movement status of obstacles around the vehicle.

[0056] The working principle of LiDAR is that the perception layer continuously emits laser beams through LiDAR and receives light pulses reflected back by objects. The time difference between the two signals is calculated based on the speed of light to determine the relative distance between the vehicle and the object. The angle of the object is measured by horizontal rotation scanning, and the height information is obtained by obtaining signals at different pitch angles. After sensing the distance, angle and other information between the object, a three-dimensional point cloud map can be obtained. Then, machine learning algorithms can be used to detect obstacles of interest (such as vehicles and pedestrians) from the three-dimensional point cloud map to achieve real-time environmental perception and obstacle avoidance functions.

[0057] In the present application scheme, a point cloud map can be constructed based on the driving data of the autonomous driving vehicle within a set time period before and after a traffic accident occurs, and multiple contours of the autonomous driving vehicle can be identified from the point cloud map, and the first driving trajectory of the autonomous driving vehicle can be determined based on the multiple contours as the self-driving vehicle's driving trajectory.

[0058] Considering that the point cloud map is determined based on light pulses, it is not completely continuous and has certain risk intervals. Therefore, in order to obtain a more accurate self-vehicle driving trajectory, this application also proposes another self-vehicle driving trajectory determination scheme, which can include the following steps when implemented:

[0059] The first step is to construct a point cloud map based on the driving data of the autonomous driving vehicle within a set time period before and after the traffic accident, identify multiple contours of the autonomous driving vehicle from the point cloud map, and determine the first driving trajectory of the autonomous driving vehicle based on the multiple contours.

[0060] When constructing a point cloud map, the outline of the autonomous driving vehicle is also constructed in the point cloud map. The first driving trajectory of the autonomous driving vehicle can be roughly determined based on multiple outlines of the autonomous driving vehicle during its driving process in the point cloud map.

[0061] The second step is to simulate the second driving trajectory of the autonomous driving vehicle within the set time period by using a motion control model built using kinematic principles based on the center of mass of the autonomous driving vehicle.

[0062] At the same time, a motion control model is built using kinematic principles. The motion control model can be a combination of formulas based on various kinematic formulas, such as speed, acceleration, various angles, distance and other motion parameters. Then, the second driving trajectory of the autonomous driving vehicle within a set time period is simulated with the center of mass of the autonomous driving vehicle as the center. Specifically, the angles such as the slip angle and the heading angle can be input into the built motion control model to output the required second driving trajectory.

[0063] The third step is to compare and fuse the first driving trajectory with the second driving trajectory to obtain the driving trajectory of the autonomous driving vehicle within the set time period.

[0064] Finally, the two driving trajectories obtained by the autonomous driving vehicle in different ways are compared and fused to complement each other. The coordinate points with more spatial coordinates are retained and the coordinate points with the least spatial coordinates are deleted, so as to normalize the trajectories and obtain the driving trajectory of the autonomous driving vehicle within the set time period.

[0065] Step 104: Based on the point cloud map and the image information within the set time period, determine the movement trajectory of at least one target object involved in the traffic accident within the set time period.

[0066] It should be understood that it is not only vehicles that are traveling or moving on the road, but also pedestrians. Therefore, vehicles may be involved in traffic accidents: other self-driving vehicles or electric bicycles or electric tricycles or bicycles; they may also be pedestrians: walking pedestrians or stationary pedestrians; they may also be road facilities: roadblocks, traffic cones, road guardrails, bus stops, roadside trash cans, green belts, etc.

[0067] Therefore, the target object involved in this traffic accident may be one or more. When there are multiple target objects, these target objects may all be stationary, or all may be moving, or some may be stationary and some may be moving. Then, according to the number and classification of the target objects involved in this traffic accident, the movement trajectory of the target objects can be determined in the following ways:

[0068] A target object

[0069] If the target object is stationary, based on the image information of the target object during the collision collected by the camera and combined with the shape change of the target object in the point cloud space in the point cloud map, the collision deformation of the target object is determined as the movement trajectory of the target object within the set time period;

[0070] If it is a moving target object, the target object is identified from the image information collected by the camera within the set time period, and the movement trajectory of the target object within the set time period is determined in combination with the point cloud centroid of the target object calculated by the point cloud map.

[0071] Multiple target objects

[0072] If the multiple target objects are all stationary, based on the image information of the target objects during the collision process collected by the camera and combined with the shape change of the target objects in the point cloud space in the point cloud map, the collision deformation of the target objects is determined as the movement trajectory of the target objects within the set time period;

[0073] If the multiple target objects are all moving, the target objects are identified from the image information collected by the camera within the set time period, and the movement trajectory of the target objects within the set time period is determined by combining the point cloud mass center of the target objects calculated by the point cloud map;

[0074] If some of the multiple target objects are stationary and some are moving, then, for the partially stationary target objects, based on the image information of the target objects during the collision process captured by the camera and combined with the shape change of the target objects in the point cloud space in the point cloud map, the collision deformation of the target objects is determined as the movement trajectory of the target objects within the set time period; for the partially moving target objects, the target objects are identified from the image information captured by the camera within the set time period, and combined with the point cloud centroid of the target objects calculated by the point cloud map, the movement trajectory of the target objects within the set time period is determined.

[0075] In fact, for stationary target objects, the camera can be used to record images and videos of the collision process to confirm the shape change of the target object before and after the collision; the point cloud map can assist in confirming the spatial shape of the target object. Since stationary target objects have almost no displacement, the deformation before and after the collision can be regarded as the movement trajectory of the target object within the set time period.

[0076] Optionally, in the present application scheme, for a moving target object, the target object can be identified from the image information collected by the camera within the set time period based on an object recognition model trained by a convolutional neural network; according to the spatial distribution of the target object in the image, a density-based clustering algorithm is used to determine the point cloud changes of the target object in the point cloud map, and the point cloud contour of the target object is segmented in combination with the image contour to calculate the point cloud centroid of the target object; and the centroids of all point clouds belonging to the same target object are counted to obtain the movement trajectory of the target object within the set time period.

[0077] Specifically, the convolutional neural network (CNN) can be used to identify and classify target objects, and the moving objects involved in the accident can be found through feature recognition in historical images (pictures and videos); this process can introduce a self-feedback process to strengthen model training. Afterwards, based on the identified target objects and the distribution position of the image in space (coordinates and the relative spatial position of each object), the density-based clustering algorithm DBSCAN is used in the point cloud map to obtain the point cloud changes of the vehicle point cloud over time, and the image contour is combined to segment the vehicle point cloud shape, calculate the point cloud distribution center position, and output its trajectory map over time.

[0078] Therefore, by classifying the motion state of the target object, different methods are used to determine the movement trajectory of the target object, thereby improving the accuracy of trajectory confirmation.

[0079] Step 106: The driving trajectory of the autonomous driving vehicle and the movement trajectory of the at least one target object are fused in time and space coordinates to restore the collision trajectory of the traffic accident.

[0080] It should be noted that the trajectory fusion here can be performed by fusion of time and space coordinates, integrating the trajectories of different objects into a road scene. Furthermore, in order to obtain a more realistic and accurate collision trajectory, the fused trajectory can also be rendered, that is, the objects in the road scene are presented by rendering, thereby increasing the authenticity of the road scene and the collision trajectory.

[0081] Step 108: Based on the collision trajectory, the traffic accident is judged, and an accident handling decision is executed according to the judgment result.

[0082] Specifically, the autonomous driving vehicle can automatically determine the traffic accident based on the determined collision trajectory, that is, determine the responsibility for the traffic accident. Afterwards, it can determine whether to move the vehicle based on the determination result, or report the accident level to the cloud staff, implement remote dispatch and other operations, move the vehicle away, and avoid long-term traffic congestion.

[0083] Furthermore, the judgment result includes the accident level; then, when making a decision on the accident handling based on the judgment result, the judgment result can be reported; and the decision on whether to automatically leave the accident scene immediately after the judgment is completed or wait for rescue is made based on the accident level. Thus, the autonomous driving vehicle determines the accident level by itself, and independently decides whether to move the vehicle in time or wait for rescue based on the accident level, thereby improving the timeliness and efficiency of accident handling.

[0084] In this step, some traffic rules or accident determination criteria can be combined to facilitate the autonomous driving vehicle to determine responsibility based on the collision trajectory.

[0085] Reference Figure 2 As shown, a schematic diagram of the automatic handling process of traffic accidents of an autonomous driving vehicle provided in an embodiment of the present application.

[0086] Step 202: The autonomous driving vehicle collects accident information.

[0087] Step 204: Determine the driving trajectory of the vehicle based on the accident information.

[0088] Step 206: Determine the movement trajectory of other target objects based on the accident information.

[0089] Other target objects may be objects involved in the traffic accident, but they may not directly collide with the autonomous vehicle. They may be objects that indirectly cause the autonomous vehicle to collide. In other words, the autonomous vehicle or other target objects involved in the traffic accident may not directly collide with each other. They may collide indirectly, for example, when avoiding other objects and colliding with other objects.

[0090] Step 208: The vehicle's driving trajectory is integrated with the movement trajectory of other target objects to restore the collision trajectory.

[0091] Step 210: The autonomous driving vehicle determines the responsibility for the traffic accident.

[0092] Step 212: Make a decision based on the accident level in the determination result.

[0093] Specifically, it can be decided whether to move the vehicle in time according to the accident level. For example, if the accident level is low, it means the accident is not serious, and the vehicle can be moved in time after automatic evidence collection. If the accident level is high, it means the accident is serious and the vehicle may not be started. Therefore, the accident can be reported in time and the arrival of vehicle rescue can be waited for.

[0094] Step 214: Report the accident determination result and the fused trajectory to relevant units for verification.

[0095] Specifically, the accident determination results and the fused collision trajectory can be reported to the insurance company or the traffic police team for verification of the determination results to ensure that the determination is accurate and fair.

[0096] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0097] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0098] Figure 3 FIG. 1 shows a structural block diagram of an automatic traffic accident handling device for an automatic driving vehicle provided by an embodiment of the present application. Figure 3 As shown. The automatic traffic accident handling device 300 of the autonomous driving vehicle of this embodiment may include a first determination module 301, a second determination module 302, a restoration module 303 and a judgment module 304. Among them, the first determination module 301 is used to determine the driving trajectory of the autonomous driving vehicle within a set time period before and after the traffic accident occurs based on the point cloud map. The second determination module 302 is used to determine the movement trajectory of at least one target object involved in this traffic accident within the set time period based on the point cloud map and the image information within the set time period. The restoration module 303 is used to fuse the driving trajectory of the autonomous driving vehicle and the movement trajectory of the at least one target object with time and space coordinates to restore the collision trajectory of this traffic accident. The judgment module 304 is used to judge this traffic accident based on the collision trajectory, and execute the accident handling decision according to the judgment result.

[0099] It should be noted that part or all of the automatic traffic accident handling device of the autonomous driving vehicle of this embodiment may be an application located in the local terminal, or may also be a functional unit such as a plug-in or software development kit (SDK) set in the application located in the local terminal, or may also be a processing engine located in a network-side server, or may also be a distributed system located on the network side, for example, a processing engine or distributed system in an autonomous driving platform on the network side, etc. This embodiment does not specifically limit this.

[0100] It is understandable that the application may be a local program (nativeApp) installed on the local terminal, or may be a webpage program (webApp) of a browser on the local terminal, which is not limited in this embodiment.

[0101] Optionally, in a possible implementation of this embodiment, when the first determination module 301 determines the driving trajectory of the autonomous driving vehicle within a set time period before and after a traffic accident based on the point cloud map, it is specifically used to construct a point cloud map according to the driving data of the autonomous driving vehicle within a set time period before and after the traffic accident, and identify multiple contours of the autonomous driving vehicle from the point cloud map, and determine the first driving trajectory of the autonomous driving vehicle based on the multiple contours; based on the center of mass of the autonomous driving vehicle, a motion control model constructed using kinematic principles is used to simulate the second driving trajectory of the autonomous driving vehicle within the set time period; and the first driving trajectory is compared and merged with the second driving trajectory to obtain the driving trajectory of the autonomous driving vehicle within the set time period.

[0102] Optionally, in a possible implementation of the present embodiment, the second determination module 302 determines the movement trajectory of at least one target object involved in the traffic accident within the set time period based on the point cloud map and the image information within the set time period. Specifically, for a stationary target object, based on the image information of the target object during the collision process captured by the camera, and in combination with the shape change of the target object in the point cloud space in the point cloud map, the collision deformation of the target object is determined as the movement trajectory of the target object within the set time period; and / or; for a moving target object, identifying the target object from the image information captured by the camera within the set time period, and determining the movement trajectory of the target object within the set time period in combination with the point cloud centroid of the target object calculated by the point cloud map.

[0103] Optionally, in a possible implementation of the present embodiment, when the second determination module 302 identifies the target object from the image information collected by the camera within the set time period and determines the movement trajectory of the target object within the set time period in combination with the point cloud centroid of the target object calculated by the point cloud map, it is specifically used to identify the target object from the image information collected by the camera within the set time period based on an object recognition model trained by a convolutional neural network; determine the point cloud change of the target object in the point cloud map based on a density-based clustering algorithm according to the spatial distribution of the target object in the image, and segment the point cloud contour of the target object in combination with the image contour to calculate the point cloud centroid of the target object; and count the centroids of all point clouds belonging to the same target object to obtain the movement trajectory of the target object within the set time period.

[0104] Optionally, in a possible implementation of this embodiment, the judgment result includes an accident level; when the judgment module 304 executes an accident handling decision based on the judgment result, it is specifically used to report the judgment result; and decide whether to automatically leave the accident scene immediately or wait for rescue after the judgment is completed based on the accident level.

[0105] In this embodiment, after a traffic accident occurs in an autonomous driving vehicle, the driving trajectory of the autonomous driving vehicle in a set time period before and after the traffic accident can be determined based on the point cloud map; the movement trajectory of at least one target object involved in the traffic accident in the set time period can be determined based on the point cloud map and the image information in the set time period; the driving trajectory of the autonomous driving vehicle and the movement trajectory of at least one target object can be integrated with time and space coordinates to restore the collision trajectory of the traffic accident; based on the collision trajectory, the traffic accident can be judged, and the accident handling decision can be executed according to the judgment result. In this way, the collision trajectory can be accurately restored, the responsibility for the traffic accident can be determined more objectively and accurately, and the accident handling decision can be executed in a timely manner according to the judgment result, thereby avoiding traffic congestion caused by minor accidents and improving the efficiency of accident handling.

[0106] An embodiment of the present application provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is loaded and executed by a processor to implement the method for automatic handling of traffic accidents of an autonomous driving vehicle as described above.

[0107] An embodiment of the present application provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction, and the instruction is loaded and executed by the processor to implement automatic handling of traffic accidents of the autonomous driving vehicle as described above.

[0108] An embodiment of the present application provides an autonomous driving vehicle, comprising the electronic device as described above. Specifically, the autonomous driving vehicle may be a vehicle of level L2 or above.

[0109] In the technical solution of this application, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the relevant laws and regulations and do not violate public order and good morals.

[0110] Figure 4A schematic block diagram of an example electronic device 400 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0111] like Figure 4 As shown, the electronic device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0112] Multiple components in the electronic device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the electronic device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0113] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 401 performs the various methods and processes described above, such as the method for automatically handling traffic accidents of autonomous driving vehicles. For example, in some embodiments, the method for automatically handling traffic accidents of autonomous driving vehicles may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the method for automatically handling traffic accidents of autonomous driving vehicles described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured in any other appropriate manner (e.g., by means of firmware) to execute the method for automatic handling of traffic accidents of an autonomous driving vehicle.

[0114] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0115] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0116] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0117] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0118] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0119] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0120] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps disclosed in this application can be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in this application can be achieved, and this document does not limit this.

[0121] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for automatically handling traffic accidents of an autonomous driving vehicle, characterized in that: include: After a traffic accident occurs with an autonomous vehicle, the driving trajectory of the autonomous vehicle within a set time period before and after the traffic accident is determined based on the point cloud map; Determine, based on the point cloud map and the image information within the set time period, a movement trajectory of at least one target object involved in the traffic accident within the set time period; The driving trajectory of the autonomous driving vehicle and the movement trajectory of the at least one target object are integrated in time and space coordinates to restore the collision trajectory of the traffic accident; Based on the collision trajectory, the traffic accident is judged, and the accident handling decision is executed according to the judgment result.

2. The method according to claim 1, characterized in that Determine the driving trajectory of the autonomous driving vehicle within a set time period before and after the traffic accident based on the point cloud map, specifically including: constructing a point cloud map based on driving data of the autonomous driving vehicle within a set time period before and after the traffic accident occurs, identifying multiple contours of the autonomous driving vehicle from the point cloud map, and determining a first driving trajectory of the autonomous driving vehicle based on the multiple contours; Based on the center of mass of the autonomous driving vehicle, a motion control model constructed using kinematic principles is used to simulate a second driving trajectory of the autonomous driving vehicle within the set time period; The first driving trajectory is compared and integrated with the second driving trajectory to obtain the driving trajectory of the autonomous driving vehicle within the set time period.

3. The method according to claim 1 or 2, characterized in that Determining the movement trajectory of at least one target object involved in the traffic accident within the set time period based on the point cloud map and the image information within the set time period specifically includes: For a stationary target object, based on the image information of the target object during the collision process collected by the camera and combined with the shape change of the target object in the point cloud space in the point cloud map, the collision deformation of the target object is determined as the movement trajectory of the target object within the set time period; and / or; For a moving target object, the target object is identified from the image information collected by the camera within the set time period, and the movement trajectory of the target object within the set time period is determined by combining the point cloud centroid of the target object calculated by the point cloud map.

4. The method according to claim 3, characterized in that Identifying the target object from the image information collected by the camera within the set time period, and determining the movement trajectory of the target object within the set time period in combination with the point cloud centroid of the target object calculated by the point cloud map, specifically includes: An object recognition model trained based on a convolutional neural network identifies a target object from image information collected by a camera within the set time period; According to the spatial distribution of the target object in the image, the point cloud changes of the target object are determined in the point cloud map based on the density clustering algorithm, and the point cloud contour of the target object is segmented in combination with the image contour to calculate the point cloud centroid of the target object; The centroids of all point clouds belonging to the same target object are counted to obtain the movement trajectory of the target object within the set time period.

5. The method according to claim 1 or 2, characterized in that: The determination result includes the accident level; The accident handling decision is then executed according to the judgment result, including: Reporting the determination result; And based on the severity of the accident, the vehicle will decide whether to automatically leave the accident scene or wait for rescue immediately after the judgment is completed.

6. An automatic traffic accident handling device for an automatic driving vehicle, characterized in that: include: A first determination module is used to determine the driving trajectory of the autonomous driving vehicle within a set time period before and after the traffic accident occurs based on the point cloud map after the autonomous driving vehicle occurs a traffic accident; A second determination module is used to determine the movement trajectory of at least one target object involved in the traffic accident within the set time period based on the point cloud map and the image information within the set time period; A restoration module, used to fuse the driving trajectory of the autonomous driving vehicle and the movement trajectory of the at least one target object in time and space coordinates to restore the collision trajectory of the traffic accident; The determination module is used to determine the traffic accident based on the collision trajectory and to make an accident handling decision according to the determination result.

7. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-5.

9. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 5.

10. An autonomous driving vehicle comprising the electronic device as claimed in claim 7.

Images