Method and device for collision avoidance of an autonomous vehicle
By acquiring obstacle information and calculating vehicle pose using sensors, assessing collision risk, and executing collision avoidance measures, the safety issues of autonomous vehicles when deviating from their path or experiencing chassis failure are resolved, achieving more efficient collision avoidance.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NINGBO SINIAN ZHIJIA TECH CO LTD
- Filing Date
- 2023-03-27
- Publication Date
- 2026-05-29
AI Technical Summary
In existing technologies, autonomous vehicles cannot effectively avoid collisions when they deviate from the planned path or when the chassis response fails, thus affecting driving safety.
The system acquires obstacle information through sensors, calculates the vehicle's pose after a preset time interval, and determines whether a collision will occur based on the obstacle information, then performs collision avoidance measures, including speed control and emergency braking.
This improves the collision avoidance capabilities of autonomous vehicles in different situations, ensuring driving safety.
Smart Images
Figure CN116572988B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of autonomous driving technology, and in particular to a method, apparatus, electronic device, and computer-readable storage medium for collision avoidance of autonomous vehicles. Background Technology
[0002] When an autonomous vehicle is operating within its designed operating range, its safety is ensured by the autonomous driving system. This ensures safety not only when the autonomous driving system is functioning normally, but also when the system malfunctions or malfunctions. A crucial aspect of this safety protection is obstacle avoidance.
[0003] Therefore, how to handle collision avoidance for vehicles under different circumstances is a technical problem that urgently needs to be solved in this field. Summary of the Invention
[0004] This application provides a method for collision avoidance in an autonomous vehicle, the method comprising:
[0005] Obstacle information around the vehicle is obtained through sensors, wherein the obstacle information includes the pose of the obstacle in the vehicle coordinate system;
[0006] The vehicle's position is calculated after a preset time interval based on the vehicle's driving information, and the vehicle will collide with the obstacle based on the obstacle information. The driving information includes one or a combination of the vehicle's preset planned path, the control command sequence for controlling the vehicle's driving, the vehicle chassis's steering and speed, the real-time speed of the vehicle's rear axle center, the tangential direction and the distance moved along the tangential direction, the vehicle's lateral movement rate and the lateral displacement distance.
[0007] In response to a collision, collision information is output, which includes the distance from the vehicle to the collision location and the vehicle's pose at the time of the collision.
[0008] Collision avoidance processing is performed based on the collision information, wherein the collision avoidance processing includes one or a combination of speed control, maintaining direction emergency braking, and controlling direction emergency braking.
[0009] Optionally, the obstacle information includes the time when the obstacle information is acquired, and the acquisition of obstacle information around the vehicle via the sensor includes:
[0010] Obtain information about obstacles around the vehicle using sensors;
[0011] Calculate the time difference between the current time and the time when the obstacle information was acquired, calculate the pose change of the vehicle within the time difference, and update the obstacle information based on the pose change.
[0012] Optionally, the sensor may include one or a combination of lidar, camera, and ultrasound.
[0013] Optionally, the method further includes:
[0014] In abnormal conditions, the presence of obstacles and the distance from the obstacles to the vehicle are determined based on obstacle information obtained from the sensors.
[0015] Optionally, the collision avoidance process further includes:
[0016] Perform collision avoidance maneuvers and verify the results of the collision avoidance maneuvers;
[0017] In response to the vehicle's speed change being less than a first threshold after a collision avoidance maneuver, emergency braking is initiated.
[0018] This application provides a collision avoidance device for autonomous vehicles, characterized in that the device comprises:
[0019] The sensor module is used to acquire obstacle information around the vehicle through sensors, wherein the obstacle information includes the pose of the obstacle in the vehicle coordinate system;
[0020] The collision calculation module is used to calculate the vehicle's pose after a preset time interval based on the vehicle's driving information, and to determine whether the vehicle will collide with the obstacle based on the obstacle information. The driving information includes one or a combination of the vehicle's preset planned path, the control command sequence for controlling the vehicle's driving, the vehicle chassis's steering and speed, the real-time speed of the vehicle's rear axle center, the tangential direction and the distance moved along the tangential direction, the vehicle's lateral movement rate and the lateral displacement distance.
[0021] The collision output module outputs collision information in response to a collision, including the distance from the vehicle to the collision location and the vehicle's pose at the time of the collision.
[0022] The collision avoidance module performs collision avoidance processing based on the collision information, wherein the collision avoidance processing includes one or a combination of speed control, maintaining direction emergency braking, and controlling direction emergency braking.
[0023] Optionally, the obstacle information includes the time when the obstacle information is acquired, and the acquisition of obstacle information around the vehicle via the sensor includes:
[0024] Obtain information about obstacles around the vehicle using sensors;
[0025] Calculate the time difference between the current time and the time when the obstacle information was acquired, calculate the pose change of the vehicle within the time difference, and update the obstacle information based on the pose change.
[0026] Optionally, the sensor may include one or a combination of lidar, camera, and ultrasound.
[0027] Optionally, the method further includes:
[0028] In abnormal conditions, the presence of obstacles and the distance from the obstacles to the vehicle are determined based on obstacle information obtained from the sensors.
[0029] Optionally, the collision avoidance process further includes:
[0030] Perform collision avoidance maneuvers and verify the results of the collision avoidance maneuvers;
[0031] In response to the vehicle's speed change being less than a first threshold after a collision avoidance maneuver, emergency braking is initiated.
[0032] This application also provides an electronic device, including:
[0033] processor;
[0034] Memory used to store processor-executable instructions;
[0035] The processor implements the steps of the above method by running the executable instructions.
[0036] This application also provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.
[0037] Through the above embodiments, the vehicle's pose after a preset time interval can be calculated in various ways, and collision information, which determines whether the vehicle will collide with the obstacle, can be calculated based on the pose and obstacle information. Collision avoidance processing can then be performed based on this collision information to ensure the safety of vehicle operation. Attached Figure Description
[0038] Figure 1 This is a flowchart illustrating an exemplary embodiment of a method for collision avoidance in an autonomous vehicle;
[0039] Figure 2 This is an exemplary embodiment illustrating a vehicle collision that is about to occur.
[0040] Figure 3 This is a schematic diagram illustrating a vehicle undergoing lateral drift, as shown in an exemplary embodiment.
[0041] Figure 4 This is a block diagram illustrating an autonomous vehicle collision avoidance device, as shown in an exemplary embodiment.
[0042] Figure 5This is an exemplary embodiment illustrating the hardware structure of an electronic device housing a collision avoidance device for an autonomous vehicle. Detailed Implementation
[0043] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.
[0044] It should be noted that the steps of the corresponding methods are not necessarily performed in the order shown and described in this specification in other embodiments. In some other embodiments, the methods may include more or fewer steps than described in this specification. Furthermore, a single step described in this specification may be broken down into multiple steps in other embodiments; and multiple steps described in this specification may be combined into a single step in other embodiments.
[0045] To enable those skilled in the art to better understand the technical solutions in the embodiments of this specification, the relevant technologies of autonomous driving involved in the embodiments of this specification will be briefly described below.
[0046] Pose: Describes the position and orientation of an object (such as a coordinate) in a specified coordinate system. Pose is commonly used to describe the position and orientation of an object in a spatial coordinate system.
[0047] Braking by Wire: Braking by Wire systems are also known as electronic control braking systems, which are divided into mechanical braking by Wire systems and hydraulic braking by Wire systems.
[0048] Point cloud data: Laser pulses emitted by a lidar are reflected from the ground or object surface, forming multiple echoes that return to the lidar sensor. The processed reflection data is called point cloud data.
[0049] Path planning: The vehicle's driving trajectory is planned based on information such as the surrounding environment and location of the vehicle collected by various sensors, as well as the current vehicle status.
[0050] Application Scenarios Overview
[0051] When autonomous vehicles operate within their designed operating range, their safety is ensured by the autonomous driving system. This ensures safety not only during normal operation but also in the event of system malfunctions or anomalies. A crucial aspect of this safety protection is obstacle avoidance. For autonomous, driverless container transport vehicles, ensuring safe and efficient operation without a driver requires collision avoidance capabilities in various situations. Driverless container transport vehicles include unmanned trucks and intelligent mobile flatbed trucks.
[0052] In existing technologies, only sensors are used to acquire obstacle information and perform collision avoidance. This approach can lead to the vehicle deviating from the planned path or the vehicle chassis failing to respond, thus affecting the collision avoidance results and the driving safety of the autonomous vehicle.
[0053] Inventive concept
[0054] In view of this, this specification aims to propose a technical solution that calculates the vehicle's pose after a preset time interval through multiple methods, calculates collision information based on the pose and obstacle information to determine whether a collision will occur between the vehicle and the obstacle, and performs collision avoidance processing based on the collision information, thereby ensuring the safety of vehicle operation.
[0055] The core concept of this instruction manual is:
[0056] To address the potential motion of autonomous vehicles during operation, multiple methods are employed to determine whether a collision will occur between the vehicle and obstacles, and collision avoidance measures are implemented based on collision information to ensure vehicle safety.
[0057] The present application will now be described through specific embodiments and in conjunction with specific application scenarios.
[0058] Please see Figure 1 , Figure 1 This is a flowchart illustrating an exemplary embodiment of a collision avoidance method for an autonomous vehicle, wherein the method performs the following steps:
[0059] Step 102: Obtain obstacle information around the vehicle through the sensor, wherein the obstacle information includes the pose of the obstacle in the vehicle coordinate system.
[0060] Step 104: Calculate the vehicle's pose after a preset time interval based on the vehicle's driving information, and determine whether the vehicle will collide with the obstacle based on the obstacle information. The driving information includes one or a combination of the vehicle's preset planned path, the control command sequence for controlling the vehicle's driving, the vehicle chassis's steering and speed, the real-time speed of the vehicle's rear axle center, the tangential direction and the distance moved along the tangential direction, the vehicle's lateral movement rate and the lateral displacement distance.
[0061] Step 106: In response to the occurrence of a collision, output collision information, which includes the distance of the vehicle from the collision location and the vehicle's pose at the time of the collision.
[0062] Step 108: Perform collision avoidance processing based on the collision information, wherein the collision avoidance processing includes one or a combination of speed control, maintaining direction emergency braking, and controlling direction emergency braking.
[0063] In the solution proposed in this specification, obstacle information around the vehicle can be acquired through a sensor, wherein the obstacle information includes the pose of the obstacle in the vehicle coordinate system; the vehicle's pose after a preset time interval can be calculated based on the vehicle's driving information, and it can be determined whether the vehicle will collide with the obstacle based on the obstacle information, wherein the driving information includes one or a combination of the vehicle's preset planned path, the control command sequence for controlling the vehicle's driving, the steering and speed of the vehicle chassis, the real-time speed, tangential direction, and distance moved along the tangential direction of the vehicle's rear axle center, the vehicle's lateral movement rate, and the lateral displacement distance; in response to a collision, collision information can be output, wherein the collision information includes the distance of the vehicle to the collision location and the pose at the time of the collision; collision avoidance processing can be performed based on the collision information, wherein the collision avoidance processing includes one or a combination of speed control, maintaining direction emergency braking, and controlling direction emergency braking.
[0064] In one embodiment shown, the time difference between the current time and the time when the obstacle information was acquired can be calculated, the pose change of the vehicle within the time difference can be calculated, and the obstacle information can be updated based on the pose change.
[0065] For example, obstacle information can be timestamped. Other processing modules in the autonomous driving system can perform pose transformation on the obstacle information based on the difference between the reception time and the perception time, as well as the pose changes during this period, to ensure the accuracy of the obstacle information's position in the vehicle coordinate system. The specific pose transformation method can be as follows: vehicle wheelbase is L; vehicle speed at time t2 is v, steering wheel angle is δ; time change from time t1 to time t2 is Δt = t2 - t1; vehicle position movement is Δs = vΔt, angle change is Δθ = Δs tanδ / L; vehicle turning radius is R = L / tanδ; the coordinates of any point in the obstacle information at time t1 are (x, y); the collision prediction function receives the obstacle information at time t2; the more precise position of the obstacle at time t2 (x, y)... ′ y ′ Calculated using the following formula:
[0066] x ′ = (xR)cosΔθ - ysinΔθ + R
[0067] y ′ = (xR)sinΔθ + ycosΔθ
[0068] In one embodiment shown, the sensor may include one or a combination of lidar, camera, and ultrasound.
[0069] The sensing sensors include LiDAR (Light Detection and Ranging), Camera, and Ultrasonic sensors. The LiDAR sensing range covers a 360° area around the vehicle without blind spots close to it; the Camera sensing range also covers a 360° area around the vehicle without blind spots close to it; the Ultrasonic sensors are located at the lower front of the vehicle, primarily covering an area of approximately 2 meters in front. The computing platform can include two main computing units and one safety processing unit. One main computing unit handles visual perception; the other handles LiDAR perception; and the safety processing unit handles ultrasonic perception and anomaly handling.
[0070] In one embodiment shown, under abnormal conditions, the presence of an obstacle and the distance of the obstacle to the vehicle are determined based on obstacle information obtained from sensors.
[0071] For example, when sensors that require algorithmic processing encounter abnormalities or malfunctions, ultrasonic sensors can directly output the sensing results for obstacle avoidance. Ultrasonic waves can directly output whether there are obstacles within the sensing range and their distance.
[0072] In one embodiment shown, a collision avoidance process can be performed, and the result of the collision avoidance process can be verified; in response to the vehicle changing speed less than a first threshold after the collision avoidance process is performed, emergency braking can be initiated.
[0073] For example, the vehicle's real-time deceleration can be calculated. If the vehicle's deceleration is less than a first threshold, emergency braking can be initiated. The emergency braking method can be to disconnect the vehicle's air pump and stop the wheels by locking them.
[0074] In one embodiment shown, it can be determined whether a collision will occur based on the planned path in the vehicle coordinate system and the vehicle pose after a preset time interval.
[0075] like Figure 2 As shown, Figure 2 This is a schematic diagram of an impending vehicle collision. For example, it can first determine whether the vehicle's current position is on the planned path. If so, it can then determine whether a collision will occur based on the planned path in the vehicle coordinate system and the vehicle's pose after a preset time interval. The vehicle's pose after moving 0.5m along the path can be calculated, and it can be determined whether this pose collides with obstacles detected by the LiDAR and camera. Afterward, the distance from the current vehicle to the collision point and the vehicle's pose at the moment of collision can be output.
[0076] In one embodiment shown, it can be determined whether a collision will occur based on a sequence of control commands for controlling vehicle movement and the vehicle's pose after a preset time interval.
[0077] For example, the vehicle's pose can be calculated 0.025 seconds after the next control command, and it can be determined whether the pose collides with obstacles detected by the lidar and camera. Then, the distance from the current vehicle to the collision point and the pose at the time of the collision can be output.
[0078] When the vehicle's current position is not on the planned path, the autonomous driving control system will correct the deviation between the vehicle and the planned path. The vehicle will not drive according to the planned path. The response of the vehicle chassis is malfunctioning or inaccurate. The chassis does not execute the expected control commands, and the vehicle will not drive according to the planned path.
[0079] To address the aforementioned issues, in one embodiment shown, it is possible to determine whether a collision will occur based on the vehicle chassis's steering and speed, as well as the vehicle's position after a preset time interval.
[0080] In one embodiment shown, it can be determined whether a collision will occur based on the real-time speed of the vehicle's rear axle center, the tangential direction and the distance moved along the tangential direction, and the vehicle's pose after a preset time interval.
[0081] In one embodiment shown, it can be determined whether a collision will occur based on the vehicle's lateral movement rate and lateral displacement distance, as well as the vehicle's pose after a preset time interval.
[0082] like Figure 3 As shown, Figure 3 This is a schematic diagram of a vehicle undergoing lateral deviation. As shown in the figure, from time t1 to time t2, due to the lateral deviation, the distance between the vehicle and the obstacles gradually decreases. For example, it can be determined whether the vehicle is currently traveling straight. If so, the distance between the vehicle and the obstacles sensed by the LiDAR and cameras on the left and right sides can be calculated. The minimum distance between the vehicle and all obstacles is taken. If this minimum distance is less than a preset distance threshold, meaning the vehicle is too close to the obstacle, the distance from the vehicle to the collision point and the vehicle's pose at the time of the collision can be output. Furthermore, if this minimum distance is less than the preset distance threshold, the deviation rate can be calculated based on the minimum distance one second ago and the current minimum distance. If this deviation rate is greater than a preset rate threshold, the distance from the vehicle to the collision point and the vehicle's pose at the time of the collision can be output.
[0083] Please see Figure 4 , Figure 4 This is an exemplary embodiment illustrating a collision avoidance device for an autonomous vehicle, characterized in that the device comprises:
[0084] The sensor module 410 is used to acquire obstacle information around the vehicle through the sensor, wherein the obstacle information includes the pose of the obstacle in the vehicle coordinate system.
[0085] The collision calculation module 420 is used to calculate the vehicle's pose after a preset time interval based on the vehicle's driving information, and to determine whether the vehicle will collide with the obstacle based on the obstacle information. The driving information includes one or a combination of the vehicle's preset planned path, the control command sequence for controlling the vehicle's driving, the vehicle chassis's steering and speed, the real-time speed of the vehicle's rear axle center, the tangential direction and the distance moved along the tangential direction, the vehicle's lateral movement rate and the lateral displacement distance.
[0086] The collision output module 430 outputs collision information in response to a collision, the collision information including the distance from the vehicle to the collision location and the vehicle's pose at the time of the collision.
[0087] The collision avoidance module 440 performs collision avoidance processing based on the collision information, wherein the collision avoidance processing includes one or a combination of speed control, maintaining direction emergency braking, and controlling direction emergency braking.
[0088] Optionally, the obstacle information includes the time when the obstacle information is acquired, and the acquisition of obstacle information around the vehicle via the sensor includes:
[0089] Obtain information about obstacles around the vehicle using sensors;
[0090] Calculate the time difference between the current time and the time when the obstacle information was acquired, calculate the pose change of the vehicle within the time difference, and update the obstacle information based on the pose change.
[0091] Optionally, the sensor may include one or a combination of lidar, camera, and ultrasound.
[0092] Optionally, the method further includes:
[0093] In abnormal conditions, the presence of obstacles and the distance from the obstacles to the vehicle are determined based on obstacle information obtained from the sensors.
[0094] Optionally, the collision avoidance process further includes:
[0095] Perform collision avoidance maneuvers and verify the results of the collision avoidance maneuvers;
[0096] In response to the vehicle's speed change being less than a first threshold after a collision avoidance maneuver, emergency braking is initiated.
[0097] This manual can calculate the vehicle's pose after a preset time interval using various methods, and calculate collision information based on the pose and obstacle information to determine whether a collision will occur between the vehicle and the obstacle. Collision avoidance processing is then performed using this collision information to ensure the safety of vehicle operation.
[0098] Please see Figure 5 , Figure 5 This is an exemplary embodiment illustrating the hardware structure of an electronic device housing a collision avoidance mechanism for an autonomous vehicle. At the hardware level, the device includes a processor 502, an internal bus 504, a network interface 506, memory 508, and non-volatile memory 510, and may also include other hardware required for various operations. One or more embodiments of this specification can be implemented in software, for example, the processor 502 reads the corresponding computer program from the non-volatile memory 510 into memory 408 and then runs it. Of course, besides software implementation, one or more embodiments of this specification do not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution entity of the following processing flow is not limited to individual logic units, but can also be hardware or logic devices.
[0099] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of the solution in this specification according to actual needs. Those skilled in the art can understand and implement this without creative effort.
[0100] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer, which can take the form of a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email sending and receiving device, game console, tablet computer, wearable device, or any combination of these devices.
[0101] In a typical configuration, a computer includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory. Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0102] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0103] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0104] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.
[0105] The terminology used in one or more embodiments of this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of one or more embodiments of this specification. The singular forms “a,” “described,” and “the” as used in one or more embodiments of this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more associated listed items.
[0106] It should be understood that although the terms first, second, third, etc., may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first information may also be referred to as second information without departing from the scope of one or more embodiments of this specification, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "in response to a determination," or "when," or "in the event of a determination."
[0107] The above description is merely a preferred embodiment of one or more embodiments of this specification and is not intended to limit the scope of one or more embodiments of this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of one or more embodiments of this specification should be included within the protection scope of one or more embodiments of this specification.
Claims
1. A method for collision avoidance in an autonomous vehicle, characterized in that, The method includes: Obstacle information around the vehicle is obtained through sensors, wherein the obstacle information includes the pose of the obstacle in the vehicle coordinate system; The vehicle's position is calculated after a preset time interval based on the vehicle's driving information, and the vehicle will collide with the obstacle based on the obstacle information. The driving information includes one or a combination of the vehicle's preset planned path, the control command sequence for controlling the vehicle's driving, the vehicle chassis's steering and speed, the real-time speed of the vehicle's rear axle center, the tangential direction and the distance moved along the tangential direction, the vehicle's lateral movement rate and the lateral displacement distance. In response to a collision, collision information is output, which includes the distance from the vehicle to the collision location and the vehicle's pose at the time of the collision. Based on the collision information, a collision avoidance process is performed, wherein the collision avoidance process includes one or a combination of speed control, maintaining direction emergency braking, and controlling direction emergency braking. The specific method of pose transformation is as follows: the vehicle wheelbase is L; the vehicle speed at time t2 is v, and the steering wheel angle is δ; the time change from time t1 to time t2 is Δt = t2 - t1; the vehicle position movement is Δs = vΔt, and the angle change is Δθ = Δs tanδ / L; the vehicle turning radius is R = L / tanδ; the coordinates of any point in the obstacle information at time t1 are (x, y); the collision prediction function receives the obstacle information at time t2; the more precise position of the obstacle at time t2 (x, y)... ′ y ′ Calculated using the following formula: x ′ =(x-R)cosΔθ-ysinΔθ+R; y ′ =(xR)sinΔθ+ycosΔθ.
2. The method according to claim 1, characterized in that, The obstacle information includes the time when the obstacle information was acquired, and the acquisition of obstacle information around the vehicle through the sensor includes: Obtain information about obstacles around the vehicle using sensors; Calculate the time difference between the current time and the time when the obstacle information was acquired, calculate the pose change of the vehicle within the time difference, and update the obstacle information based on the pose change.
3. The method according to claim 1, characterized in that, The sensor includes one or a combination of lidar, camera, and ultrasound.
4. The method according to claim 1, characterized in that, The method further includes: In abnormal conditions, the presence of obstacles and the distance from the obstacles to the vehicle are determined based on obstacle information obtained from the sensors.
5. The method according to claim 1, characterized in that, The collision avoidance process also includes: Perform collision avoidance maneuvers and verify the results of the collision avoidance maneuvers; In response to the vehicle's speed change being less than a first threshold after a collision avoidance maneuver, emergency braking is initiated.
6. A collision avoidance device for an autonomous vehicle, characterized in that, The device includes: The sensor module is used to acquire obstacle information around the vehicle through sensors, wherein the obstacle information includes the pose of the obstacle in the vehicle coordinate system; The collision calculation module is used to calculate the vehicle's pose after a preset time interval based on the vehicle's driving information, and to determine whether the vehicle will collide with the obstacle based on the obstacle information. The driving information includes one or a combination of the vehicle's preset planned path, the control command sequence for controlling the vehicle's driving, the vehicle chassis's steering and speed, the real-time speed of the vehicle's rear axle center, the tangential direction and the distance moved along the tangential direction, the vehicle's lateral movement rate and the lateral displacement distance. The collision output module outputs collision information in response to a collision, including the distance from the vehicle to the collision location and the vehicle's pose at the time of the collision. The collision avoidance module performs collision avoidance processing based on the collision information, wherein the collision avoidance processing includes one or a combination of speed control, maintaining direction emergency braking, and controlling direction emergency braking; The specific method of pose transformation is as follows: the vehicle wheelbase is L; the vehicle speed at time t2 is v, and the steering wheel angle is δ; the time change from time t1 to time t2 is Δt = t2 - t1; the vehicle position movement is Δs = vΔt, and the angle change is Δθ = Δs tanδ / L; the vehicle turning radius is R = L / tanδ; the coordinates of any point in the obstacle information at time t1 are (xy), and the collision prediction function receives the obstacle information at time t2; the more precise position (x′y′) of the obstacle at time t2 is calculated by the following formula: x′=(xR)cosΔθ-ysinΔθ+R; y′=(xR)sinΔθ+ycosΔθ.
7. The apparatus according to claim 6, characterized in that, The obstacle information includes the time when the obstacle information was acquired, and the acquisition of obstacle information around the vehicle through the sensor includes: Obtain information about obstacles around the vehicle using sensors; Calculate the time difference between the current time and the time when the obstacle information was acquired, calculate the pose change of the vehicle within the time difference, and update the obstacle information based on the pose change.
8. The apparatus according to claim 6, characterized in that, The sensor includes one or a combination of lidar, camera, and ultrasound.
9. The apparatus according to claim 6, characterized in that, The device further includes: In abnormal conditions, the presence of obstacles and the distance from the obstacles to the vehicle are determined based on obstacle information obtained from the sensors.
10. The apparatus according to claim 6, characterized in that, The collision avoidance process also includes: Perform collision avoidance maneuvers and verify the results of the collision avoidance maneuvers; In response to the vehicle's speed change being less than a first threshold after a collision avoidance maneuver, emergency braking is initiated.
11. A computer-readable storage medium having stored thereon computer instructions that, when executed by a processor, implement the steps of the method as claimed in any one of claims 1-5.
12. An electronic device, comprising: processor; Memory used to store processor-executable instructions; The processor implements the steps of the method as described in any one of claims 1-5 by executing the executable instructions.