Anti-collision method and device for autonomous vehicle

Abstract

The application discloses a collision avoidance method and device for an automatic driving vehicle, wherein the method comprises the following steps: when the automatic driving vehicle travels based on a target trajectory, detecting whether a region satisfying a preset non-passable condition exists in a grid point passable area; when it is detected that the region exists, determining a local path in the target trajectory corresponding to the region, and calculating the nearest distance between the local path and the region, so as to match the best driving speed of the automatic driving vehicle, and controlling the automatic driving vehicle to travel at the best driving speed, wherein the target acceleration is calculated according to the grid point passable area, closed-loop control is performed according to the target acceleration and the actual vehicle speed of the automatic driving vehicle, the current acceleration of the automatic driving vehicle is obtained, and the automatic driving vehicle is decelerated or braked at the current acceleration. According to the application, when it is detected that the non-passable region exists, the automatic driving vehicle can be controlled to decelerate or brake according to the current acceleration of the vehicle, and the safety of vehicle driving is effectively improved.

Description

Collision avoidance methods and devices for autonomous vehicles Technical Field

[0001] This application relates to the field of intelligent driving technology for automobiles, and in particular to a collision avoidance method and device for autonomous vehicles. Background Technology

[0002] Valet parking technology, as a high-level autonomous driving system, is a key technology for the future development of intelligent vehicles. Because it can autonomously handle various working conditions encountered during the process of following a path in a garage, it has good prospects for engineering mass production and has become a research hotspot in the field of automotive intelligence, as well as a function that the market urgently needs.

[0003] In related technologies, the vehicle speed is constrained by the curvature of the current vehicle's driving trajectory. The curvature of the planned path is used to determine the current vehicle's cornering state, and it is determined whether there is a collision risk. The corresponding target speed is then output to ensure the driving safety of the current vehicle.

[0004] However, the relevant technologies rely solely on the curvature of the planned path to determine the vehicle's cornering status, resulting in a significant deviation between the actual driving path and the planned path. This increases the risk of collisions, reduces vehicle safety and reliability, and diminishes the user's driving experience, which urgently needs to be addressed. Summary of the Invention

[0005] This application is based on the inventor's understanding and insights into the following issues:

[0006] Intelligent vehicles equipped with valet parking functions use multiple sensors, including cameras, radar, and positioning systems, to perceive parking lot road conditions. After receiving information from these sensors, the planning and control system plans a route from the current location to a designated location or parking space and follows the path. This tests the real-time performance and accuracy of the perception system, as well as the smoothness and safety of the planning and control system in tracking the path and speed. Valet parking mainly addresses scenarios in underground parking lots, including normal lanes, narrow passages, right-angle turns, and various dynamic and stationary targets, ultimately driving to the target parking space or parking at the target location.

[0007] Because parking lots contain various moving and static objects with unpredictable movements, and include narrow bends, walls, and other difficult-to-detect boundaries, safe and stable driving during valet parking is crucial. Valet parking involves sending steering wheel angle control commands to guide the vehicle along a planned path. However, deviations between the actual vehicle's path and the planned path can cause delays in path following, especially during turns. This problem is more pronounced at higher speeds, greatly increasing the probability of collisions with walls or other vehicles within the parking space. Therefore, valet parking, particularly when navigating curves, requires receiving information about static obstacles such as walls and pillars from sensors, combining this information with the driving path information to assess collision risks, and outputting a target speed based on the lateral and longitudinal distances between the vehicle and these static obstacles.

[0008] Currently, valet parking technology mainly uses the curvature of the driving trajectory to constrain the vehicle speed when cornering, relying solely on the curvature of the planned path to determine the vehicle's cornering status. In most cases, there is a significant error between the actual driving path and the planned path. If the driving path deviates significantly from the actual path, the constrained speed obtained from the path curvature may not meet the requirements for following the trajectory when cornering, and may even cause the actual driving path to intersect with the road boundary, which greatly increases the risk of collision.

[0009] This application provides a collision avoidance method and device for autonomous vehicles to solve the problem in related technologies that only use the curvature of the planned path to determine the vehicle's cornering state, resulting in a large deviation between the actual driving path and the planned path, increasing the risk of collision, reducing the safety and reliability of the vehicle, and reducing the user's driving experience.

[0010] The first aspect of this application provides a collision avoidance method for an autonomous vehicle, comprising the following steps: when the autonomous vehicle is traveling based on a target trajectory, detecting whether there is an area in the passable area of ​​the grid points that meets a preset impassable condition; when the area is detected, determining a local path in the target trajectory corresponding to the area, and calculating the shortest distance between the local path and the area; matching the optimal driving speed of the autonomous vehicle according to the shortest distance, and controlling the autonomous vehicle to travel according to the optimal driving speed, wherein a target acceleration is calculated based on the passable area of ​​the grid points, and closed-loop control is performed based on the target acceleration and the actual speed of the autonomous vehicle to obtain the current acceleration of the autonomous vehicle, and deceleration or braking is performed according to the current acceleration.

[0011] Based on the above technical means, the embodiments of this application can, when an impassable area is detected in the passable area of ​​the grid point, match the optimal driving speed of the autonomous vehicle according to the shortest distance between the local path and the impassable area, and obtain the current acceleration according to the target acceleration and the actual speed of the autonomous vehicle, and decelerate or brake according to the current acceleration, effectively improving the safety of vehicle driving and enhancing the user's driving experience.

[0012] Optionally, in one embodiment of this application, the step of matching the optimal driving speed of the autonomous vehicle according to the nearest distance, and controlling the autonomous vehicle to drive at the optimal driving speed, includes: detecting whether the nearest distance is less than a preset safe distance; when the nearest distance is detected to be less than the preset safe distance, determining whether there are any impassable points within the passable area within a preset distance in front of the vehicle and within a preset range on the left and right sides of the path; if there are no impassable points within the passable area of ​​a first distance within the preset range, then the optimal driving speed is a first target speed; if there are no impassable points within the passable area of ​​a second distance within the preset range, then the optimal driving speed is a second target speed, wherein the first distance is greater than the second distance, and the second target speed is less than the first target speed; if there are no impassable points within the passable area of ​​a third distance within the preset range, then the optimal driving speed is a third target speed, wherein the second distance is greater than the third distance, and the third target speed is less than the second target speed.

[0013] Based on the above technical means, the embodiments of this application can effectively improve the intelligence level of the vehicle and enhance the safety and reliability of the user's driving by determining that there are no passable points on the left and right sides of the local path within a certain passable area, and matching the target vehicle speed according to the nearest distance.

[0014] Optionally, in one embodiment of this application, determining whether there are impassable points within the passable area within a preset distance in front of the vehicle and within a preset range on the left and right sides of the path includes: obtaining the passability matrix of the area; and determining whether there are impassable points within the passable area based on the attribute information of the passability matrix.

[0015] Based on the above technical means, the embodiments of this application can determine whether a path point and its surrounding area are passable by using the attributes in the matrix, thereby effectively improving the intelligence of the vehicle and enhancing the user's driving experience.

[0016] Optionally, in one embodiment of this application, before detecting the existence of a region that meets the preset impassable conditions in the grid point passable area, the method further includes: using the rear axle center of the autonomous vehicle as the coordinate origin to establish a preset passable area in front of the vehicle, so as to detect the existence of the region that meets the preset impassable conditions based on the preset passable area in front of the vehicle.

[0017] Based on the above technical means, the embodiments of this application can establish a passable area in front of the vehicle, effectively improving the feasibility of collision avoidance for autonomous vehicles, enhancing vehicle driving safety, and meeting the driving needs of users.

[0018] A second aspect of this application provides a collision avoidance device for an autonomous vehicle, comprising: a detection module, configured to detect whether there is a region satisfying a preset impassable condition within the passable area of ​​a grid point when the autonomous vehicle is traveling based on a target trajectory; a calculation module, configured to determine a local path in the target trajectory corresponding to the region when the region is detected, and calculate the shortest distance between the local path and the region; and a control module, configured to match the optimal driving speed of the autonomous vehicle according to the shortest distance, and control the autonomous vehicle to travel according to the optimal driving speed, wherein a target acceleration is calculated based on the passable area of ​​the grid point, and closed-loop control is performed based on the target acceleration and the actual speed of the autonomous vehicle to obtain the current acceleration of the autonomous vehicle, and deceleration or braking is performed according to the current acceleration.

[0019] Optionally, in one embodiment of this application, the control module includes: a detection unit, configured to detect whether the nearest distance is less than a preset safe distance; a judgment unit, configured to, when the nearest distance is detected to be less than the preset safe distance, determine whether there are any impassable points within the passable area within a preset distance in front of the vehicle and within a preset range on the left and right sides of the path; a first processing unit, configured to, if there are no impassable points within the passable area of ​​a first distance within the preset range, then the optimal driving speed is a first target speed; a second processing unit, configured to, if there are no impassable points within the passable area of ​​a second distance within the preset range, then the optimal driving speed is a second target speed, wherein the first distance is greater than the second distance, and the second target speed is less than the first target speed; and a third processing unit, configured to, if there are no impassable points within the passable area of ​​a third distance within the preset range, then the optimal driving speed is a third target speed, wherein the second distance is greater than the third distance, and the third target speed is less than the second target speed.

[0020] Optionally, in one embodiment of this application, the determining unit is further configured to obtain the access matrix of the area and determine whether there are impassable points in the passable area based on the attribute information of the access matrix.

[0021] Optionally, in one embodiment of this application, the apparatus of this application embodiment further includes: an establishment module, used to establish a preset passable area in front of the vehicle by taking the rear axle center of the autonomous vehicle as the coordinate origin before detecting the existence of an area that meets the preset impassable conditions in the passable area of ​​the grid points, so as to detect the existence of an area that meets the preset impassable conditions based on the preset passable area in front of the vehicle.

[0022] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the collision avoidance method for an autonomous vehicle as described in the above embodiments.

[0023] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described collision avoidance method for an autonomous vehicle.

[0024] The beneficial effects of this application are:

[0025] (1) The embodiments of this application can establish a passable area in front of the vehicle, which effectively improves the feasibility of collision avoidance for autonomous vehicles, improves the safety of vehicle driving, and meets the driving needs of users.

[0026] (2) The embodiments of this application can determine whether there are passable points on the left and right sides of the local path within a certain passable area, and match the target vehicle speed according to the nearest distance when there are no passable points, which effectively improves the intelligence level of the vehicle and enhances the safety and reliability of the user's driving.

[0027] (3) In this embodiment of the application, when an impassable area is detected in the passable area of ​​the grid point, the optimal driving speed of the autonomous vehicle is matched according to the shortest distance between the local path and the impassable area, and the current acceleration is obtained according to the target acceleration and the actual speed of the autonomous vehicle. The vehicle is decelerated or braked according to the current acceleration, which effectively improves the safety of vehicle driving and enhances the user's driving experience.

[0028] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0029] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0030] Figure 1 is a flowchart of a collision avoidance method for an autonomous vehicle according to an embodiment of this application;

[0031] Figure 2 is a schematic diagram of a grid area according to a specific embodiment of this application;

[0032] Figure 3 is a schematic diagram of the structure of the collision avoidance device for an autonomous vehicle according to an embodiment of this application;

[0033] Figure 4 is a structural schematic diagram of a vehicle provided according to an embodiment of this application.

[0034] Among them, 10-collision avoidance device for autonomous vehicles; 100-detection module, 200-computing module and 300-control module; 401-memory, 402-processor and 403-communication interface. Detailed Implementation

[0035] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0036] The following description, with reference to the accompanying drawings, illustrates a collision avoidance method and apparatus for an autonomous vehicle according to embodiments of this application. Addressing the problem mentioned in the background section that the related technologies rely solely on the curvature of the planned path to determine the vehicle's cornering state, leading to a significant deviation between the actual driving path and the planned path, increasing the risk of collisions, reducing vehicle safety and reliability, and diminishing the user's driving experience, this application provides a collision avoidance method for an autonomous vehicle. In this method, when the autonomous vehicle is traveling based on a target trajectory and detects an area that meets the impassable conditions, a local path within the target trajectory corresponding to the area is determined. The shortest distance between the local path and the area is calculated, and the optimal driving speed of the autonomous vehicle is matched. The target acceleration is calculated based on the passable area of ​​the grid points to obtain the current acceleration. Deceleration or braking is then performed according to the current acceleration, effectively improving vehicle driving safety and enhancing the user's driving experience. This solves the problem in the related technologies where relying solely on the curvature of the planned path to determine the vehicle's cornering state results in a significant deviation between the actual driving path and the planned path, increasing the risk of collisions, reducing vehicle safety and reliability, and diminishing the user's driving experience.

[0037] Specifically, Figure 1 is a flowchart illustrating a collision avoidance method for an autonomous vehicle provided in an embodiment of this application.

[0038] As shown in Figure 1, the collision avoidance method for this autonomous vehicle includes the following steps:

[0039] In step S101, when the autonomous vehicle is driving based on the target trajectory, it is detected whether there is an area in the grid point passable area that meets the preset impassable conditions.

[0040] It is understood that, in the embodiments of this application, when an autonomous vehicle is driving based on a target trajectory, for example, when the autonomous vehicle is driving in valet parking mode according to the local path information and road boundary information in the following steps output by trajectory planning, it can detect whether there are areas in the grid point passable area that meet the conditions for impassability, thereby effectively improving the feasibility of collision avoidance of the autonomous vehicle and improving the intelligence level of the vehicle.

[0041] It should be noted that, for ease of description, the following steps will be described in detail using the example of an autonomous vehicle following a path in valet parking mode in the embodiments of this application.

[0042] In step S102, when an impassable area is detected, a local path in the target trajectory corresponding to the impassable area is determined, and the shortest distance between the local path and the area is calculated.

[0043] It is understood that, when an impassable area is detected, the embodiments of this application can determine a local path in the target trajectory corresponding to the impassable area and calculate the shortest distance between the local path and the impassable area. The optimal driving speed of the autonomous vehicle can be matched according to the shortest distance in the following steps, thereby effectively improving vehicle safety and enhancing the level of vehicle automation.

[0044] In step S103, the optimal driving speed of the autonomous vehicle is matched based on the nearest distance, and the autonomous vehicle is controlled to drive at the optimal driving speed. Specifically, the target acceleration is calculated based on the passable area of ​​the grid points, and closed-loop control is performed based on the target acceleration and the actual speed of the autonomous vehicle to obtain the current acceleration of the autonomous vehicle, so as to decelerate or brake according to the current acceleration.

[0045] It can be understood that the embodiments of the present application can match the optimal driving speed of the autonomous vehicle according to the shortest distance in the following steps, so that the vehicle travels at a safe and comfortable speed, calculate the target acceleration according to the passable area of the grid points, and perform closed-loop control according to the target acceleration, the actual vehicle speed of the autonomous vehicle, and obtain the current acceleration of the autonomous vehicle. Deceleration or braking to stop can be performed according to the current acceleration, thereby ensuring the safety of vehicle driving.

[0046] Among them, in an embodiment of the present application, matching the optimal driving speed of the autonomous vehicle according to the shortest distance to control the autonomous vehicle to travel at the optimal driving speed includes: detecting whether the shortest distance is less than a preset safety distance; when it is detected that the shortest distance is less than the preset safety distance, determining whether there are impassable points in the passable area within a preset distance in front of the vehicle and within a preset range on both the left and right sides of the path; if there are no impassable points in the passable area at the first distance within the preset range, the optimal driving speed is the first target vehicle speed; if there are no impassable points in the passable area at the second distance within the preset range, the optimal driving speed is the second target vehicle speed, where the first distance is greater than the second distance, and the second target vehicle speed is less than the first target vehicle speed; if there are no impassable points in the passable area at the third distance within the preset range, the optimal driving speed is the third target vehicle speed, where the second distance is greater than the third distance, and the third target vehicle speed is less than the second target vehicle speed.

[0047] For example, in the embodiments of the present application, the grid point passable area GridMatrixForLonCtl of the current vehicle, the path point row index PathIndex, the planned output grid point passable area target vehicle speed GridTarSpdFinal, and the impassable area target distance GridDisToStop:

[0048] When there are impassable points in the passable area within the safety distance in front of the vehicle (i.e., taking the path point length as PathIndex_Cons) and within 50 cm on both the left and right sides of the path (i.e., within two columns on both sides of the path), the target vehicle speed GridTarSpd1 is output.

[0049] When there are impassable points in the passable area within the safety distance in front of the vehicle (i.e., taking the path point length as PathIndex_Cons) and within 25 cm on both the left and right sides of the path (i.e., within one column on both sides of the path), the target vehicle speed GridTarSpd2 is output, and GridTarSpd2 < GridTarSpd1 < GridTarSpdMax, where GridTarSpdMax is referenced from the upper limit of the cruise target vehicle speed and is not specifically limited here.

[0050] If there is an impassable point on the path within the safe distance ahead of the vehicle (i.e., the path length is PathIndex_Cons), then the output will be: target speed 0, target distance:

[0051] GridDisToStop=j*0.3-VehLength,

[0052] Where j is the coordinate of the impassable point on the path, and VehLength is the distance from the rear axle to the front of the vehicle.

[0053] In summary, the embodiments of this application can effectively improve the automation level of vehicles, enhance vehicle safety and reliability, and meet the user's driving experience.

[0054] In one embodiment of this application, determining whether there are impassable points within the passable area within a preset distance in front of the vehicle and within a preset range on the left and right sides of the path includes: obtaining the passability matrix of the area; and determining whether there are impassable points within the passable area based on the attribute information of the passability matrix.

[0055] In actual implementation, this application embodiment can obtain the passage matrix of the impassable area, determine whether there are impassable points in the passable area based on the attribute information of the passage matrix, and output the corresponding driving speed. The passability of the path point and the surrounding area is determined by the attributes in the GridMatrixForLonCtl matrix, thereby effectively improving the intelligence of the vehicle and enhancing the user's driving experience.

[0056] Optionally, in one embodiment of this application, before detecting that there is a region in the grid point passable area that meets the preset impassable conditions, the method further includes: using the rear axle center of the autonomous vehicle as the coordinate origin to establish a preset passable area in front of the vehicle, so as to detect the existence of a region that meets the preset impassable conditions based on the preset passable area in front of the vehicle.

[0057] For example, as shown in Figure 2, this embodiment of the application can establish a passable area in front of the vehicle with the center of the rear axle of the autonomous vehicle as the origin of the coordinate system. There are 30 points in the horizontal direction with a horizontal point spacing of 25cm, and 60 points in the vertical direction with a vertical point spacing of 30cm. The numbering order is 1-30 from left to right and 1-60 from back to front. Each point is assigned a passable attribute, with passable being 1 and inpassable being 0. By default, all points are passable, that is, the passable attribute of all grid points is 1 by default.

[0058] Next, in this embodiment, the static obstacle FreeSpace point of the sensing input can be received. If the static obstacle FreeSpace point exists in the passable area, by comparing the coordinates of the FreeSpace point with the positional relationship of the points in the passable area, the passability attribute of the corresponding point in the passable area is set to 0, indicating that the location of the corresponding point in the passable area is not passable. In this way, during the vehicle's driving process, the passability of the FreeSpace point output at each moment is judged in the passable area point matrix and assigned a value to obtain GridMatrixForLongCtl containing the passability attributes of each grid area, thereby ensuring the comfort and safety of the vehicle driving.

[0059] In some embodiments, the present application embodiments can also calculate the target acceleration of the grid point in the passable area based on the vehicle speed signal, the function activation signal FunctionMode, the target distance in the passable area, and the target speed in the passable area, so as to improve the driving safety of the vehicle.

[0060] For example, when the function activation signal FunctionMode=1, i.e., in valet parking tracking mode, the target acceleration is calculated based on the passable area of ​​the grid points; otherwise, a default value is output. The target speed difference within the passable area is:

[0061] VerrorGridDec=(Vt_GridDec_kph-Vh_kph) / 3.6,

[0062] Specifically, when VerrorGridDec > 0, if VerrorGridDec > VerrorGrid_AccelThres, then At_GridDec = At_GridDecUpLmt; otherwise, At_GridDec = VerrorGridDec * VerrorGrid_AccelGain.

[0063] Where GridDecCalUpLmt is the upper limit of the target acceleration.

[0064] When VerrorGridDec <= 0, if the target distance of the passable area GridDisToStop <= 0, then At_GridDec = VerrorGridDec * VerrorGrid_DecGain, and the minimum value is At_GridDecLowLmt. If the target distance of the passable area GridDisToStop > 0, then At_GridDec = (Vt_GridDec) * VerrorGrid_DecGain. 2 -Vh_mps 2) / 2(GridDisToStop-GridDec SafeDis), and the upper limit of the target acceleration is calculated as GridDecCalUpLmt, where GridDecLowLmt is the lower limit of the target acceleration, GridDisToStop is the target distance in the passable area, and the lower limit is obtained by calibrating the target distance in the passable area GridDisToStop.

[0065] Therefore, after calculating the target acceleration, this embodiment of the application can receive the target acceleration through the longitudinal control function for closed-loop control, so as to realize the safe deceleration or braking of the vehicle through static obstacles in valet parking mode, thereby improving vehicle safety and enhancing the user's driving experience.

[0066] The collision avoidance method for autonomous vehicles proposed in this application can, when an autonomous vehicle is traveling based on a target trajectory and a region meeting the impassable conditions is detected, determine a local path in the target trajectory corresponding to the region, calculate the shortest distance between the local path and the region, match the optimal driving speed of the autonomous vehicle, and calculate the target acceleration based on the passable area of ​​the grid points to obtain the current acceleration. Then, deceleration or braking is performed according to the current acceleration, effectively improving vehicle driving safety and enhancing the user's driving experience. This solves the problem in related technologies where only the curvature of the planned path is used to determine the vehicle's cornering state, resulting in a large deviation between the actual driving path and the planned path, increasing the risk of collision, reducing vehicle safety and reliability, and lowering the user's driving experience.

[0067] Next, referring to the accompanying drawings, a collision avoidance device for an autonomous vehicle according to an embodiment of this application is described.

[0068] Figure 3 is a block diagram of the collision avoidance device for an autonomous vehicle according to an embodiment of this application.

[0069] As shown in Figure 3, the collision avoidance device 10 of the autonomous vehicle includes: a detection module 100, a calculation module 200, and a control module 300.

[0070] Specifically, the detection module 100 is used to detect whether there are areas in the grid point passable area that meet preset impassable conditions when the autonomous vehicle is driving based on the target trajectory.

[0071] The calculation module 200 is used to determine the local path in the target trajectory corresponding to the detected area and calculate the shortest distance between the local path and the area when the area is detected.

[0072] The control module 300 is used to match the optimal driving speed of the autonomous vehicle based on the nearest distance, so as to control the autonomous vehicle to drive at the optimal driving speed. Specifically, it calculates the target acceleration based on the passable area of ​​the grid points, and performs closed-loop control based on the target acceleration and the actual speed of the autonomous vehicle to obtain the current acceleration of the autonomous vehicle, so as to decelerate or brake according to the current acceleration.

[0073] Optionally, in one embodiment of this application, the control module 300 includes: a detection unit, a judgment unit, a first processing unit, a second processing unit, and a third processing unit.

[0074] The detection unit is used to detect whether the nearest distance is less than a preset safe distance.

[0075] The judgment unit is used to determine whether there are any impassable points in the passable area within the preset distance in front of the vehicle and within the preset range on the left and right sides of the path when the nearest distance is detected to be less than the preset safe distance.

[0076] The first processing unit is configured to determine the optimal driving speed as the first target speed if there are no impassable points within a passable area at a first distance within a preset range.

[0077] The second processing unit is configured to determine the optimal driving speed as the second target speed if there are no impassable points within the passable area at a second distance within a preset range, wherein the first distance is greater than the second distance and the second target speed is less than the first target speed.

[0078] The third processing unit is configured to determine the optimal driving speed as the third target speed if there are no impassable points within the passable area at a third distance within a preset range, wherein the second distance is greater than the third distance and the third target speed is less than the second target speed.

[0079] Optionally, in one embodiment of this application, the determining unit is further configured to obtain the access matrix of the area and determine whether there are impassable points in the passable area based on the attribute information of the access matrix.

[0080] Optionally, in one embodiment of this application, the apparatus 10 of this application embodiment further includes: an establishment module.

[0081] The module is used to establish a preset passable area in front of the vehicle by taking the rear axle center of the autonomous vehicle as the origin of the coordinate system before detecting areas that meet the preset impassable conditions in the passable area of ​​the grid points. This allows for the detection of areas that meet the preset impassable conditions based on the preset passable area in front of the vehicle.

[0082] It should be noted that the foregoing explanation of the collision avoidance method embodiment for autonomous vehicles also applies to the collision avoidance device for autonomous vehicles in this embodiment, and will not be repeated here.

[0083] The collision avoidance device for autonomous vehicles proposed in this application can, when an autonomous vehicle is traveling based on a target trajectory and a region meeting the impassable conditions is detected, determine a local path in the target trajectory corresponding to the region, calculate the shortest distance between the local path and the region, match the optimal driving speed of the autonomous vehicle, and calculate the target acceleration based on the passable area of ​​the grid points to obtain the current acceleration. Then, deceleration or braking is performed according to the current acceleration, effectively improving vehicle driving safety and enhancing the user's driving experience. This solves the problem in related technologies where only the curvature of the planned path is used to determine the vehicle's cornering state, resulting in a large deviation between the actual driving path and the planned path, increasing the risk of collision, reducing vehicle safety and reliability, and lowering the user's driving experience.

[0084] Figure 4 is a structural schematic diagram of a vehicle provided in an embodiment of this application. The vehicle may include:

[0085] The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0086] When the processor 402 executes the program, it implements the collision avoidance method for autonomous vehicles provided in the above embodiments.

[0087] Furthermore, the vehicle also includes:

[0088] Communication interface 403 is used for communication between memory 401 and processor 402.

[0089] The memory 401 is used to store computer programs that can run on the processor 402.

[0090] The memory 401 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0091] If the memory 401, processor 402, and communication interface 403 are implemented independently, they can be interconnected via a bus to communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, only one thick line is used in Figure 4, but this does not indicate that there is only one bus or one type of bus.

[0092] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0093] Processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0094] This embodiment also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described collision avoidance method for autonomous vehicles.

[0095] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0096] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0097] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0098] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0099] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0100] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0101] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0102] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A collision avoidance method for an autonomous vehicle, characterized in that, Includes the following steps: When an autonomous vehicle is driving based on a target trajectory, it is detected whether there are areas in the passable area of ​​the grid points that meet the preset impassable conditions. When the region is detected, a local path in the target trajectory corresponding to the region is determined, and the shortest distance between the local path and the region is calculated; and the optimal driving speed of the autonomous vehicle is matched according to the shortest distance, so as to control the autonomous vehicle to drive according to the optimal driving speed, wherein the target acceleration is calculated based on the passable area of ​​the grid points, and closed-loop control is performed based on the target acceleration and the actual speed of the autonomous vehicle to obtain the current acceleration of the autonomous vehicle, so as to decelerate or brake according to the current acceleration; wherein, the step of matching the optimal driving speed of the autonomous vehicle according to the shortest distance and controlling the autonomous vehicle to drive according to the optimal driving speed includes: detecting whether the shortest distance is less than a preset safety distance; When the nearest distance is detected to be less than the preset safe distance, it is determined whether there are any impassable points within the passable area within the preset distance in front of the vehicle and within the preset range on both sides of the path; if there are no impassable points within the passable area of ​​the first distance within the preset range, the optimal driving speed is the first target speed; if there are no impassable points within the passable area of ​​the second distance within the preset range, the optimal driving speed is the second target speed, wherein the first distance is greater than the second distance and the second target speed is less than the first target speed; if there are no impassable points within the passable area of ​​the third distance within the preset range, the optimal driving speed is the third target speed, wherein the second distance is greater than the third distance and the third target speed is less than the second target speed.

2. The method according to claim 1, characterized in that, The step of determining whether there are impassable points within the passable area within a preset distance in front of the vehicle and within a preset range on the left and right sides of the path includes: obtaining the passability matrix of the area; and determining whether there are impassable points within the passable area based on the attribute information of the passability matrix.

3. The method according to claim 1, characterized in that, Before detecting areas in the grid point passable area that meet preset impassable conditions, the method further includes: using the rear axle center of the autonomous vehicle as the coordinate origin to establish a preset passable area in front of the vehicle, so as to detect areas that meet preset impassable conditions based on the preset passable area in front of the vehicle.

4. A collision avoidance device for an autonomous vehicle, characterized in that, include: The detection module is used to detect whether there are areas in the passable area of ​​the grid points that meet the preset impassable conditions when the autonomous vehicle is driving based on the target trajectory. A calculation module is used to determine a local path in the target trajectory corresponding to the detected area, and calculate the shortest distance between the local path and the area when the area is detected; and a control module is used to match the optimal driving speed of the autonomous vehicle according to the shortest distance, so as to control the autonomous vehicle to drive according to the optimal driving speed, wherein a target acceleration is calculated based on the passable area of ​​the grid points, and closed-loop control is performed based on the target acceleration and the actual speed of the autonomous vehicle to obtain the current acceleration of the autonomous vehicle, so as to decelerate or brake according to the current acceleration; wherein, the step of matching the optimal driving speed of the autonomous vehicle according to the shortest distance to control the autonomous vehicle to drive according to the optimal driving speed includes: detecting whether the shortest distance is less than a predetermined value. A safe distance is set; when the nearest distance is detected to be less than the preset safe distance, it is determined whether there are any impassable points within the passable area within the preset distance in front of the vehicle and within the preset range on both sides of the path; if there are no impassable points within the passable area of ​​the first distance within the preset range, the optimal driving speed is the first target speed; if there are no impassable points within the passable area of ​​the second distance within the preset range, the optimal driving speed is the second target speed, wherein the first distance is greater than the second distance, and the second target speed is less than the first target speed; if there are no impassable points within the passable area of ​​the third distance within the preset range, the optimal driving speed is the third target speed, wherein the second distance is greater than the third distance, and the third target speed is less than the second target speed.

5. The apparatus according to claim 4, characterized in that, The control module is further used to obtain the access matrix of the area and determine whether there are impassable points in the passable area based on the attribute information of the access matrix.

6. The apparatus according to claim 4, characterized in that, It also includes: a module for establishing a preset passable area ahead of the vehicle, using the rear axle center of the autonomous vehicle as the coordinate origin before detecting an area that meets the preset impassable conditions in the passable area of ​​the grid points, so as to detect the area that meets the preset impassable conditions based on the preset passable area ahead of the vehicle.

7. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the collision avoidance method for an autonomous vehicle as described in any one of claims 1-3.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the collision avoidance method for an autonomous vehicle as described in any one of claims 1-3.

Images