Vehicle Obstacle Avoidance Method, Device, Computer Readable Storage Medium, and Vehicle

Abstract

The present disclosure relates to a vehicle obstacle avoidance method, apparatus, computer-readable storage medium, and vehicle. The method includes: when the vehicle is traveling on a pre-planned path and detects an obstacle, obtaining the attribute of the obstacle, determining a first coordinate of the position of the vehicle center after the vehicle completes obstacle avoidance based on the attribute of the obstacle and the vehicle parameter information of the vehicle, matching a target obstacle avoidance lane change width from a plurality of pre-stored obstacle avoidance lane change widths, each obstacle avoidance lane change width corresponding to a specified number of alternative routes, determining a target route from the alternative routes corresponding to the target obstacle avoidance lane change width, determining an actual obstacle avoidance route according to the first coordinate and the target route data, and controlling the vehicle to travel along the actual obstacle avoidance route to avoid the obstacle; it can adaptively adjust the obstacle avoidance route according to the attribute of the obstacle and the vehicle's own situation, improving the riding experience of the passengers and providing guarantee for ensuring driving safety and improving driving efficiency.

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous driving, and more particularly, to a vehicle obstacle avoidance method, apparatus, computer-readable storage medium, and vehicle. Background Art

[0002] Autonomous driving technology and its applications have currently become the focus of social attention. However, during the process of an autonomous vehicle driving along a pre-planned path, obstacles (such as a malfunctioning vehicle) may be encountered. In this regard, the autonomous vehicle needs to be able to automatically, safely, and in real time generate a new route like a human-driven vehicle to effectively avoid the obstacles. Currently, the general autonomous driving system has an obstacle avoidance function, but it cannot adaptively adjust the obstacle avoidance route according to the actual situation. For example, the obstacle avoidance route needs to consider the attributes of the obstacles (such as vulnerable road users, malfunctioning vehicles, etc.), and on the other hand, it also needs to take into account the riding experience of the passengers and crew (for example, passengers hope that the obstacle avoidance process is as smooth as possible).

[0003] For the above reasons, there is an urgent need for an autonomous vehicle adaptive obstacle avoidance route generation method to solve the above problems. Summary of the Invention

[0004] The purpose of the present disclosure is to provide a vehicle obstacle avoidance method, apparatus, electronic device, and computer-readable storage medium to solve the problem that existing autonomous vehicles cannot adaptively adjust the obstacle avoidance route according to the actual situation.

[0005] According to a first aspect of an embodiment of the present disclosure, a vehicle obstacle avoidance method is provided, including: when a vehicle is driving on a pre-planned path and an obstacle is detected, obtaining the attribute of the obstacle; based on the attribute of the obstacle and the vehicle parameter information of the vehicle, determining a first coordinate of the position where the vehicle is located after completing obstacle avoidance; matching a target obstacle avoidance lane change width from a plurality of pre-stored obstacle avoidance lane change widths; each of the obstacle avoidance lane change widths corresponds to a specified number of alternative routes; determining a target route from the alternative routes corresponding to the target obstacle avoidance lane change width; determining an actual obstacle avoidance route according to the first coordinate and the target route data; and controlling the vehicle to drive along the actual obstacle avoidance route to avoid the obstacle.

[0006] Optionally, the determining a first coordinate of the position where the vehicle is located after completing obstacle avoidance based on the attribute of the obstacle and the vehicle parameter information of the vehicle includes: determining an obstacle avoidance level according to the attribute of the obstacle; determining a preset safety distance according to the obstacle avoidance level; determining a rectangular obstacle fence of the obstacle according to the first position, first length, and first width of the obstacle; and determining a first coordinate of the position where the vehicle is located after completing obstacle avoidance according to the preset safety distance, the rectangular obstacle fence, the vehicle length, and the vehicle width.

[0007] Optionally, the calculation formula of the first coordinate includes:

[0008]

[0009]

[0010] where (X s , Y s ) is the first coordinate, W is the vehicle width, L is the vehicle length, W 2 is the closest lateral distance between the side of the vehicle and the side of the rectangular obstacle fence after the vehicle completes obstacle avoidance, L 2 is the closest longitudinal distance between the side of the vehicle and the side of the rectangular obstacle fence after the vehicle completes obstacle avoidance, θ is the driving azimuth angle after the vehicle completes obstacle avoidance, R is the radius of the earth, (X g , Y g ) is the coordinate of the first vertex, and the first vertex is the lower vertex of the rectangular obstacle fence closest to the obstacle avoidance steering side of the vehicle.

[0011] Optionally, the matching of the target obstacle avoidance lane-changing width from multiple pre-stored obstacle avoidance lane-changing widths based on the first coordinate includes: determining the corresponding first obstacle avoidance lane-changing width based on the vehicle position and the first coordinate; the first obstacle avoidance lane-changing width is the lateral projection distance of the line connecting the center positions of the vehicle before and after obstacle avoidance in the driving direction; and taking the one closest to the first obstacle avoidance lane-changing width among the pre-stored multiple obstacle avoidance lane-changing widths as the target obstacle avoidance lane-changing width.

[0012] Optionally, the target route data includes the positions, speeds, and accelerations of a predetermined number of coordinate points on the pre-stored target route; the determination of the actual obstacle avoidance route according to the first coordinate and the target route data includes: determining the positions, speeds, and accelerations of the predetermined number of coordinate points on the actual obstacle avoidance route according to the first coordinate and the target route data; the predetermined number of coordinate points includes the first adjacent coordinate, the second adjacent coordinate, and the remaining coordinate points; determining a first route according to the positions of the first adjacent coordinate, the second adjacent coordinate, and the remaining coordinate points; and taking the first route as the actual obstacle avoidance route.

[0013] Optionally, determining the positions, speeds, and accelerations of the predetermined number of coordinate points on the actual obstacle avoidance route according to the first coordinate and the target route data includes: determining the first adjacent coordinate by the following method: obtaining a first angle between a first route and the due north direction; the first route is a straight line between the first coordinate and the first adjacent coordinate, and the first adjacent coordinate is the coordinate point on the actual obstacle avoidance route closest to the first coordinate; determining the first adjacent coordinate according to the first angle, the radius of the earth, the first position, the first length, the first width, the driving azimuth angle of the vehicle after completing obstacle avoidance, the coordinates of the first vertex, and the target route data; the first vertex is the vertex below the obstacle fence closest to the side where the vehicle avoids obstacles and turns; determining the second adjacent coordinate by the following method: obtaining a second angle between a second route and the due north direction; the second route is a straight line between the second adjacent coordinate and the first adjacent coordinate, and the second adjacent coordinate is the coordinate point on the actual obstacle avoidance route adjacent to the first adjacent coordinate; determining the second adjacent coordinate according to the second angle, the radius of the earth, the first position, the first length, the first width, the driving azimuth angle of the vehicle after completing obstacle avoidance, the coordinates of the first vertex, and the target route data; using the method for determining the first adjacent coordinate or the second adjacent coordinate to determine the positions of the remaining coordinate points on the actual obstacle avoidance route; taking the speeds and accelerations of the predetermined number of coordinate points on the target route as the speeds and accelerations of the corresponding coordinate points on the actual obstacle avoidance route.

[0014] Optionally, controlling the vehicle to travel along the actual obstacle avoidance route to avoid the obstacle includes: obtaining the speed and acceleration of the starting coordinate in the actual obstacle avoidance route; controlling the movement of the vehicle according to the starting coordinate, the current position of the vehicle, the current speed of the vehicle, and the current acceleration of the vehicle, so that the vehicle maintains the speed and acceleration of the starting coordinate when reaching the starting coordinate position; when the vehicle reaches the starting coordinate, controlling the vehicle to travel according to the positions, speeds, and accelerations of the predetermined number of coordinate points on the actual obstacle avoidance route.

[0015] According to a second aspect of the embodiments of the present disclosure, a vehicle obstacle avoidance device is provided, including: an acquisition module configured to acquire the attribute of an obstacle when the vehicle is traveling on a pre-planned path and detects the obstacle; a processing module configured to determine a first coordinate of the position where the vehicle is located after completing obstacle avoidance based on the attribute of the obstacle and the vehicle parameter information of the vehicle; the processing module is further configured to match a target obstacle avoidance lane-changing width from a plurality of pre-stored obstacle avoidance lane-changing widths; each of the obstacle avoidance lane-changing widths corresponds to a specified number of alternative routes; the processing module is further configured to determine a target route from the alternative routes corresponding to the target obstacle avoidance lane-changing width; the processing module is further configured to determine an actual obstacle avoidance route according to the first coordinate and the target route data; a control module configured to control the vehicle to travel along the actual obstacle avoidance route to avoid the obstacle.

[0016] According to a third aspect of the embodiments of the present disclosure, a non-transitory computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the foregoing vehicle obstacle avoidance method are implemented.

[0017] According to a fourth aspect of the embodiments of the present disclosure, a vehicle is provided, including: a memory on which a computer program is stored; a processor configured to execute the computer program in the memory to implement the steps of the foregoing vehicle obstacle avoidance method.

[0018] The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects: when the vehicle is traveling on a pre-planned path and detects an obstacle, acquire the attribute of the obstacle, determine a first coordinate of the position where the vehicle is located after completing obstacle avoidance based on the attribute of the obstacle and the vehicle parameter information of the vehicle, match a target obstacle avoidance lane-changing width from a plurality of pre-stored obstacle avoidance lane-changing widths, each of the obstacle avoidance lane-changing widths corresponds to a specified number of alternative routes, determine a target route from the alternative routes corresponding to the target obstacle avoidance lane-changing width, determine an actual obstacle avoidance route according to the first coordinate and the target route data, and control the vehicle to travel along the actual obstacle avoidance route to avoid the obstacle; it can adaptively adjust the obstacle avoidance route according to the attribute of the obstacle and the vehicle's own situation, improving the riding experience of the passengers and providing guarantee for ensuring driving safety and improving driving efficiency.

[0019] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings are used to provide a further understanding of the present disclosure, and constitute a part of the specification, and are used to explain the present disclosure together with the following specific embodiments, but do not constitute a limitation to the present disclosure. In the drawings:

[0021] Figure 1 It is a flowchart of a vehicle obstacle avoidance method shown in an exemplary embodiment of the present disclosure.

[0022] Figure 2 It is a flowchart of another vehicle obstacle avoidance method shown in an exemplary embodiment of the present disclosure.

[0023] Figure 3 It is a schematic diagram of vehicle obstacle avoidance shown in an exemplary embodiment of the present disclosure.

[0024] Figure 4 It is a block diagram of a vehicle obstacle avoidance device shown in an exemplary embodiment of the present disclosure.

[0025] Figure 5 It is a block diagram of an electronic device shown in an exemplary embodiment of the present disclosure.

[0026] Description of reference numerals

[0027] 30 - Vehicle obstacle avoidance device; 301 - Acquisition module; 303 - Processing module; 305 - Control module; 400 - Electronic device; 401 - Processor; 402 - Memory; 403 - Multimedia component; 404 - I / O interface; 405 - Communication component. Detailed implementation manners

[0028] The following describes the detailed implementation manners of the present disclosure with reference to the accompanying drawings. It should be understood that the detailed implementation manners described herein are only used to illustrate and explain the present disclosure, and are not used to limit the present disclosure.

[0029] When the following description relates to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present disclosure. On the contrary, they are only examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0030] Please refer to Figure 1 , Figure 1 , which is a flowchart of a vehicle obstacle avoidance method shown in an exemplary embodiment of the present disclosure. This method is executed by an electronic device, for example, by an autonomous vehicle or a control device integrated on an autonomous vehicle. Figure 1 The vehicle obstacle avoidance method shown includes the following steps:

[0031] In step S101, when the vehicle is driving on a pre - planned path and detects an obstacle, obtain the attribute of the obstacle.

[0032] When an autonomous vehicle is driving on a pre-planned path and detects an obstacle, it obtains the attributes of the obstacle; for example, pedestrians, faulty vehicles, ordinary obstacles, etc., as well as the first position, the first length, and the first width of the obstacle.

[0033] In step S102, based on the attributes of the obstacle and the vehicle parameter information, the first coordinate of the position where the vehicle is located after completing obstacle avoidance is determined.

[0034] Exemplarily, the obstacle avoidance level, the obstacle fence of the obstacle, and the position coordinates of the four vertices of the obstacle fence can be determined according to the attributes of the obstacle. The obstacle avoidance level is the danger level of the obstacle, and the obstacle fence is determined according to the first position, the first length, and the first width of the obstacle. For example, the obstacle fence can be, but is not limited to, the smallest rectangular frame that can enclose the obstacle. The preset safety distance is determined according to the obstacle avoidance level, and then the first coordinate of the position where the vehicle center is located after the vehicle completes obstacle avoidance is determined according to the preset safety distance, the obstacle fence, the vehicle length, and the vehicle width. The vehicle center can be, but is not limited to, the geometric center of the vehicle.

[0035] In step S103, the target obstacle avoidance lane-changing width is matched from multiple pre-stored obstacle avoidance lane-changing widths based on the first coordinate.

[0036] Each obstacle avoidance lane-changing width corresponds to a specified number of alternative routes.

[0037] Exemplarily, the corresponding first obstacle avoidance lane-changing width can be determined based on the vehicle position and the first coordinate. The first obstacle avoidance lane-changing width is the lateral projection distance of the line connecting the vehicle center positions before and after vehicle obstacle avoidance in the driving direction; the one that is closest to the first obstacle avoidance lane-changing width among the multiple pre-stored obstacle avoidance lane-changing widths is used as the target obstacle avoidance lane-changing width.

[0038] In step S104, the target route is determined from the alternative routes corresponding to the target obstacle avoidance lane-changing width.

[0039] One can be selected from the alternative routes corresponding to the target obstacle avoidance lane-changing width as the target route to be used as the obstacle avoidance route.

[0040] In step S105, the actual obstacle avoidance route is determined according to the first coordinate and the target route data.

[0041] The target route data includes position, speed, acceleration, etc. It can be the position, speed, and acceleration of a predetermined number of coordinate points on the target route. Determining the actual obstacle avoidance route according to the first coordinate and the target route data can be: determining the position, speed, and acceleration of a predetermined number (such as 10) of coordinate points on the actual obstacle avoidance route according to the first coordinate and the target route data.

[0042] In step S106, the vehicle is controlled to drive along the actual obstacle avoidance route to avoid the obstacle.

[0043] After obtaining the position, speed, and acceleration of the actual obstacle avoidance route, the autonomous vehicle adjusts the speed and acceleration of the vehicle according to the current position, speed, and acceleration of the vehicle, so that the autonomous vehicle maintains the speed and acceleration of the starting coordinate when it travels to the starting coordinate position, and the starting coordinate is the starting point of the actual obstacle avoidance route, and completes the obstacle avoidance operation according to the position, speed, and acceleration of the calculated actual obstacle avoidance route.

[0044] The vehicle obstacle avoidance method provided by the present disclosure, when the vehicle is traveling on a pre-planned path and detects an obstacle, obtains the attribute of the obstacle, determines the first coordinate of the position where the vehicle is located after completing the obstacle avoidance based on the attribute of the obstacle and the vehicle parameter information of the vehicle, matches the target obstacle avoidance lane change width from multiple pre-stored obstacle avoidance lane change widths based on the first coordinate, each obstacle avoidance lane change width corresponds to a specified number of alternative routes, determines the target route from the alternative routes corresponding to the target obstacle avoidance lane change width, determines the actual obstacle avoidance route according to the first coordinate and the target route data, and controls the vehicle to travel according to the actual obstacle avoidance route to avoid the obstacle; it can adaptively adjust the obstacle avoidance route according to the attribute of the obstacle and the vehicle's own situation, improving the riding experience of the passengers and providing guarantee for ensuring driving safety and improving driving efficiency.

[0045] Please refer to Figure 2 , Figure 2 which is a flowchart of another vehicle obstacle avoidance method shown in an exemplary embodiment of the present disclosure. This method is executed by a computer device, for example, by an autonomous vehicle or a control device integrated on the autonomous vehicle.

[0046] It should be noted that Figure 2 the vehicle obstacle avoidance method shown in Figure 1 is consistent with the implementation content of the vehicle obstacle avoidance method shown in Figure 2 and the parts not mentioned in Figure 1 can refer to the description in

[0047] Figure 2 The vehicle obstacle avoidance method shown in

[0048] includes the following steps: In step S201, when the vehicle is traveling on a pre-planned path and detects an obstacle, obtain the attribute of the obstacle.

[0049] The vehicle may be an autonomous vehicle, and in the present disclosure, the autonomous vehicle is taken as an example for illustration.

[0050] The autonomous vehicle is traveling on a pre-planned path. Please refer to Figure 3 , Figure 3 which is a vehicle obstacle avoidance schematic diagram shown in an exemplary embodiment of the present disclosure. As shown in Figure 3As shown, the autonomous vehicle travels from A to B. The pre-planned path can be a series of stored position points, such as longitude and latitude, coordinate points, etc. During the driving process of the autonomous vehicle, the vehicle senses that there is an obstacle on the path ahead of the pre-planned path. The devices for sensing obstacles can include, but are not limited to, on-vehicle cameras, millimeter-wave radars, lidars, V2X devices, roadside cameras, millimeter-wave radars, lidars, etc.

[0051] Through the above-mentioned sensing devices, the attributes of the obstacle can be obtained, such as pedestrians, faulty vehicles, ordinary obstacles, etc., as well as the first position, the first length L 1 and the first width W 1 of the obstacle. If the roadside device is used to sense the obstacle, the roadside device can send the sensed obstacle information to the autonomous vehicle.

[0052] In step S202, based on the attributes of the obstacle and the vehicle parameter information, the first coordinate of the position where the vehicle is located after completing obstacle avoidance is determined.

[0053] Exemplarily, the obstacle avoidance level can be determined according to the attributes of the obstacle. For example, the obstacle avoidance level for vulnerable road users such as pedestrians and motorcycles is set as level 1, the obstacle avoidance level for traffic participants such as faulty vehicles and accident vehicles is set as level 2, and the obstacle avoidance level for ordinary obstacles such as paper boxes and cartons is set as level 3; the obstacle avoidance level is related to the length and width of the distance between the center of the vehicle and the obstacle fence after completing obstacle avoidance. That is to say, the preset safety distances for different obstacles are different, and the preset safety distance can be determined according to the obstacle avoidance level. For example, when the obstacle avoidance level is level 1, it indicates that the danger level of the obstacle is relatively high, and the longitudinal and lateral safety distances need to be set larger; when the obstacle avoidance level is level 2, it indicates that the danger level of the obstacle is moderate, and the longitudinal and lateral safety distances can be moderate; when the obstacle avoidance level is level 3, it indicates that the danger level of the obstacle is relatively low, and the longitudinal and lateral safety distances can be smaller; the obstacle fence is determined according to the first position, the first length and the first width of the obstacle, and the position coordinates of the four vertices of the obstacle fence can also be determined. For example, the obstacle fence can be the smallest rectangular frame that can enclose the obstacle.

[0054] Exemplarily, please refer to Figure 3 , when the obstacle avoidance level is level 1, L 2 can be set to 1, W 2 can be set to 1; when the obstacle avoidance level is level 3, L 2 can be set to 0.6, W 2 can be set to 0.4; W 2 is the shortest lateral distance between the side of the vehicle and the side of the obstacle fence after the vehicle completes obstacle avoidance, and L 2 is the shortest longitudinal distance between the side of the vehicle and the side of the obstacle fence after the vehicle completes obstacle avoidance.

[0055] Determine the first coordinate of the position where the vehicle center is located after the vehicle completes obstacle avoidance according to the preset safety distance, obstacle fence, vehicle length, and vehicle width. The vehicle center can be, but is not limited to, the geometric center of the vehicle. The vehicle parameter information includes the vehicle length L, vehicle width W, current vehicle position, vehicle speed, vehicle acceleration, etc. According to the above obstacle avoidance level and combining this vehicle parameter information, the first coordinate of the position where the vehicle center is located after the autonomous vehicle completes obstacle avoidance can be determined.

[0056] In one implementation, the calculation formula for the first coordinate includes:

[0057]

[0058]

[0059] where, (X s , Y s ) is the first coordinate, W is the vehicle width, L is the vehicle length, W 2 is the closest lateral distance between the side of the vehicle after obstacle avoidance and the side of the obstacle fence, L 2 is the closest longitudinal distance between the side of the vehicle after obstacle avoidance and the side of the obstacle fence, θ is the driving azimuth angle after the vehicle completes obstacle avoidance, R is the radius of the earth, (X g , Y g ) is the coordinate of the first vertex, and the first vertex is the vertex below the obstacle fence closest to the side of the vehicle where obstacle avoidance steering occurs. Please refer to Figure 3 . When the vehicle travels leftward for obstacle avoidance, the first vertex is the lower left vertex of the obstacle fence.

[0060] In step S203, based on the first coordinate, the target obstacle avoidance lane change width is matched from multiple pre-stored obstacle avoidance lane change widths.

[0061] Matching the target obstacle avoidance lane change width from multiple pre-stored obstacle avoidance lane change widths based on the first coordinate includes: determining the corresponding first obstacle avoidance lane change width based on the vehicle position and the first coordinate. The first obstacle avoidance lane change width is the lateral projection distance of the line connecting the vehicle center positions before and after obstacle avoidance in the driving direction; taking the obstacle avoidance lane change width closest to the first obstacle avoidance lane change width among the multiple pre-stored obstacle avoidance lane change widths as the target obstacle avoidance lane change width.

[0062] Please continue to refer to Figure 3 , and the calculation formula for the first obstacle avoidance lane change width W 3 can be obtained as including: where, (X t , Y t) is the current position coordinates of the vehicle, and θ t is the current driving azimuth angle of the vehicle; based on the obtained first obstacle avoidance lane change width, the target obstacle avoidance lane change width is screened out from multiple pre-stored obstacle avoidance lane change widths. In one implementation, the nearest neighbor classification method can be used, that is, the obstacle avoidance lane change width closest to the first obstacle avoidance lane change width among the multiple pre-stored obstacle avoidance lane change widths is used as the target obstacle avoidance lane change width. For example, if the first obstacle avoidance lane change width is 5.01m, and the multiple pre-stored obstacle avoidance lane change widths include 4.9m, 4.95m, 5m, 5.05m, then the one closest to 5.01m is 5m, and 5m can be used as the target obstacle avoidance lane change width.

[0063] It should be noted that the multiple pre-stored obstacle avoidance lane change widths are obtained by training the obstacle avoidance route data. For example, multiple experienced drivers can be selected to conduct obstacle avoidance lane change training for multiple obstacle avoidance lane change widths (sampled every m meters, for example, m = 0.05m); in this way, for each fixed obstacle avoidance lane change width, a series of lane change curves will be obtained correspondingly. These lane change curves include position, speed, acceleration, etc., which can be the position, speed, and acceleration of a predetermined number of coordinate points on the lane change curve. In the present disclosure, three curves are selected from these lane change curves for storage as alternative routes. For example, please continue to refer to Figure 3 and the one with a relatively long longitudinal distance during the obstacle avoidance driving process can be stored as alternative route 1, the one with a moderate longitudinal distance during the obstacle avoidance driving process can be stored as alternative route 2, and the one with a relatively short longitudinal distance during the obstacle avoidance driving process can be stored as alternative route 3. Thus, a specified number of alternative routes corresponding to each obstacle avoidance lane change width are obtained.

[0064] In step S204, the target route is determined from the alternative routes corresponding to the target obstacle avoidance lane change width.

[0065] As mentioned above, the specified number of alternative routes corresponding to each obstacle avoidance lane change width. In one implementation, the specified number can be but is not limited to 3. One can be selected from the alternative routes corresponding to the target obstacle avoidance lane change width as the target route h to be used as the obstacle avoidance route. In one implementation, the target route can be determined from the alternative routes according to the riding habits information of the passengers and the length of the alternative routes. For example, if the passengers of the autonomous vehicle select the smooth driving type, then alternative route 1 is used as the obstacle avoidance route, that is, lane change for obstacle avoidance starts when the distance from the obstacle is relatively far, and the obstacle avoidance method is relatively gentle; if the passengers of the autonomous vehicle select the normal driving type, then alternative route 2 is used as the obstacle avoidance route, and the obstacle avoidance method is relatively moderate; similarly, if the passengers of the autonomous vehicle select the fast driving type, then alternative route 3 is used as the obstacle avoidance route, that is, lane change for obstacle avoidance starts when the distance from the obstacle is relatively close, and the obstacle avoidance method is relatively rapid.

[0066] In step S205, an actual obstacle avoidance route is determined according to the first coordinate and the target route data.

[0067] The target route data includes position, speed, acceleration, etc., and can be the positions, speeds, and accelerations of a predetermined number of coordinate points on the target route. In one implementation, the predetermined number can be, but is not limited to, 10. For example, the predetermined number of coordinate points can include the first adjacent coordinate, the second adjacent coordinate, and the remaining coordinate points, where the first adjacent coordinate is the coordinate point on the actual obstacle avoidance route closest to the first coordinate, and the second adjacent coordinate is the coordinate point on the actual obstacle avoidance route adjacent to the first adjacent coordinate.

[0068] Determining the actual obstacle avoidance route according to the first coordinate and the target route data can be: determining the positions, speeds, and accelerations of a predetermined number (such as 10) of coordinate points on the actual obstacle avoidance route according to the first coordinate and the target route data.

[0069] Exemplarily, the first adjacent coordinate can be determined by the following method:

[0070] Obtain the first angle between the first route and the due north direction, where the first route is the straight line between the first coordinate and the first adjacent coordinate, and the first adjacent coordinate is the coordinate point on the actual obstacle avoidance route closest to the first coordinate; determine the first adjacent coordinate according to the first angle, the radius of the earth, the first position, the first length, the first width, the driving azimuth angle of the vehicle after completing obstacle avoidance, the coordinates of the first vertex, and the target route data, where the first vertex is the vertex below the obstacle fence closest to the side of the vehicle for obstacle avoidance turning; the calculation formula for the first adjacent coordinate includes:

[0071]

[0072]

[0073] where (X s-1 , Y s-1 ) is the first adjacent coordinate, (X s , Y s ) is the first coordinate, R is the radius of the earth, (X c , Y c ) are the coordinates of the end point of obstacle avoidance completion on the target route, (X c-1 , Y c-1 ) are the coordinates of the adjacent point of (X c , Y c ),

[0074] Similarly, the second adjacent coordinate (X s-2 , Y s-2):Obtain the second included angle between the second route and the due north direction. The second route is the straight line between the second adjacent coordinate and the first adjacent coordinate. Determine the second adjacent coordinate according to the second included angle, the radius of the earth, the first position, the first length, the first width, the driving azimuth angle of the vehicle after obstacle avoidance, the coordinates of the first vertex, and the target route data. The calculation formula of the second adjacent coordinate is similar to that of the first adjacent coordinate and can be deduced by analogy, so it will not be elaborated here.

[0075] Through the above method, the positions of a predetermined number of coordinate points on the actual obstacle avoidance route have been obtained. Determine the first route according to the first adjacent coordinate, the second adjacent coordinate, and the positions of the remaining coordinate points, and use the first route as the position of the actual obstacle avoidance route. Next, the speeds and accelerations of a predetermined number of coordinate points on the target route can be used as the speeds and accelerations of the corresponding coordinate points on the actual obstacle avoidance route, so as to obtain the positions, speeds, and accelerations of a predetermined number of coordinate points on the actual obstacle avoidance route.

[0076] In step S206, control the vehicle to drive along the actual obstacle avoidance route to avoid obstacles.

[0077] After obtaining the position, speed, and acceleration of the actual obstacle avoidance route, the autonomous vehicle adjusts the speed and acceleration of the vehicle according to the current position, speed, and acceleration of the vehicle, so that the autonomous vehicle maintains the speed and acceleration of the starting coordinate when it drives to the starting coordinate position. The starting coordinate is the starting point of the actual obstacle avoidance route, and completes the obstacle avoidance operation according to the calculated actual obstacle avoidance route data. For example, the speed and acceleration of the starting coordinate in the actual obstacle avoidance route can be obtained, and the vehicle movement is controlled according to the starting coordinate, the current position of the vehicle, the current speed of the vehicle, and the current acceleration of the vehicle, so that the vehicle maintains the speed and acceleration of the starting coordinate when it reaches the starting coordinate position. When the vehicle reaches the starting coordinate, the vehicle is controlled to drive according to the positions, speeds, and accelerations of a predetermined number of coordinate points on the actual obstacle avoidance route to avoid obstacles.

[0078] In summary, the vehicle obstacle avoidance method provided by the present disclosure includes: when the vehicle is driving on the pre-planned path and detects an obstacle, obtain the attributes of the obstacle, and based on the attributes of the obstacle and the vehicle parameter information of the vehicle, determine the first coordinate of the position of the vehicle after obstacle avoidance. Match the target obstacle avoidance lane change width from a plurality of pre-stored obstacle avoidance lane change widths. Each obstacle avoidance lane change width corresponds to a specified number of alternative routes. Determine the target route from the alternative routes corresponding to the target obstacle avoidance lane change width. Determine the actual obstacle avoidance route according to the first coordinate and the target route data, and control the vehicle to drive along the actual obstacle avoidance route to avoid obstacles; it can adaptively adjust the obstacle avoidance route according to the attributes of the obstacle and the vehicle itself, improving the riding experience of the passengers and providing guarantee for ensuring driving safety and improving driving efficiency.

[0079] Figure 4 is a block diagram of a vehicle obstacle avoidance device shown in an exemplary embodiment of the present disclosure. Referring to Figure 4 , the vehicle obstacle avoidance device 30 includes an acquisition module 301, a processing module 303, and a control module 305.

[0080] The acquisition module 301 is configured to acquire the attribute of the obstacle when the vehicle is driving on a pre-planned path and detects an obstacle;

[0081] The processing module 303 is configured to determine a first coordinate of the position of the vehicle after the vehicle completes obstacle avoidance based on the attribute of the obstacle and the vehicle parameter information of the vehicle;

[0082] The processing module 303 is further configured to match a target obstacle avoidance lane-changing width from a plurality of pre-stored obstacle avoidance lane-changing widths based on the first coordinate; each of the obstacle avoidance lane-changing widths corresponds to a specified number of alternative routes;

[0083] The processing module 303 is further configured to determine a target route from the alternative routes corresponding to the target obstacle avoidance lane-changing width;

[0084] The processing module 303 is further configured to determine an actual obstacle avoidance route according to the first coordinate and the target route data;

[0085] The control module 305 is configured to control the vehicle to drive along the actual obstacle avoidance route to avoid the obstacle.

[0086] Optionally, the processing module 303 is further configured to determine an obstacle avoidance level according to the attribute of the obstacle;

[0087] Determine a preset safety distance according to the obstacle avoidance level;

[0088] Determine an obstacle fence of the obstacle according to the first position, the first length, and the first width of the obstacle;

[0089] Determine the first coordinate of the position of the vehicle after the vehicle completes obstacle avoidance according to the preset safety distance, the obstacle fence, the vehicle length, and the vehicle width.

[0090] Optionally, the calculation formula of the first coordinate includes:

[0091]

[0092]

[0093] wherein, (X s , Y s ) is the first coordinate, W is the vehicle width, L is the vehicle length, W2 L is the closest lateral distance between the side of the vehicle and the side of the obstacle fence after the vehicle completes obstacle avoidance. 2 is the closest longitudinal distance between the side of the vehicle and the side of the obstacle fence after the vehicle completes obstacle avoidance. θ is the driving azimuth angle of the vehicle after completing obstacle avoidance, R is the radius of the earth, (X g , Y g ) are the coordinates of the first vertex, and the first vertex is the lower vertex of the obstacle fence closest to the side of the vehicle where obstacle avoidance steering occurs.

[0094] Optionally, the processing module 303 is further configured to determine a corresponding first obstacle avoidance lane change width based on the vehicle position and the first coordinate; the first obstacle avoidance lane change width is the lateral projection distance of the line connecting the center positions of the vehicle before and after obstacle avoidance in the driving direction.

[0095] Take the obstacle avoidance lane change width closest to the first obstacle avoidance lane change width among the pre-stored multiple obstacle avoidance lane change widths as the target obstacle avoidance lane change width.

[0096] Optionally, the processing module 303 is further configured to determine the positions, speeds, and accelerations of the predetermined number of coordinate points on the actual obstacle avoidance route according to the first coordinate and the target route data; the predetermined number of coordinate points includes a first adjacent coordinate, a second adjacent coordinate, and the remaining coordinate points.

[0097] Determine a first route according to the positions of the first adjacent coordinate, the second adjacent coordinate, and the remaining coordinate points.

[0098] Take the first route as the actual obstacle avoidance route.

[0099] Optionally, the processing module 303 is further configured to determine the first adjacent coordinate by the following method:

[0100] Obtain a first included angle between the first route and the due north direction; the first route is the straight line between the first coordinate and the first adjacent coordinate, and the first adjacent coordinate is the coordinate point on the actual obstacle avoidance route closest to the first coordinate.

[0101] Determine the first adjacent coordinate according to the first included angle, the radius of the earth, the first position, the first length, the first width, the driving azimuth angle of the vehicle after completing obstacle avoidance, and the coordinates of the first vertex; the first vertex is the lower vertex of the rectangular obstacle fence closest to the side of the vehicle where obstacle avoidance steering occurs.

[0102] Determine the second adjacent coordinate by the following method:

[0103] Obtain a second included angle between the second route and the due north direction; the second route is a straight line between the second adjacent coordinate and the first adjacent coordinate, and the second adjacent coordinate is a coordinate point adjacent to the first adjacent coordinate on the actual obstacle avoidance route;

[0104] Determine the second adjacent coordinate according to the second included angle, the radius of the earth, the first position, the first length, the first width, the driving azimuth angle of the vehicle after completing obstacle avoidance, and the coordinates of the first vertex;

[0105] Use the method for determining the first adjacent coordinate or the second adjacent coordinate to determine the positions of the remaining coordinate points on the actual obstacle avoidance route;

[0106] Take the speeds and accelerations of the predetermined number of coordinate points on the target route as the speeds and accelerations of the corresponding coordinate points on the actual obstacle avoidance route.

[0107] Optionally, the obtaining module 301 is further configured to obtain the speed and acceleration of the starting coordinate in the actual obstacle avoidance route;

[0108] The processing module 303 is further configured to control the movement of the vehicle according to the starting coordinate, the current position of the vehicle, the current speed of the vehicle, and the current acceleration of the vehicle, so that the vehicle maintains the speed and acceleration of the starting coordinate when reaching the position of the starting coordinate;

[0109] When the vehicle reaches the starting coordinate, control the vehicle to travel according to the positions, speeds, and accelerations of the predetermined number of coordinate points on the actual obstacle avoidance route.

[0110] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0111] Figure 5 is a block diagram of an electronic device shown according to an exemplary embodiment. As Figure 5 shown, the electronic device 400 may be a device integrated on an autonomous vehicle. The electronic device 400 may include: a processor 401, a memory 402. The electronic device 400 may further include one or more of a multimedia component 403, an input / output (I / O) interface 404, and a communication component 405.

[0112] Among them, the processor 401 is used to control the overall operation of the electronic device 400 to complete all or part of the steps in the above vehicle obstacle avoidance method. The memory 402 is used to store various types of data to support the operation of the electronic device 400. These data may include, for example, instructions for any application or method operating on the electronic device 400, as well as application-related data, such as contact data, received and sent messages, pictures, audio, video, and so on. The memory 402 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 403 may include a screen and an audio component. The screen can be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals can be further stored in the memory 402 or sent through the communication component 405. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 404 provides an interface between the processor 401 and other interface modules, and the above other interface modules can be a keyboard, a mouse, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 405 is used for wired or wireless communication between the electronic device 400 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G, 4G, NB-IoT, eMTC, or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 405 may include: a Wi-Fi module, a Bluetooth module, an NFC module, and so on.

[0113] In an exemplary embodiment, the electronic device 400 can be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components, and is used to execute the above-mentioned vehicle obstacle avoidance method.

[0114] In another exemplary embodiment, a computer-readable storage medium including program instructions is further provided. When the program instructions are executed by a processor, the steps of the above-mentioned vehicle obstacle avoidance method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 402 including program instructions, and the above-mentioned program instructions can be executed by the processor 401 of the electronic device 400 to complete the above-mentioned vehicle obstacle avoidance method.

[0115] In another exemplary embodiment, a computer-readable storage medium including program instructions is further provided. When the program instructions are executed by a processor, the steps of the above-mentioned vehicle obstacle avoidance method are implemented.

[0116] In another exemplary embodiment, a computer program product is further provided. The computer program product includes a computer program that can be executed by a programmable device, and the computer program has a code portion for executing the above-mentioned vehicle obstacle avoidance method when executed by the programmable device.

[0117] The preferred embodiments of the present disclosure have been described in detail above in conjunction with the accompanying drawings. However, the present disclosure is not limited to the specific details in the above embodiments. Within the scope of the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0118] In addition, it should be noted that, in the above specific embodiments, the various specific technical features described can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the present disclosure does not separately describe various possible combination methods.

[0119] Furthermore, any combination can be made between various different embodiments of the present disclosure as long as it does not violate the idea of the present disclosure, and it should also be regarded as the content disclosed by the present disclosure.

Claims

1. A vehicle obstacle avoidance method, characterized in that, it includes: When the vehicle is driving on the pre-planned path and detects an obstacle, obtain the attributes of the obstacle; Based on the attributes of the obstacle and the vehicle parameter information of the vehicle, determine the first coordinate of the position of the vehicle after the vehicle completes obstacle avoidance; Based on the first coordinate, match the target obstacle avoidance lane-changing width from multiple pre-stored obstacle avoidance lane-changing widths; each of the obstacle avoidance lane-changing widths corresponds to a specified number of alternative routes; Determine the target route from the alternative routes corresponding to the target obstacle avoidance lane-changing width; The data of the target route includes the positions, speeds, and accelerations of a predetermined number of coordinate points on the pre-stored target route; determine the positions, speeds, and accelerations of the predetermined number of coordinate points on the actual obstacle avoidance route according to the first coordinate and the data of the target route; the predetermined number of coordinate points includes the first adjacent coordinate, the second adjacent coordinate, and the remaining coordinate points; Determine the first route according to the positions of the first adjacent coordinate, the second adjacent coordinate, and the remaining coordinate points; Take the first route as the actual obstacle avoidance route; Control the vehicle to drive along the actual obstacle avoidance route to avoid the obstacle; The determining the positions, speeds, and accelerations of the predetermined number of coordinate points on the actual obstacle avoidance route according to the first coordinate and the data of the target route includes: Determine the first adjacent coordinate by the following method: Obtain the first angle between the first route and the due north direction; the first route is the straight line between the first coordinate and the first adjacent coordinate, and the first adjacent coordinate is the coordinate point on the actual obstacle avoidance route closest to the first coordinate; Determine the first adjacent coordinate according to the first angle, the radius of the earth, the first position, the first length, the first width, the driving azimuth angle of the vehicle after completing obstacle avoidance, the coordinates of the first vertex, and the data of the target route; the first vertex is the vertex below the obstacle fence closest to the side where the vehicle avoids obstacles; Determine the second adjacent coordinate by the following method: Obtain the second angle between the second route and the due north direction; the second route is the straight line between the second adjacent coordinate and the first adjacent coordinate, and the second adjacent coordinate is the coordinate point on the actual obstacle avoidance route adjacent to the first adjacent coordinate; Determine the second adjacent coordinate according to the second angle, the radius of the earth, the first position, the first length, the first width, the driving azimuth angle of the vehicle after completing obstacle avoidance, the coordinates of the first vertex, and the data of the target route; Use the method of determining the first adjacent coordinate or the second adjacent coordinate to determine the positions of the remaining coordinate points on the actual obstacle avoidance route; Take the speeds and accelerations of the predetermined number of coordinate points on the target route as the speeds and accelerations of the corresponding coordinate points on the actual obstacle avoidance route.

2. The method according to claim 1, characterized in that, The determining the first coordinate of the position of the vehicle after the vehicle completes obstacle avoidance based on the attributes of the obstacle and the vehicle parameter information of the vehicle includes: Determine the obstacle avoidance level according to the attributes of the obstacle; Determine the preset safety distance according to the obstacle avoidance level; Determine the obstacle fence of the obstacle according to the first position, the first length, and the first width of the obstacle; Determine the first coordinate of the position where the vehicle is located after the vehicle completes obstacle avoidance according to the preset safety distance, the obstacle fence, the vehicle length, and the vehicle width.

3. The method according to claim 2, wherein, the calculation formula of the first coordinate includes: Among them, (X s , Y s ) is the first coordinate, W is the vehicle width, L is the vehicle length, W 2 is the nearest lateral distance between the side of the vehicle and the side of the obstacle fence after the vehicle completes obstacle avoidance, L 2 is the nearest longitudinal distance between the side of the vehicle and the side of the obstacle fence after the vehicle completes obstacle avoidance, θ is the driving azimuth angle of the vehicle after completing obstacle avoidance, R is the radius of the earth, (X g , Y g ) is the coordinate of the first vertex, and the first vertex is the vertex below the obstacle fence closest to the side of the vehicle where obstacle avoidance steering occurs.

4. The method according to claim 1, wherein, the matching of the target obstacle avoidance lane change width from multiple pre-stored obstacle avoidance lane change widths based on the first coordinate includes: Determine the corresponding first obstacle avoidance lane change width based on the vehicle position and the first coordinate; the first obstacle avoidance lane change width is the lateral projection distance of the connection line of the vehicle center positions before and after the vehicle avoids the obstacle in the driving direction; Take the one closest to the first obstacle avoidance lane change width among the multiple pre-stored obstacle avoidance lane change widths as the target obstacle avoidance lane change width.

5. The method according to claim 1, wherein, the controlling the vehicle to travel along the actual obstacle avoidance route to avoid the obstacle includes: Obtain the speed and acceleration of the starting coordinate in the actual obstacle avoidance route; Control the vehicle movement according to the starting coordinate, the current vehicle position, the current vehicle speed, and the current vehicle acceleration, so that the vehicle maintains the speed and acceleration of the starting coordinate when reaching the starting coordinate position; When the vehicle reaches the starting coordinate, control the vehicle to travel according to the positions, speeds, and accelerations of the predetermined number of coordinate points on the actual obstacle avoidance route.

6. A vehicle obstacle avoidance device, wherein, comprises: An acquisition module, configured to acquire the attributes of the obstacle when the vehicle is traveling on a pre-planned path and detects an obstacle; A processing module, configured to determine the first coordinate of the position where the vehicle is located after the vehicle completes obstacle avoidance based on the attributes of the obstacle and the vehicle parameter information of the vehicle; The processing module is further configured to match a target obstacle avoidance lane change width from multiple pre-stored obstacle avoidance lane change widths based on the first coordinate; each obstacle avoidance lane change width corresponds to a specified number of alternative routes; The processing module is further configured to determine a target route from the alternative routes corresponding to the target obstacle avoidance lane change width; The data of the target route includes the positions, speeds, and accelerations of a predetermined number of coordinate points on the pre-stored target route; the processing module is further configured to determine the positions, speeds, and accelerations of the predetermined number of coordinate points on the actual obstacle avoidance route according to the first coordinate and the data of the target route; the predetermined number of coordinate points includes the first adjacent coordinate, the second adjacent coordinate, and the remaining coordinate points; determine the first route according to the positions of the first adjacent coordinate, the second adjacent coordinate, and the remaining coordinate points; take the first route as the actual obstacle avoidance route; A control module, configured to control the vehicle to travel along the actual obstacle avoidance route to avoid the obstacle; The processing module is further configured to: Determine the first adjacent coordinate by the following method: Obtain a first included angle between the first route and the due north direction; the first route is a straight line between the first coordinate and the first adjacent coordinate, and the first adjacent coordinate is the coordinate point on the actual obstacle avoidance route that is closest to the first coordinate; Determine the first adjacent coordinate according to the first included angle, the radius of the earth, the first position, the first length, the first width, the driving azimuth angle of the vehicle after completing obstacle avoidance, the coordinates of the first vertex, and the data of the target route; the first vertex is the vertex below the obstacle fence that is closest to the side where the vehicle avoids obstacles and turns; Determine the second adjacent coordinate by the following method: Obtain a second included angle between the second route and the due north direction; the second route is a straight line between the second adjacent coordinate and the first adjacent coordinate, and the second adjacent coordinate is the coordinate point on the actual obstacle avoidance route that is adjacent to the first adjacent coordinate; Determine the second adjacent coordinate according to the second included angle, the radius of the earth, the first position, the first length, the first width, the driving azimuth angle of the vehicle after completing obstacle avoidance, the coordinates of the first vertex, and the data of the target route; Use the method for determining the first adjacent coordinate or the second adjacent coordinate to determine the positions of the remaining coordinate points on the actual obstacle avoidance route; Use the speeds and accelerations of the predetermined number of coordinate points on the target route as the speeds and accelerations of the corresponding coordinate points on the actual obstacle avoidance route.

7. A non-transitory computer-readable storage medium, on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the steps of the method according to any one of claims 1-5 are implemented.

8. A vehicle, characterized in that, comprising: a memory, on which a computer program is stored; a processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1-5.

Images