Vehicle obstacle avoidance processing method and device, electronic equipment and storage medium

Abstract

The invention discloses a vehicle obstacle avoidance processing method and device, electronic equipment and a storage medium. Comprising the steps that the driving working condition of a target vehicle at the current moment is obtained, and the driving working condition comprises a basic working condition and a non-reference working condition; obtaining vehicle body information, vehicle body key point information and a minimum turning radius of the target vehicle and obstacle information under the reference working condition, and determining transverse obstacle avoidance data based on the vehicle body information and the obstacle information of the target vehicle; and / or longitudinal obstacle avoidance data are determined based on the vehicle body key point information, the minimum turning radius and the obstacle information of the target vehicle, and the transverse obstacle avoidance data comprise the rear axle turning radius and the front axle course angle; the longitudinal obstacle avoidance data comprises an obstacle avoidance distance; and obstacle avoidance processing is performed on the target vehicle based on the transverse obstacle avoidance data and / or the longitudinal obstacle avoidance data. According to the scheme, by determining the transverse obstacle avoidance data and / or the longitudinal obstacle avoidance data, obstacle avoidance processing of the vehicle in an obstacle scene is realized, and the obstacle avoidance capability and the passing rate of the vehicle are improved.

Description

Technical Field

[0001] This invention relates to the field of vehicle obstacle avoidance technology, and in particular to a method, device, electronic device, and storage medium for vehicle obstacle avoidance. Background Technology

[0002] With the development of the intelligent driving industry, various methods of environmental perception have emerged, such as using cameras, ultrasonic radar, millimeter-wave radar, and lidar in different combinations to perceive the vehicle's driving environment. Based on the surrounding environmental information, the vehicle determines its obstacle avoidance strategy, enabling lane changes or obstacle avoidance. However, high-precision equipment is needed to collect accurate environmental perception data, and more precise obstacle avoidance and maneuvering methods are required to ensure smooth passage in complex environments and confined driving spaces. Currently available obstacle avoidance and maneuvering methods have limitations in terms of efficiency. Summary of the Invention

[0003] This invention provides a method, apparatus, electronic device, and storage medium for vehicle obstacle avoidance, in order to solve the problem of low obstacle avoidance efficiency in the prior art.

[0004] According to one aspect of the present invention, a vehicle obstacle avoidance method is provided, comprising:

[0005] Obtain the current driving conditions of the target vehicle, including basic conditions and non-baseline conditions;

[0006] Acquire the target vehicle's body information, key body point information, minimum turning radius, and obstacle information under baseline conditions; determine lateral obstacle avoidance data based on the target vehicle's body information and obstacle information; and / or determine longitudinal obstacle avoidance data based on the target vehicle's key body point information, minimum turning radius, and obstacle information, wherein the lateral obstacle avoidance data includes the rear axle turning radius and front axle heading angle; and the longitudinal obstacle avoidance data includes obstacle avoidance distance.

[0007] Obstacle avoidance processing is performed on the target vehicle based on lateral obstacle avoidance data and / or longitudinal obstacle avoidance data.

[0008] Optionally, the baseline condition is inner obstacle avoidance in the first rotation direction. The vehicle body information includes the vehicle width and axle distance, and the obstacle information includes the position data of multiple obstacle corner points. Based on the target vehicle's vehicle body information and obstacle information, lateral obstacle avoidance data is determined, including: determining the turning radius corresponding to each obstacle corner point based on the position data of each obstacle corner point and the vehicle body width; determining the angle data corresponding to each obstacle corner point based on the rear axle turning radius and axle distance corresponding to each obstacle corner point; and determining the lateral obstacle avoidance data based on the turning radius and angle data corresponding to each obstacle corner point.

[0009] Optionally, the baseline condition is obstacle avoidance on the outside in the first rotation direction; determining lateral obstacle avoidance data based on the target vehicle's body information and obstacle information includes: acquiring a turning radius calculation model, wherein the turning radius calculation model includes a mathematical relationship between turning radius parameters, two-dimensional coordinate parameters of the overhanging corner point, and linear parameters, and the linear parameters are the linear parameters of the obstacle edge lines obtained by fitting the position data of adjacent obstacle corner points; acquiring the two-dimensional coordinate data of the target overhanging corner point and the linear parameter values ​​corresponding to multiple obstacle edge lines, and substituting them into the turning radius calculation model to obtain the turning radius corresponding to each obstacle edge line; determining the angle data corresponding to each obstacle edge line based on the turning radius corresponding to each obstacle edge line and the axle distance; and determining lateral obstacle avoidance data based on the turning radius and angle data corresponding to each obstacle edge line.

[0010] Optionally, longitudinal obstacle avoidance data is determined based on the target vehicle's key point information, minimum turning radius, and obstacle information. This includes: obtaining the effective collision area of ​​the vehicle under a baseline condition from the key point information, and obtaining the target vehicle's minimum turning radius at the current moment; wherein the effective collision area includes multiple vehicle segments, each segment being formed by connecting at least two key points sequentially; for each vehicle segment, first distance data is determined based on the key point position information, obstacle information, and minimum turning radius, wherein the first distance data includes the distance data of multiple obstacle corner points relative to the instantaneous turning center of the target vehicle; first angle data is determined based on the key point position information, obstacle information, minimum turning radius, and first distance data, wherein the first angle data includes the angle data corresponding to multiple obstacle corner points, each angle being the angle formed by the obstacle corner point and the vehicle collision point relative to the instantaneous turning center of the target vehicle; obstacle avoidance distances for each obstacle corner point are determined based on the first distance data and the first angle, and the minimum obstacle avoidance distance among the obstacle corner points is selected as the longitudinal obstacle avoidance data for the vehicle segment.

[0011] Optionally, the method for obtaining obstacle information under the reference working condition includes: when the target vehicle is in a non-reference working condition, spatially transforming the obstacle information under the non-reference working condition to obtain the transformed position information under the reference working condition corresponding to the non-reference working condition, and updating the obstacle information based on the transformed position information; the method also includes: inverting the lateral obstacle avoidance data and / or longitudinal obstacle avoidance data to obtain the lateral obstacle avoidance data and / or longitudinal obstacle avoidance data under the non-reference working condition.

[0012] Optionally, before determining the longitudinal obstacle avoidance data based on the target vehicle's key point information, minimum turning radius, and obstacle information, the method further includes: determining whether the obstacle is within the effective collision area based on the obstacle information and the vehicle's key point information; if the obstacle is within the effective collision area, then proceeding to determine the longitudinal obstacle avoidance data; if the obstacle is not within the effective collision area, then not proceeding to determine the longitudinal obstacle avoidance data. The method for determining whether the obstacle is within the effective collision area includes one or more of the following: determining the effective collision area range based on the vehicle's key point information; if the obstacle information meets the effective collision area range, then determining that the obstacle is within the effective collision area; obtaining the instantaneous turning center position data of the target vehicle; determining second distance data based on the obstacle information and the instantaneous turning center position data; determining a distance threshold based on the vehicle's key point information and the instantaneous turning center position data; if the second distance data meets the distance threshold, then determining that the obstacle is within the effective collision area.

[0013] Optionally, the method also includes: if the longitudinal obstacle avoidance data is less than the preset obstacle avoidance distance threshold, then the collision detection result of the vehicle body area is determined to be a collision risk; based on the driving conditions, the collision detection result and the vehicle body area corresponding to the collision detection result, the collision position status of the vehicle body area is determined, and the collision position status is transmitted to the visualization terminal for display.

[0014] According to another aspect of the present invention, a vehicle obstacle avoidance processing device is provided, comprising:

[0015] The driving condition acquisition module is used to acquire the driving condition of the target vehicle at the current moment. The driving condition includes basic condition and non-baseline condition.

[0016] The obstacle avoidance data determination module is used to acquire the target vehicle's body information, key body point information, minimum turning radius, and obstacle information under baseline conditions, and to determine lateral obstacle avoidance data based on the target vehicle's body information and obstacle information; and / or, to determine longitudinal obstacle avoidance data based on the target vehicle's key body point information, minimum turning radius, and obstacle information, wherein the lateral obstacle avoidance data includes the rear axle turning radius and front axle heading angle; and the longitudinal obstacle avoidance data includes the obstacle avoidance distance.

[0017] The obstacle avoidance processing module is used to perform obstacle avoidance processing on the target vehicle based on lateral obstacle avoidance data and / or longitudinal obstacle avoidance data.

[0018] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0019] At least one processor; and

[0020] A memory that is communicatively connected to at least one processor; wherein,

[0021] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the vehicle obstacle avoidance processing method according to any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the vehicle obstacle avoidance processing method of any embodiment of the present invention.

[0023] The technical solution of this invention obtains the current driving conditions of the target vehicle, including basic and non-baseline driving conditions; obtains the vehicle's body information, key body point information, minimum turning radius, and obstacle information under the baseline driving conditions; determines lateral obstacle avoidance data based on the vehicle's body information and obstacle information; and / or determines longitudinal obstacle avoidance data based on the target vehicle's key body point information, minimum turning radius, and obstacle information, wherein the lateral obstacle avoidance data includes the rear axle turning radius and front axle heading angle; and the longitudinal obstacle avoidance data includes the obstacle avoidance distance; thus, it achieves the determination of lateral obstacle avoidance data and longitudinal obstacle avoidance data based on multi-dimensional data, ensuring vehicle obstacle avoidance from both lateral and longitudinal perspectives. The rationality and safety of the real-time path planning enable vehicles to flexibly cope with obstacles in different directions. Single or combined strategies can be selected based on actual conditions, effectively improving the reliability and efficiency of obstacle avoidance in complex road conditions and meeting the safety and real-time requirements of intelligent driving. Based on lateral obstacle avoidance data and / or longitudinal obstacle avoidance data, obstacle avoidance processing of the target vehicle is performed, achieving multi-dimensional dynamic obstacle avoidance through the synergistic or independent action of lateral and longitudinal obstacle avoidance data. Lateral data alone can accurately plan turning trajectories, while longitudinal data alone can control safe distances. The combination of the two forms a three-dimensional obstacle avoidance strategy, flexibly adapting to different working conditions. Data fusion enhances the scientific nature of decision-making, ensuring safe and smooth obstacle avoidance for the vehicle. This solution establishes a precise and dynamic decision-making data foundation by acquiring comprehensive information on driving conditions, vehicle body, and obstacles. The independent or collaborative determination of lateral and longitudinal obstacle avoidance data enables multi-dimensional and refined control of vehicle obstacle avoidance behavior. Based on the obstacle avoidance processing of these two types of data, it can flexibly adapt to different road and working conditions, enhancing the vehicle's ability to cope with complex scenarios. This not only improves the scientificity and reliability of obstacle avoidance strategies but also ensures that the vehicle can safely and efficiently avoid obstacles during dynamic driving, solving the problem of low obstacle avoidance efficiency and significantly improving the safety and stability of intelligent driving.

[0024] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a flowchart of a vehicle obstacle avoidance method provided in Embodiment 1 of the present invention;

[0027] Figure 2 This is a schematic diagram of the distribution of key points on a vehicle body as applicable to an embodiment of the present invention;

[0028] Figure 3 This is a schematic diagram of a vehicle's inner obstacle avoidance method applicable to an embodiment of the present invention;

[0029] Figure 4 This is a schematic diagram of a vehicle bypassing an obstacle on the outside, applicable to an embodiment of the present invention;

[0030] Figure 5 This is a flowchart of a vehicle obstacle avoidance method provided in Embodiment 2 of the present invention;

[0031] Figure 6 This is a schematic diagram of a vehicle longitudinal obstacle avoidance applicable to an embodiment of the present invention;

[0032] Figure 7 This is a schematic diagram of a vehicle longitudinal obstacle avoidance applicable to an embodiment of the present invention;

[0033] Figure 8 This is a schematic diagram of the structure of a vehicle obstacle avoidance device provided in Embodiment 3 of the present invention;

[0034] Figure 9 This is a schematic diagram of the structure of an electronic device that implements the vehicle obstacle avoidance and bypass processing method of the present invention. Detailed Implementation

[0035] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0036] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0037] Example 1

[0038] Figure 1 This is a flowchart of a vehicle obstacle avoidance method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations involving vehicle obstacle avoidance. This method can be executed by a vehicle obstacle avoidance device, which can be implemented in hardware and / or software. This vehicle obstacle avoidance device can be configured in electronic devices such as vehicle controllers. Figure 1 As shown, the method includes:

[0039] S110. Obtain the current driving conditions of the target vehicle, including basic conditions and non-baseline conditions.

[0040] The driving conditions can be specifically understood as the obstacle avoidance conditions of the target vehicle. Obstacle avoidance conditions include, but are not limited to, forward right turn, forward left turn, reverse right turn, and reverse left turn. Furthermore, based on the positional relationship of the obstacle relative to the target vehicle, each obstacle avoidance condition can be further divided into inner obstacle avoidance and outer obstacle avoidance, or left obstacle avoidance and right obstacle avoidance. Therefore, the driving conditions include, but are limited to, forward right turn inner obstacle avoidance, forward left turn inner obstacle avoidance, reverse right turn inner obstacle avoidance, reverse left turn inner obstacle avoidance, forward right turn outer obstacle avoidance, forward left turn outer obstacle avoidance, reverse right turn outer obstacle avoidance, and reverse left turn outer obstacle avoidance. Any of the above driving conditions can be set as the baseline condition, or the baseline condition can be set according to the direction of the horizontal and vertical axes of the constructed vehicle coordinate system. Optionally, the forward direction of the vehicle can be set as the positive direction of the horizontal axis of the vehicle coordinate system, and the left side of the vehicle can be set as the positive direction of the vertical axis of the vehicle coordinate system. In this case, the forward right turn inside obstacle avoidance and forward right turn outside obstacle avoidance can be set as baseline conditions, and other conditions can be set as non-baseline conditions. The specific setting of baseline and non-baseline conditions is based on the actual driving situation and is not limited here.

[0041] Specifically, the driving condition type of the target vehicle can be determined by a preset driving condition determination model based on the vehicle's operating information at the current moment. The vehicle operating information includes, but is not limited to, the steering wheel angle, gear status, and the relative position of obstacles to the target vehicle. The driving condition type is then matched with a preset set of benchmark driving conditions. If the match is successful, the driving condition of the target vehicle at the current moment is determined as the benchmark driving condition; otherwise, the driving condition of the target vehicle at the current moment is determined as a non-benchmark driving condition.

[0042] Optionally, obtaining the current driving condition of the target vehicle includes: determining a first driving condition of the target vehicle based on the steering wheel angle and gear position, wherein the first driving condition includes forward right turn, forward left turn, reverse right turn, and reverse left turn; determining a second driving condition of the target vehicle based on the relative positional relationship between the obstacle and the target vehicle, wherein the second driving condition includes inside obstacle avoidance and outside obstacle avoidance; and determining the target vehicle's driving condition based on the first driving condition, the second driving condition, and a preset benchmark driving condition list. The benchmark driving condition list can be understood as a pre-set list containing at least one driving condition type, used to determine whether the current driving condition is a benchmark driving condition. This benchmark driving condition list can be pre-set when developing algorithms for lateral obstacle avoidance data and longitudinal obstacle avoidance data.

[0043] Specifically, sensors can collect real-time steering wheel angle and gear position signals of the target vehicle. Based on preset logic, the direction of the steering wheel angle (left or right) and the gear position (drive or reverse) are determined to establish the first working condition. For example, a right turn with the steering wheel in drive is determined as a drive-right turn, and a left turn with the steering wheel in reverse is determined as a reverse-left turn. Simultaneously, radar, cameras, and other sensing devices are used to acquire the relative position information of obstacles and the target vehicle. The position of the obstacle relative to the vehicle's path is analyzed. If the obstacle is inside the vehicle's path, it is determined as an inside obstacle avoidance; if it is outside, it is determined as an outside obstacle avoidance, thus obtaining the second working condition. Finally, by combining the information from the first and second operating conditions and through logical combinations (such as based solely on the first operating condition, based solely on the second operating condition, or a combination of both), the current driving condition type of the target vehicle is determined to comprehensively reflect the actual operating status of the vehicle in steering, gear shifting, and obstacle avoidance scenarios. Then, the driving condition type is matched with a preset benchmark operating condition list. If the match is successful, the current driving condition of the target vehicle is determined to be the benchmark operating condition; if the match fails, the current driving condition of the target vehicle is determined to be a non-benchmark operating condition.

[0044] S120. Obtain the target vehicle's body information, key body point information, minimum turning radius, and obstacle information under reference conditions; determine lateral obstacle avoidance data based on the target vehicle's body information and obstacle information; and / or determine longitudinal obstacle avoidance data based on the target vehicle's key body point information, minimum turning radius, and obstacle information, wherein the lateral obstacle avoidance data includes the rear axle turning radius and front axle heading angle, and the longitudinal obstacle avoidance data includes the obstacle avoidance distance.

[0045] Specifically, vehicle body information refers to the physical structural parameters of the target vehicle, including but not limited to vehicle width and axle distance; key vehicle body point information refers to the coordinate data of key reference points on the vehicle body in the vehicle coordinate system, including but not limited to the center points of the front and rear axles, the four corner vertices of the vehicle body, the center of gravity, and the corner points of the rearview mirrors. These points serve as the benchmark for calculating the vehicle's spatial position, and key vehicle body points can be set according to actual needs, such as... Figure 2 The diagram shows the distribution of key points on the vehicle body. Points 0-13 are the set key points. The coordinate data of each key point in the vehicle coordinate system can be determined through vehicle information. More key points can be set according to different vehicle models or monitoring needs; this is not limited here. The minimum turning radius refers to the radius of the circle traced by the center plane of the outer steering wheel on the support plane when the vehicle is turning at its minimum stable speed with the steering wheel turned to its limit. This can be read from the vehicle control system. The obstacle information under the baseline operating condition is the position coordinates of obstacles in a preset standard operating scenario, serving as an environmental reference for vehicle obstacle avoidance analysis. This information can be obtained through position acquisition equipment. The rear axle turning radius refers to the radius of the trajectory of the rear axle center around the steering center when the vehicle turns. It determines the range of the vehicle's rear wheel steering trajectory and directly affects whether the rear wheels can avoid obstacles when the vehicle is going around them laterally. The front axle heading angle is the angle between the vehicle's front axle centerline and the direction of travel. It is used to characterize the steering angle of the front wheels. By adjusting this angle, the vehicle's obstacle avoidance trajectory can be planned to ensure that the vehicle body can smoothly bypass lateral obstacles. The obstacle avoidance distance refers to the safe driving distance that the vehicle needs to maintain in the longitudinal direction of travel to avoid collision with obstacles in front.

[0046] Specifically, the system acquires vehicle body information, key body point information, and minimum turning radius parameters of the target vehicle through onboard sensors and the vehicle control system, while simultaneously retrieving obstacle information under baseline conditions. If lateral obstacle avoidance data is required, the system uses a lateral obstacle avoidance data calculation method to calculate the required rear axle turning radius and front axle heading angle based on the vehicle body information and obstacle information. If longitudinal obstacle avoidance data is required, the system uses a longitudinal obstacle avoidance data calculation method based on the key body point information, minimum turning radius, and longitudinal distance to the obstacle to calculate the minimum obstacle avoidance distance required for the vehicle to avoid a collision, i.e., the longitudinal safety buffer distance. The entire process can be performed using either lateral obstacle avoidance data or longitudinal obstacle avoidance data alone, or a combination of both can be used for comprehensive judgment.

[0047] In this embodiment, by comprehensively considering the vehicle's own characteristics and the obstacle environment, the determination of lateral obstacle avoidance data and longitudinal obstacle avoidance data is made more consistent with the actual movement law of the vehicle, thereby improving the accuracy and reliability of the obstacle avoidance strategy. The independent calculation and synergistic effect of lateral and longitudinal obstacle avoidance data can cover obstacle avoidance needs in different dimensions, enhance the vehicle's obstacle avoidance ability in complex road conditions, and ensure driving safety. The obstacle information analysis based on the baseline working condition can provide a standardized basis for obstacle avoidance decision-making for the intelligent driving system, which is convenient for system optimization and scenario expansion, and improves versatility.

[0048] Optionally, the baseline condition is inner obstacle avoidance in the first rotation direction. The vehicle body information includes the vehicle width and axle distance, and the obstacle information includes the position data of multiple obstacle corner points. Based on the target vehicle's vehicle body information and obstacle information, lateral obstacle avoidance data is determined, including: determining the turning radius corresponding to each obstacle corner point based on the position data of each obstacle corner point and the vehicle body width; determining the angle data corresponding to each obstacle corner point based on the rear axle turning radius and axle distance corresponding to each obstacle corner point; and determining the lateral obstacle avoidance data based on the turning radius and angle data corresponding to each obstacle corner point.

[0049] The first turning direction refers to a specific turning direction of the target vehicle, which can be either a left turn or a right turn, depending on the actual situation. The obstacle information specifically refers to the position information of each corner point of the obstacle. For example, detected obstacles can be projected onto the vehicle's coordinate system and represented by a rectangle. The four corner points of the rectangle represent the corner points of the obstacle. That is, each obstacle information includes information on multiple obstacle corner points, and the obstacle information can be composed of the coordinate data of multiple obstacle corner points.

[0050] Specifically, vehicle and obstacle information is acquired under the baseline condition of an inner obstacle avoidance scenario with the first rotation direction as the reference condition. Next, for each obstacle corner, based on its position data and vehicle width, the turning radius corresponding to that corner is calculated using geometric relationships; this is the rotation radius the rear axle must satisfy when the vehicle avoids the obstacle. Then, combining the axle distance and the rear axle turning radius corresponding to each obstacle corner, trigonometric functions are used to calculate the angle data corresponding to each obstacle corner. Finally, the maximum value among the turning radii corresponding to each obstacle corner is selected as the rear axle turning radius, and the minimum value among the angle data corresponding to each obstacle corner is selected as the front axle heading angle. The rear axle turning radius and front axle heading angle are then set as the lateral obstacle avoidance data. Figure 3 The diagram illustrates a vehicle obstacle avoidance maneuver. The vehicle's coordinate system is based on the rear axle center as the origin, with the positive x-axis perpendicular to the rear axle and pointing towards the front of the vehicle, and the positive y-axis along the rear axle and pointing towards the left side of the vehicle. In the diagram, 'r' represents the turning radius. The angle yaw between the side formed by the obstacle corner point A and the instantaneous turning center point B, and the side formed by the rear axle center point o and the instantaneous turning center point B, is the corresponding front axle heading angle. The rear axle turning radius 'r' and the front axle heading angle 'yaw' are calculated as follows:

[0051]

[0052]

[0053] Where (x, y) represents the position data of the obstacle corner points in the vehicle coordinate system, d is half the length of the rear axle, and h is the wheelbase. The coordinates of each obstacle corner point are calculated using Formula 1 and Formula 2 to obtain r and yaw values ​​for the inner obstacle bypass condition. Based on the relative relationship, the maximum r and minimum yaw values ​​for this condition are taken to obtain the required r and yaw values ​​for bypassing the inner obstacle.

[0054] In this embodiment, the obstacle avoidance scenario is transformed into a geometric problem through quantitative calculation to improve data accuracy. At the same time, the turning radius and angle data are integrated to characterize the obstacle avoidance requirements from both distance and direction dimensions. It can also calculate and synthesize the results for multiple obstacle corners to adapt to complex contours. Extreme value screening ensures safety redundancy. Furthermore, the data source is easy to obtain and the calculation logic is easy to integrate into engineering.

[0055] Optionally, the baseline condition is obstacle avoidance on the outside in the first rotation direction; determining lateral obstacle avoidance data based on the target vehicle's body information and obstacle information includes: acquiring a turning radius calculation model, wherein the turning radius calculation model includes a mathematical relationship between turning radius parameters, two-dimensional coordinate parameters of the overhanging corner point, and linear parameters, and the linear parameters are the linear parameters of the obstacle edge lines obtained by fitting the position data of adjacent obstacle corner points; acquiring the two-dimensional coordinate data of the target overhanging corner point and the linear parameter values ​​corresponding to multiple obstacle edge lines, and substituting them into the turning radius calculation model to obtain the turning radius corresponding to each obstacle edge line; determining the angle data corresponding to each obstacle edge line based on the turning radius corresponding to each obstacle edge line and the axle distance; and determining lateral obstacle avoidance data based on the turning radius and angle data corresponding to each obstacle edge line.

[0056] In this embodiment, in the obstacle avoidance scenario on the outer side in the first rotation direction, in addition to considering the obstacle corner points, it is also necessary to consider whether the outer corner points of the vehicle body have tangent coordinates on the obstacle boundary line segment, thereby determining whether there is an outer collision risk. Therefore, it is necessary to calculate the lateral obstacle avoidance distance based on the vehicle's outer overhanging corner point information and obstacle corner point data. The overhanging corner points can be specifically understood as the four corner points of the vehicle body contour. All four angles can be used as target overhanging corner points. In practical applications, along the vehicle's driving direction, any one of the two overhanging corner points on the outer side of the vehicle body is set as the target overhanging corner point. If the obstacle is in front of the vehicle, the front overhanging corner point can be set as the target overhanging corner point. If the obstacle is located near the rear overhanging corner point, the rear overhanging corner point is set as the target overhanging corner point.

[0057] Specifically, in the baseline obstacle avoidance scenario with the first rotation direction as the reference condition, the tangent point information of the target overhang point relative to the obstacle edge line is determined based on the target vehicle's body information and obstacle information. This is achieved by acquiring the target vehicle's body information and obstacle information. Then, a turning radius calculation model is obtained. This model describes the relationship between the turning radius parameter, the two-dimensional coordinate parameters of the vehicle's overhang point (such as the front or rear overhang point), and the linear parameters obtained by fitting adjacent obstacle corner points (i.e., the obstacle edge line equations) through mathematical formulas. Next, real-time coordinate data of the target overhang point is extracted, and linear fitting is performed on the adjacent corner points of each obstacle edge line to obtain the corresponding linear parameter values. These data are then substituted into the model to calculate the turning radius required for the vehicle to navigate around each obstacle edge line. Subsequently, combined with the axle distance, the angle data corresponding to each obstacle edge line, such as the front axle heading angle, is calculated using trigonometric functions. Finally, the maximum value among the turning radii corresponding to each obstacle corner point is selected as the rear axle turning radius, and the minimum value among the angle data corresponding to each obstacle corner point is selected as the front axle heading angle. The rear axle turning radius and the front axle heading angle are set as lateral obstacle avoidance data to guide the vehicle's obstacle avoidance path planning.

[0058] In this embodiment, the vehicle wheelbase h, front overhang F, rear overhang R, and vehicle width 2d are determined based on the target vehicle's body information. The front overhang is the horizontal distance from the front of the vehicle to the front axle, and the rear overhang is the horizontal distance from the rear axle to the rear of the vehicle. The corner coordinates of the obstacle edges (x1, y1) and (x2, y2) are determined. Based on the relationship that the distance from the vehicle's overhang corner (X, Y) to the center of the circle is equal to the distance from the tangent to the center of the circle, a system of equations is solved to obtain the turning radius r, and thus the tangent coordinates (x0, y0). The calculation process for the turning radius and angle data corresponding to each obstacle edge is as follows:

[0059] The equation of the line containing the obstacle's edge is calculated from the coordinates of the corner points (x1, y1) and (x2, y2): y = kx + b; (Formula 3)

[0060] Based on the vehicle body information, the coordinates of the outer rear overhang corner point are determined as (-R, d), and the coordinates of the outer front overhang corner point are (h+F, d), which can be uniformly denoted as (X, Y). R is the rear overhang length, i.e., the horizontal distance between the rear axle and the rear of the vehicle, and F is the front overhang length, i.e., the horizontal distance between the front axle and the front of the vehicle. Let the center of the circle be (0, r), where r can be positive or negative; r is positive when the vehicle turns left and negative when it turns right. Based on the equality of distances, an equation is established:

[0061]

[0062] Simplifying formula (4) yields the equation for r:

[0063] Ar 2 +Br+C=0;(Formula 5)

[0064] The solution yields:

[0065] In formula (6), the turning radius is used as a calculation model. A, B, and C refer to the relationships between one or more parameters in the two-dimensional coordinate parameters (X,Y) and linear parameters (k,b) of the overhang point. Based on the angle data corresponding to the turning radius and axle distance, the angle data can be calculated using formula (2).

[0066] In this embodiment, after obtaining the turning radius corresponding to each obstacle edge, a validity analysis is performed on the obtained turning radius for any obstacle edge. If the turning radius corresponding to the obstacle edge is valid, the tangent point information (x) of the target overhang point relative to the obstacle edge is further determined. n ,y n If the tangent point is valid, there is no need to modify the turning radius. If the tangent point is invalid, the tangent point information needs to be readjusted. That is, the corner point of the obstacle closest to the target overhang cantilever point can be selected as the corrected tangent point (x). n ,y nBased on the corrected tangent point information and the two-dimensional coordinate data of the target overhang point, the target turning radius corresponding to the obstacle edge is determined, such as... Figure 4 The diagram shown illustrates a vehicle's obstacle avoidance maneuver, specifically by calculating the corner points (x, y) of the obstacle. n ,y n The perpendicular bisector L of the chord connecting the rear overhang point (X,Y) is used to calculate the y-value, which is the corrected turning radius. Since the turning center must lie on the perpendicular bisector L, the value of y is substituted into the line x=0 where the turning center is located. When r is negative, it means that the turning center is on the right side of the vehicle; when r is positive, it means that the turning center is on the left side of the vehicle. After obtaining r, it is substituted into formula (3) to calculate the yaw value. Optionally, the validity analysis of the turning radius includes: the validity of r is judged based on whether the steering center is within the calculation range of the driving condition. For example, when the steering center represented by the r value is greater than the applicable range of the driving condition, which can be understood as the current driving range of the vehicle, or when the steering center represented by the r value is on the other side of the X-axis, it is set as an invalid value r; otherwise, it is an effective value r. The validity check of the tangent point information includes: if the tangent point exists within the line segment connecting the corner points (x1, y1) and (x2, y2) of the obstacle, the tangent point information is determined to be valid; if it is outside the line segment, the tangent point information is determined to be invalid.

[0067] In this embodiment, before determining the tangent point information, unsolvable conditions can be excluded first. The method includes: for the tangent point calculation of the outer rear overhang corner, when the distance between the intersection of the obstacle edge line and the straight line where the outer edge line of the vehicle body and the Y axis are located is greater than the rear overhang R, formulas (3)-(6) have no solution and are not applicable. Moreover, there will be no collision with the obstacle at this time, so this condition is discarded. For the tangent point calculation of the outer front overhang corner, when the y value of the obstacle corner point coordinates is not less than the straight line where the outer edge line of the vehicle body is located, y = d, or the x value is not greater than the straight line where the front overhang of the vehicle body is located, x = h + F, the obstacle will not collide with the intersection of the front overhang, so this condition is discarded.

[0068] In this embodiment, the turning radius can be accurately calculated through a mathematical model to avoid collisions. The dynamic adaptability based on the linear parameters of the real-time corner fitting can cope with complex obstacles. The calculation method combining linear fitting and model is efficient and suitable for real-time control. The analysis of multiple edge lines can handle multi-boundary scenarios. Moreover, the model parameters are easy to obtain and the algorithm is easy to deploy in engineering.

[0069] Optionally, before determining the longitudinal obstacle avoidance data based on the target vehicle's key point information, minimum turning radius, and obstacle information, the method further includes: determining whether the obstacle is within the effective collision area based on the obstacle information and the vehicle's key point information; if the obstacle is within the effective collision area, then proceeding to determine the longitudinal obstacle avoidance data; if the obstacle is not within the effective collision area, then not proceeding to determine the longitudinal obstacle avoidance data.

[0070] Specifically, the system first uses onboard sensors to collect the coordinates of key points on the target vehicle body, as well as the location information of obstacles, and obtains the vehicle's minimum turning radius data. Next, based on the key point information, a vehicle contour model is constructed. The spatial relationship between the obstacle's location and the vehicle contour is compared to determine whether the obstacle is within the effective collision area that the vehicle's driving path might reach. If the obstacle is determined to be within this area, longitudinal obstacle avoidance data, such as obstacle avoidance distance, is further calculated based on the vehicle body key point information, minimum turning radius, and obstacle information. If the obstacle is determined not to be within the effective collision area, the system stops executing the longitudinal obstacle avoidance data calculation process and does not perform any further processing.

[0071] In this embodiment, by pre-screening, the calculation of invalid obstacles is skipped, unnecessary data processing is reduced, the system's computational load is lowered, and computational efficiency is improved; by focusing on obstacles that may cause collisions, computational resources are concentrated on key scenarios, optimizing the timeliness and accuracy of obstacle avoidance decisions and enhancing the pertinence of decisions; by avoiding mishandling of non-threatening obstacles, the probability of system false triggering is reduced, ensuring the stability and comfort of the driving process and reducing the risk of misjudgment.

[0072] Optionally, the method for determining whether an obstacle is within the effective collision area includes one or more of the following: determining the effective collision area range based on vehicle body key point information; if the obstacle information meets the effective collision area range, then the obstacle is determined to be within the effective collision area; acquiring the instantaneous turning center position data of the target vehicle; determining second distance data based on the obstacle information and the instantaneous turning center position data; determining a distance threshold based on the vehicle body key point information and the instantaneous turning center position data; if the second distance data meets the distance threshold, then the obstacle is determined to be within the effective collision area. It should be noted that when lateral obstacle avoidance is not possible, space should be utilized as much as possible to travel to the limit position in the current direction, increasing the effective space for the next path change. In similar situations, reasonable obstacle avoidance of the vehicle's longitudinal collision distance is required. This can be achieved by calculating the key points of the vehicle body boundaries that need to be included in subsequent calculations and calculating the effective area of ​​the vehicle body that can collide with the vehicle body through the current driving direction; determining whether longitudinal collision avoidance is needed based on obstacle information; when longitudinal collision avoidance is needed, outputting the collision point information of the minimum collision distance for each vehicle body boundary; and performing longitudinal collision avoidance according to the calibrated or reserved safety distance. The input structure for drivable area information under the current driving conditions includes, but is not limited to: drivable area information radiating outwards from the vehicle's geometric center or rear axle center until it intersects with the obstacle's edge; drivable area information radiating outwards from a ray perpendicular to the vehicle's outer edge until it intersects with the obstacle's edge; and drivable area information radiating outwards from the vehicle's outer edge with a fixed step size until it intersects with the obstacle. Through the above structure, environmental obstacle information can be transformed into the vehicle's drivable spatial boundary, providing a basic input for determining whether obstacle avoidance processing is required.

[0073] Specifically, based on key vehicle body information, the effective collision zone of the vehicle is constructed through geometric calculations, such as a polygonal area formed by extending the vehicle body outline outwards by a certain safety distance. The position and size of obstacles are compared with this area; if an obstacle is completely or partially within this area, it is determined to be within the effective collision zone. Alternatively, the instantaneous turning center position of the target vehicle can be calculated using sensor data such as vehicle steering angle and wheel speed, combined with the minimum turning radius. The second distance data from the obstacle to the instantaneous turning center, and the distance from key vehicle body points to the instantaneous turning center, are calculated separately, and the minimum value is taken as a distance threshold. If the second distance data is less than or equal to the distance threshold, it indicates that the obstacle may affect the vehicle's turning path, thus determining that it is within the effective collision zone. These two judgment methods can be used individually or combined complementaryly to improve accuracy.

[0074] In this embodiment, the method for determining the effective collision area based on key points of the vehicle body is intuitive and computationally simple, enabling rapid identification of near-range obstacle threats. By using the instantaneous turning center and distance threshold judgment method, the vehicle's steering characteristics are fully considered, effectively identifying potential collision risks during cornering and improving judgment accuracy in complex conditions. The combined use of these two methods balances computational efficiency and judgment comprehensiveness, reducing the probability of missed or false judgments, enhancing the reliability and safety of vehicle obstacle avoidance decisions, and adapting to different driving scenarios and obstacle distribution conditions.

[0075] S130. Perform obstacle avoidance processing on the target vehicle based on lateral obstacle avoidance data and / or longitudinal obstacle avoidance data.

[0076] Specifically, the system first acquires the target vehicle's lateral obstacle avoidance data (rear axle turning radius, front axle heading angle, etc.) and longitudinal obstacle avoidance data (avoidance distance). If only lateral obstacle avoidance data is used, the system will adjust the vehicle's steering system based on the rear axle turning radius and front axle heading angle, controlling the steering wheel angle and steering speed to ensure the vehicle completes the lateral obstacle avoidance maneuver with a safe radius. If only longitudinal obstacle avoidance data is used, the vehicle will adjust its speed based on the obstacle avoidance distance, accelerating, decelerating, or braking to ensure safe passage before longitudinal contact with the obstacle. If both lateral and longitudinal obstacle avoidance data are used simultaneously, the system will comprehensively analyze both to formulate a composite obstacle avoidance strategy that takes into account both steering and speed adjustments. For example, it may control the vehicle speed while turning, enabling the vehicle to safely and efficiently complete obstacle avoidance maneuvers under complex conditions.

[0077] In this embodiment, horizontal and vertical data can be used individually or in combination. Depending on the scenario, horizontal and vertical obstacle avoidance data can be used individually or in combination to avoid biased decision-making. Horizontal and vertical obstacle avoidance data provide reliable data support for precise control of steering and vehicle speed. It fits the spatial relationship of obstacles, can switch data dimensions as needed, and integrate and process complex working conditions to improve the vehicle's obstacle avoidance ability and pass rate.

[0078] The technical solution of this embodiment obtains the current driving conditions of the target vehicle, including basic and non-baseline driving conditions; obtains the vehicle body information, key point information, minimum turning radius, and obstacle information under the baseline driving conditions; determines lateral obstacle avoidance data based on the vehicle body information and obstacle information; and / or determines longitudinal obstacle avoidance data based on the key point information, minimum turning radius, and obstacle information of the target vehicle, wherein the lateral obstacle avoidance data includes the rear axle turning radius and front axle heading angle; the longitudinal obstacle avoidance data includes the obstacle avoidance distance; and performs obstacle avoidance processing on the target vehicle based on the lateral obstacle avoidance data and / or the longitudinal obstacle avoidance data. This solution establishes a precise and dynamic decision-making data foundation by acquiring comprehensive information on driving conditions, vehicle body, and obstacles. The independent or collaborative determination of lateral and longitudinal obstacle avoidance data enables multi-dimensional and refined control of vehicle obstacle avoidance behavior. Based on the obstacle avoidance processing of these two types of data, it can flexibly adapt to different road and working conditions, enhancing the vehicle's ability to cope with complex scenarios. This not only improves the scientificity and reliability of obstacle avoidance strategies but also ensures that the vehicle can safely and efficiently avoid obstacles during dynamic driving, solving the problem of low obstacle avoidance efficiency and significantly improving the safety and stability of intelligent driving.

[0079] Example 2

[0080] Figure 5 This is a flowchart of a vehicle obstacle avoidance method provided in Embodiment 2 of the present invention. The method in this embodiment is a further optimization of the method in the above embodiments. Optionally, the effective collision area of ​​the vehicle under a reference condition and the minimum turning radius of the target vehicle at the current moment are obtained from the vehicle's key point information. The effective collision area includes multiple vehicle segments, each segment being formed by connecting at least two key points sequentially. First distance data is determined based on the key point position information, obstacle information, and minimum turning radius on the vehicle segments. The first distance data includes the distance data of multiple obstacle corner points relative to the instantaneous turning center of the target vehicle. First angle data is determined based on the key point position information, obstacle information, minimum turning radius, and first distance data on the vehicle segments. The first angle data includes the angle data corresponding to multiple obstacle corner points, each angle being the angle formed by the obstacle corner point and the vehicle collision point relative to the instantaneous turning center of the target vehicle. The obstacle avoidance distance for each obstacle corner point is determined based on the first distance data and the first angle, and the minimum obstacle avoidance distance among the obstacle corner points is selected as the obstacle avoidance data for the vehicle segments. Figure 5 As shown, the method includes:

[0081] S510: Obtain the current driving conditions of the target vehicle, including basic conditions and non-baseline conditions.

[0082] S520: Obtain the target vehicle's body information, key body point information, minimum turning radius, and obstacle information under baseline conditions. Based on the target vehicle's body information and obstacle information, determine lateral obstacle avoidance data, including the rear axle turning radius and the front axle heading angle.

[0083] S530: Obtain the effective collision area of ​​the vehicle body under the benchmark condition from the key point information of the vehicle body, and obtain the minimum turning radius of the target vehicle at the current moment.

[0084] The effective collision area comprises multiple vehicle body segments, each formed by connecting at least two key vehicle body points sequentially. It should be noted that, for example... Figure 2 This diagram illustrates the distribution of key points on a vehicle body. The effective collision area varies depending on the driving conditions. A mapping relationship between driving conditions and the effective collision area can be pre-defined. For example, when the vehicle is moving forward and turning right, the effective collision area is: Point0-Point6, Point7-Point9, Point11-Point12. When the vehicle is moving backward and turning right, the effective collision area is: Point1-Point2, Point12-Point0, Point6-Point11. When the vehicle is moving forward and turning left, the effective collision area is: Point5-Point11, Point2-Point4, Point13-Point0. When the vehicle is moving backward and turning left, the effective collision area is: Point9-Point10, Point11-Point13, Point0-Point5.

[0085] Specifically, the key point information calculation model is invoked, and the vehicle body information is input into the key point information calculation model to obtain the position information of each key point in the vehicle body coordinate system. For example, the input information required for key point calculation includes: rear overhang R, vehicle length L, vehicle width D = 2d, rearview mirror extension length L_Mirror based on the vehicle body boundary, rearview mirror width D_Mirror based on the vehicle body boundary, and longitudinal distance d_Mirror2R from the rear edge of the rearview mirror to the rear bumper based on the vehicle body boundary. The key point information output results are: x_Point0 = 0; y_Point0 = -d; x_Point1 = d_Mirror2R - R; y_Point1 = -d; x_Point2 = d_Mirror2R - R; y_Point2 = -(d + L_Mirror); x_Point3 = d_Mirror2R - R + D_Mirror; y_Point3 = -(d + L_Mirror); x_Point4 = d_Mirror2R - R + D_Mirror; y_Point4 = -d; x_Point5 = LR;

[0086] y_Point5=-d; x_Point6=LR; y_Point6=d;

[0087] x_Point7=d_Mirror2R-R+D_Mirror; y_Point7=d; x_Point8=d_Mirror2R-R+D_Mirror; y_Point8=(d+L_Mirror);

[0088] x_Point9=d_Mirror2R-R; y_Point9=(d+L_Mirror);

[0089] x_Point10 = d_Mirror2R-R; y_Point10 = d; x_Point11 = 0; y_Point11 = d; x_Point12 = -R; y_Point12 = d; x_Point13 = -R; y_Point13 = -d; It should be noted that the x-coordinates of Point0 and Point11 are not entirely on the straight line where the rear axle is located. On vehicles with rear-wheel steering, the x-coordinates of Point0 and Point11 can change with the x-coordinate of the straight line where the turning center is located. According to pre-set rules, the vehicle body is divided into multiple regions, each region consisting of at least two key vehicle body points connected sequentially. The mapping relationship between driving condition type and vehicle collision effective area is called, and the driving condition type corresponding to the benchmark condition is matched with the mapping relationship to determine the vehicle collision effective area under the benchmark condition. At the same time, the steering wheel angle information is obtained by using the vehicle steering system sensors, combined with the vehicle wheelbase, track width and other design parameters, and the minimum turning radius of the target vehicle at the current moment is calculated by the kinematic model. Alternatively, the minimum turning radius parameter can be directly read from the vehicle control system. The entire process involves sensor data acquisition and mathematical model calculations to quickly and accurately obtain the required key data.

[0090] In this embodiment, by dividing the vehicle body into multiple segments to determine the effective collision area, the collision-prone parts of the vehicle can be covered in detail and comprehensively, providing accurate reference for obstacle avoidance decisions. The minimum turning radius at the current moment can be calculated in real time, which can dynamically reflect the steering performance of the vehicle under different driving conditions. This allows the vehicle to formulate a reasonable path based on its own steering ability when avoiding obstacles, which helps to improve the response speed and reliability of the vehicle obstacle avoidance system and effectively ensure driving safety.

[0091] S540. For each vehicle body area, determine the first distance data based on the key point location information, obstacle information and minimum turning radius on the vehicle body area.

[0092] The first distance data includes the distance data of multiple obstacle corner points in the obstacle information relative to the instantaneous turning center of the target vehicle.

[0093] Specifically, for each segment of the vehicle body, based on the location information of key points on that segment and the information of multiple obstacle corners from the obstacle information, the straight-line distance from each obstacle corner to the instantaneous turning center can be calculated using spatial geometric distance formulas. These distance data collectively constitute the first distance data. The formula for calculating the distance corresponding to any obstacle corner in the first distance data is as follows:

[0094]

[0095] Where, r objThe distance between the obstacle's coordinates and the instantaneous turning center of the target vehicle is given by (x, y), where (x, y) represents the obstacle's coordinates detected within the drivable area; r is the minimum turning radius along the vehicle's longitudinal axis, a vector value aligned with the vehicle's coordinate system; Point(n) represents information about any key point on the vehicle body, where 1 ≤ n ≤ 13. For example... Figure 6 The diagram shows a vehicle's longitudinal obstacle avoidance.

[0096] In this embodiment, the distance from the corner of the obstacle to the instantaneous turning center is used as the core data to accurately quantify the degree of proximity of the vehicle to the obstacle during the turning process, providing an intuitive basis for risk assessment. By integrating key points of the vehicle body, obstacle information and vehicle steering characteristics, distance data is constructed from multiple dimensions to avoid the limitations of single-perspective judgment and enhance the reliability of obstacle avoidance decisions.

[0097] S550 determines the first included angle data based on the key point location information, obstacle information, minimum turning radius and first distance data on the vehicle body area.

[0098] The first included angle data includes included angle data corresponding to multiple obstacle corner points. Each included angle is the angle formed by the obstacle corner point and the collision point of the vehicle body relative to the instantaneous turning center of the target vehicle.

[0099] Specifically, for each vehicle segment, based on the key point location information on that segment, as well as the corner information of multiple obstacles, the minimum turning radius, and the first distance data, the angle formed by each obstacle corner and the vehicle collision point is calculated using the instantaneous turning center as the vertex, according to the principles of trigonometric functions. This yields the first angle data corresponding to multiple obstacle corners, thus quantifying the spatial angular relationship between the vehicle and obstacles. The formula for calculating the angle corresponding to any obstacle corner in the first angle data is as follows:

[0100]

[0101] Where α is an auxiliary angle, as referenced Figure 6 The diagram shows a longitudinal obstacle avoidance method.

[0102] In this embodiment, by calculating the included angle data, the spatial angular relationship between the vehicle and the obstacle is accurately quantified, intuitively reflecting the direction and degree of collision risk, which helps to improve the accuracy of risk assessment. Combined with real-time updated vehicle body and obstacle information and minimum turning radius, it can adapt to different driving conditions and obstacle layouts, improving the accuracy of obstacle avoidance decisions in complex scenarios. By integrating multi-dimensional data such as key vehicle body points, obstacle positions, and vehicle steering characteristics, a comprehensive obstacle avoidance analysis model is constructed to avoid the limitations of single data. The quantified included angle data facilitates rapid analysis and judgment by the system, providing direct basis for path planning and steering control, and enhancing the timeliness and reliability of obstacle avoidance strategies.

[0103] S560. Based on the first distance data and the first included angle, determine the obstacle avoidance distance for each obstacle corner point, and select the minimum obstacle avoidance distance among the obstacle avoidance distances for each obstacle corner point as the obstacle avoidance data for the vehicle body area.

[0104] Specifically, based on the acquired first distance data and first included angle data, the obstacle avoidance distance corresponding to each obstacle corner is calculated through multiplication. This is the minimum safe distance that the vehicle needs to reserve to avoid colliding with that corner. The formula for calculating the obstacle avoidance distance Distance for each obstacle corner is as follows:

[0105] Distance = r obj θ; (Formula 10)

[0106] Next, the obstacle avoidance distances for all obstacle corners are compared one by one, and the obstacle avoidance distance with the smallest value is selected as the final obstacle avoidance data for that vehicle area, providing a key basis for subsequent obstacle avoidance decisions.

[0107] For example, when the baseline condition is a vehicle moving forward and turning right, the effective collision areas are: Point0-Point6, Point7-Point9, and Point11-Point12. For the longitudinal obstacle avoidance data of the Point0-Point1 vehicle area: substitute the obstacle corner position information and the lowest turning radius into formulas (7)-(10), replace the information of x_Point(n) with the coordinate data of point0, and select the minimum value as the collision distance in this area. The Point1-Point2 area is the rear edge of the rearview mirror in the direction of travel, and will not collide due to the movement of the direction of travel, so it can be discarded. The Point2-Point3 area is the side edge of the rearview mirror in the direction of travel, and will be subject to scraping risk due to the movement of the direction of travel, so the collision distance needs to be calculated. The calculation method is the same as that of the Point0-Point1 area. It is only necessary to replace the information of x_Point(n) with the coordinate data of Point2 to calculate the minimum collision distance of the Point2-Point3 area. The Point3-Point4 area represents the front edge of the rearview mirror in the direction of travel, and is at risk of collision due to movement in that direction; therefore, collision distance calculation is necessary. Figure 7 The diagram shown illustrates a vehicle's longitudinal obstacle avoidance mechanism. Figure 7 It can be seen that the relative direction between the corner point of the obstacle and the key point Point3 of the vehicle changes. At this time, the following formula (11) can be used to replace formula (9):

[0108]

[0109] The obstacle avoidance distance is calculated by combining formulas (7), (8), (10), and (11). The collision distance calculation for the Point4-Point5 region is the same as that for the Point0-Point1 region. Substitute x, y, and r directly into formulas (8), (9), (10), and (11), and after taking the smallest value of all collision distances, the collision distance for the Point4-Point5 region can be obtained. The collision distance calculation for the Point5-Point6 region is the same as that for the Point2-Point3 region. Substitute x, y, and r directly into formulas (8), (9), and (11), and replace the information of key point Point3 in formula 12 with the information of key point Point5 and substitute them into the calculation. After taking the smallest value of all collision distances, the collision distance for the Point5-Point6 region can be obtained. The collision distance calculation for the Point7-Point8 region is the same as that for the Point2-Point3 region. x, y, and r are directly substituted into formulas (8), (9), and (11). The information of key point Point3 in formula 12 is replaced with the information of key point Point7, and then substituted into the calculation. After taking the smallest of all collision distance values, the collision distance for the Point7-Point8 region can be obtained. For the Point11-Point12 region, the calculation of α and θ will differ due to the different positions of the obstacle coordinates. The appropriate calculation method for α and θ can be selected based on the actual situation. Therefore, the calculation of θ needs to be discussed in two cases: When the x-value of the obstacle is greater than or equal to the x-value of Point11, the following formula (12) is used to calculate θ:

[0110]

[0111] When the x-value of the obstacle is less than the x-value of Point11, θ is calculated using the following formula (13):

[0112]

[0113] Under the baseline condition, the first distance data is determined sequentially based on the key point location information, obstacle information, and minimum turning radius on the vehicle body area. The first included angle data is also determined based on the same key point location information, obstacle information, minimum turning radius, and first distance data, thus obtaining the obstacle avoidance distance for each vehicle body area. In the forward right turn scenario, the collision distance calculation method for different collision areas is optimized, discarding negligible areas in the opposite direction of travel, accurately outputting the remaining collision distance, while simultaneously improving computational efficiency and reducing computational load. Finally, based on the collision distance output for each area, the remaining minimum collision distance in the forward right turn scenario can be determined, and whether stopping to avoid a collision is necessary.

[0114] For example, the baseline condition can also be a vehicle reversing and turning right. Under this condition, the effective collision area matching the vehicle reversing and turning right is obtained. For any body segment area in the effective collision area, the obstacle avoidance distance is calculated based on the key body point information, obstacle corner point information and minimum turning radius (or the coordinate data of the vehicle's instantaneous turning center in the body coordinate system) in the segment area. This yields the minimum obstacle avoidance distance in each body segment area, which provides a reliable basis for adjusting the subsequent vehicle trajectory and improves the vehicle's obstacle avoidance ability and pass rate.

[0115] In this embodiment, by combining distance and angle data, the obstacle avoidance distance of each obstacle corner point is accurately calculated from both spatial position and angular relationship dimensions, avoiding the one-sidedness of collision risk assessment; by selecting the minimum obstacle avoidance distance as representative data of the vehicle body area, the decision-making logic is simplified, and a clear reference can be quickly provided for vehicle obstacle avoidance control; using the minimum obstacle avoidance distance as a standard, the most stringent safety boundary is reserved for the vehicle, so that obstacle avoidance can be achieved as much as possible even in narrow spaces, effectively reducing the possibility of collision and improving the driving safety factor; this method does not depend on specific scenarios or vehicle types, is applicable to various driving conditions and obstacle distribution situations, and has strong versatility.

[0116] Based on the above embodiments, the method for obtaining obstacle information under the reference working condition includes: when the target vehicle is in a non-reference working condition, spatially transforming the obstacle information under the non-reference working condition to obtain the transformed position information under the reference working condition corresponding to the non-reference working condition, and updating the obstacle information based on the transformed position information; the method further includes: inverting the lateral obstacle avoidance data and / or longitudinal obstacle avoidance data to obtain the lateral obstacle avoidance data and / or longitudinal obstacle avoidance data under the non-reference working condition.

[0117] Specifically, when the target vehicle is in a non-baseline operating condition, the original position information of the obstacle is acquired. Then, according to preset spatial transformation rules (such as vehicle coordinate system transformation and kinematic model), the original position information of the obstacle is mapped to the corresponding baseline operating condition to obtain transformed position information. This is used to update the obstacle information to meet the requirements of the baseline operating condition analysis. For example, the position information of the obstacle is symmetrically transformed relative to the X-axis of the vehicle coordinate system to obtain the transformed position data of the obstacle. After calculating the lateral obstacle avoidance data and / or longitudinal obstacle avoidance data under the baseline operating condition, the data is inverted based on the differences between the non-baseline operating condition and the baseline operating condition (such as opposite steering direction and driving direction) to obtain lateral obstacle avoidance data and / or longitudinal obstacle avoidance data applicable to the non-baseline operating condition, providing a basis for the vehicle's obstacle avoidance decision under the non-baseline operating condition.

[0118] In this embodiment, obstacle information under non-baseline conditions is unified to the baseline condition standard through spatial transformation, which facilitates data processing using mature baseline condition analysis models and reduces computational complexity. The inversion of obstacle avoidance data enables the system to quickly adapt to non-baseline conditions without reconstructing the analysis logic, improving vehicle response efficiency under complex and changing conditions. A unified data processing method ensures consistency in obstacle avoidance decision-making logic between baseline and non-baseline conditions, reducing the risk of misjudgment due to condition switching and improving driving safety. This method abstracts condition differences into data transformation and processing rules, facilitating future expansion to support more types of conditions and enhancing system versatility and maintainability.

[0119] Based on the above embodiments, the method further includes: if the longitudinal obstacle avoidance data is less than a preset obstacle avoidance distance threshold, then the collision detection result of the vehicle body area is determined to be a collision risk; based on the driving conditions, the collision detection result and the vehicle body area corresponding to the collision detection result, the collision position status of the vehicle body area is determined, and the collision position status is transmitted to the visualization terminal for display.

[0120] Specifically, the system acquires longitudinal obstacle avoidance data calculated based on key vehicle body information, minimum turning radius, and obstacle information. This data is then compared to a pre-set obstacle avoidance distance threshold. If the longitudinal obstacle avoidance data is less than the threshold, the system determines that the collision detection result for that vehicle body area indicates a collision risk; otherwise, it considers there to be no collision risk. Subsequently, combining the vehicle's current driving conditions (e.g., forward left turn, inside obstacle avoidance, etc.), the collision detection results, and the corresponding risky vehicle body areas, a comprehensive analysis is performed to determine the collision position status of the vehicle body areas (e.g., a collision risk in the left front area, safety in the rear area, etc.). Finally, the collision position status is transmitted to a visualization terminal (e.g., an in-vehicle display screen, a large monitoring screen) via a data interface, and displayed to the user in an intuitive format such as graphics and text.

[0121] For example, when the baseline condition is a vehicle reversing and turning right, collision features are pre-classified according to the actual situation, and corresponding states are set for abnormal obstacle avoidance analysis and alerts, enabling better anomaly management. The collision avoidance zone for the driving condition type of forward right turn is output with a status range of 0-8. When status output is required, the following settings can be configured for unified management of obstacle avoidance anomalies:

[0122] Status = 0, inner non-collision zone or outer non-collision zone;

[0123] Status = 1, inner collision avoidance zone, collision point between 0 and 1;

[0124] Status=2, inner collision avoidance zone, the vehicle body area corresponding to the collision point in the range of 1-2, which is also between 0-1;

[0125] Status = 3, inner rearview mirror side collision avoidance zone, collision avoidance point is between 2 and 3;

[0126] Status = 4, the collision avoidance zone in front of the inner rearview mirror, the collision avoidance point is between 3 and 4;

[0127] Status = 5, inner collision avoidance zone, collision avoidance point is between 4 and 5;

[0128] Status = 6, out of the inner collision avoidance zone, collision point is between 5 and 6;

[0129] Status = 7, the collision avoidance zone in front of the outer rearview mirror, the collision avoidance point is between 7 and 8;

[0130] Status = 8, outer collision avoidance zone, collision avoidance point is between 11 and 12.

[0131] In this embodiment, by simply comparing longitudinal obstacle avoidance data with thresholds, potential collision risks can be quickly identified and a warning mechanism can be triggered in a timely manner. By combining driving conditions and collision detection results, collision risk areas can be accurately located, avoiding misjudgments caused by single data. The abstract collision position status is transformed into visual information, making it easier for drivers or system operators to intuitively grasp the vehicle's safety status and make quick response decisions. The collision risk areas are identified in advance, providing a basis for the formulation of subsequent obstacle avoidance strategies, effectively reducing the probability of collision accidents and ensuring driving safety.

[0132] S570, Perform obstacle avoidance processing on the target vehicle based on lateral obstacle avoidance data and / or longitudinal obstacle avoidance data.

[0133] The technical solution of this embodiment acquires the driving conditions of the target vehicle, obtaining vehicle body information, key point information, minimum turning radius, and obstacle information under baseline conditions. Based on the vehicle body and obstacle information, lateral obstacle avoidance data is derived. Then, the effective collision area of ​​the vehicle body is determined from the key points of the vehicle body. Combining the key points of the vehicle body area, obstacle information, and minimum turning radius, first distance data and first angle data are determined sequentially. The obstacle avoidance distance at each obstacle corner is then calculated, and the minimum obstacle avoidance distance is taken as the obstacle avoidance data for the vehicle body area. Finally, obstacle avoidance processing is performed on the vehicle based on the lateral and longitudinal data. Through the integration and in-depth analysis of multi-source data, a comprehensive vehicle obstacle avoidance decision-making system is constructed. The multi-step processing from data acquisition to obstacle avoidance data determination accurately analyzes the spatial relationship between the vehicle and obstacles. Whether it's lateral obstacle avoidance data ensuring path planning during turns or obstacle avoidance data obtained through complex calculations ensuring longitudinal safety distances, the vehicle can make scientific and reasonable obstacle avoidance actions under various conditions. The flexible horizontal and vertical data collaboration or independent application modes enhance the system's adaptability to complex road conditions, greatly improve the safety and reliability of vehicle driving, and provide a solid and effective technical solution for intelligent driving.

[0134] Example 3

[0135] Figure 8 This is a schematic diagram of a vehicle obstacle avoidance and bypass device provided in Embodiment 3 of the present invention. Figure 8 As shown, the device includes:

[0136] The driving condition acquisition module 810 is used to acquire the driving condition of the target vehicle at the current moment. The driving condition includes basic condition and non-baseline condition.

[0137] The obstacle avoidance data determination module 820 is used to acquire the target vehicle's body information, key body point information, minimum turning radius, and obstacle information under reference conditions, and to determine lateral obstacle avoidance data based on the target vehicle's body information and obstacle information; and / or, to determine longitudinal obstacle avoidance data based on the target vehicle's key body point information, minimum turning radius, and obstacle information, wherein the lateral obstacle avoidance data includes the rear axle turning radius and the front axle heading angle; and the longitudinal obstacle avoidance data includes the obstacle avoidance distance.

[0138] The obstacle avoidance processing module 830 is used to perform obstacle avoidance processing on the target vehicle based on lateral obstacle avoidance data and / or longitudinal obstacle avoidance data.

[0139] The technical solution of this embodiment involves acquiring the current driving conditions of the target vehicle through a driving condition acquisition module, which includes basic and non-baseline driving conditions; an obstacle avoidance data determination module acquiring the vehicle's body information, key body point information, minimum turning radius, and obstacle information under the baseline driving conditions, and determining lateral obstacle avoidance data based on the vehicle's body information and obstacle information; and / or determining longitudinal obstacle avoidance data based on the vehicle's key body point information, minimum turning radius, and obstacle information, wherein the lateral obstacle avoidance data includes the rear axle turning radius and front axle heading angle; and the longitudinal obstacle avoidance data includes the obstacle avoidance distance; and an obstacle avoidance processing module performing obstacle avoidance processing on the target vehicle based on the lateral obstacle avoidance data and / or the longitudinal obstacle avoidance data. This solution establishes a precise and dynamic decision-making data foundation by acquiring comprehensive information on driving conditions, vehicle body, and obstacles. The independent or collaborative determination of lateral and longitudinal obstacle avoidance data enables multi-dimensional and refined control of vehicle obstacle avoidance behavior. Based on the obstacle avoidance processing of these two types of data, it can flexibly adapt to different road and working conditions, enhancing the vehicle's ability to cope with complex scenarios. This not only improves the scientificity and reliability of obstacle avoidance strategies but also ensures that the vehicle can safely and efficiently avoid obstacles during dynamic driving, solving the problem of low obstacle avoidance efficiency and significantly improving the safety and stability of intelligent driving.

[0140] Based on the above embodiments, optionally, the reference working condition is inner obstacle avoidance in the first rotation direction, the vehicle body information includes the vehicle body width and axle distance, and the obstacle information includes the position data of multiple obstacle corner points; the obstacle avoidance data determination module 820 is specifically used to determine the turning radius corresponding to each obstacle corner point based on the position data of each obstacle corner point and the vehicle body width; to determine the angle data corresponding to each obstacle corner point based on the rear axle turning radius and axle distance corresponding to each obstacle corner point; and to determine the lateral obstacle avoidance data based on the turning radius and angle data corresponding to each obstacle corner point.

[0141] Optionally, the baseline condition is the outer obstacle bypass in the first rotation direction; the obstacle bypass data determination module 820 is specifically used to obtain the turning radius calculation model, wherein the turning radius calculation model includes the mathematical relationship between the turning radius parameters, the two-dimensional coordinate parameters of the overhanging corner point and the linear parameters, and the linear parameters are the linear parameters of the obstacle edge lines obtained by fitting the position data of adjacent obstacle corner points; the two-dimensional coordinate data of the target overhanging corner point and the linear parameter values ​​corresponding to multiple obstacle edge lines are obtained and substituted into the turning radius calculation model to obtain the turning radius corresponding to each obstacle edge line; the angle data corresponding to each obstacle edge line is determined based on the turning radius corresponding to each obstacle edge line and the axle distance; the lateral obstacle bypass data is determined based on the turning radius and angle data corresponding to each obstacle edge line.

[0142] Optionally, the obstacle avoidance data determination module 820 is specifically used to obtain the effective collision area of ​​the vehicle body under the benchmark condition from the key point information of the vehicle body, and to obtain the minimum turning radius of the target vehicle at the current moment; wherein, the effective collision area of ​​the vehicle body includes multiple vehicle body regions, each of which is formed by connecting at least two key points of the vehicle body in sequence; for each of the vehicle body regions, a first distance data is determined based on the key point position information, obstacle information, and minimum turning radius of the vehicle body region, wherein the first distance data includes the distance data of multiple obstacle corner points in the obstacle information relative to the instantaneous turning center of the target vehicle; a first included angle data is determined based on the key point position information, obstacle information, minimum turning radius, and first distance data of the vehicle body region, wherein the first included angle data includes the included angle data corresponding to multiple obstacle corner points, each included angle being the included angle formed by the obstacle corner point and the vehicle body collision point relative to the instantaneous turning center of the target vehicle; the obstacle avoidance distance of each obstacle corner point is determined based on the first distance data and the first included angle, and the minimum obstacle avoidance distance among the obstacle avoidance distances of each obstacle corner point is selected as the obstacle avoidance data of the vehicle body region.

[0143] Optionally, the obstacle avoidance data determination module 820 includes an obstacle information acquisition unit. This unit is used to spatially transform the obstacle information under a non-reference operating condition when the target vehicle is in a non-reference operating condition, obtaining the transformed position information under the reference operating condition corresponding to the non-reference operating condition, and updating the obstacle information based on the transformed position information. Specifically, the obstacle avoidance data determination module 820 is also used to invert the lateral obstacle avoidance data and / or longitudinal obstacle avoidance data to obtain the lateral obstacle avoidance data and / or longitudinal obstacle avoidance data under the non-reference operating condition.

[0144] Optionally, before determining longitudinal obstacle avoidance data based on the target vehicle's key point information, minimum turning radius, and obstacle information, the device is used to determine whether the obstacle is within the effective collision area based on the obstacle information and the vehicle's key point information. If the obstacle is within the effective collision area, the determination of longitudinal obstacle avoidance data continues; if the obstacle is not within the effective collision area, the determination of longitudinal obstacle avoidance data does not continue. The method for determining whether the obstacle is within the effective collision area includes one or more of the following: determining the effective collision area range based on the vehicle's key point information; if the obstacle information meets the effective collision area range, the obstacle is determined to be within the effective collision area; acquiring the instantaneous turning center position data of the target vehicle; determining second distance data based on the obstacle information and the instantaneous turning center position data; determining a distance threshold based on the vehicle's key point information and the instantaneous turning center position data; if the second distance data meets the distance threshold, the obstacle is determined to be within the effective collision area.

[0145] Optionally, the device is also used to determine that there is a collision risk in the collision detection result of the vehicle body area if the longitudinal obstacle avoidance data is less than the preset obstacle avoidance distance threshold; determine the collision position status of the vehicle body area based on the driving conditions, the collision detection result and the vehicle body area corresponding to the collision detection result, and transmit the collision position status to the visualization terminal for display.

[0146] The vehicle obstacle avoidance processing device provided in the embodiments of the present invention can execute the vehicle obstacle avoidance processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0147] Example 4

[0148] Figure 9This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0149] like Figure 9 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0150] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0151] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as vehicle obstacle avoidance processing methods.

[0152] In some embodiments, the vehicle obstacle avoidance processing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the vehicle obstacle avoidance processing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the vehicle obstacle avoidance processing method by any other suitable means (e.g., by means of firmware).

[0153] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0154] Computer programs for implementing the vehicle obstacle avoidance method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0155] Example 5

[0156] Embodiment 5 of the present invention also provides a computer-readable storage medium storing computer instructions for causing a processor to execute a vehicle obstacle avoidance method, the method comprising:

[0157] Obtain the current driving conditions of the target vehicle, including basic conditions and non-baseline conditions;

[0158] Acquire the target vehicle's body information, key body point information, minimum turning radius, and obstacle information under baseline conditions; determine lateral obstacle avoidance data based on the target vehicle's body information and obstacle information; and / or determine longitudinal obstacle avoidance data based on the target vehicle's key body point information, minimum turning radius, and obstacle information, wherein the lateral obstacle avoidance data includes the rear axle turning radius and front axle heading angle; and the longitudinal obstacle avoidance data includes obstacle avoidance distance.

[0159] Obstacle avoidance processing is performed on the target vehicle based on lateral obstacle avoidance data and / or longitudinal obstacle avoidance data.

[0160] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0161] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0162] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0163] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0164] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0165] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for vehicle obstacle avoidance, characterized in that, include: Obtain the current driving conditions of the target vehicle, including basic conditions and non-baseline conditions; Obtain the vehicle body information, key body point information, minimum turning radius, and obstacle information under the baseline conditions of the target vehicle; determine lateral obstacle avoidance data based on the vehicle body information and the obstacle information. And / or, longitudinal obstacle avoidance data is determined based on the target vehicle's key body point information, minimum turning radius, and obstacle information, wherein the lateral obstacle avoidance data includes the rear axle turning radius and front axle heading angle; and the longitudinal obstacle avoidance data includes obstacle avoidance distance. The target vehicle is subjected to obstacle avoidance processing based on the lateral obstacle avoidance data and / or the longitudinal obstacle avoidance data.

2. The method according to claim 1, characterized in that, The baseline working condition is an inner obstacle avoidance in the first rotation direction; the vehicle body information includes the vehicle body width and axle distance; the obstacle information includes the position data of multiple obstacle corner points. The determination of lateral obstacle avoidance data based on the target vehicle's body information and obstacle information includes: Based on the position data of each obstacle corner point and the vehicle width, the turning radius corresponding to each obstacle corner point is determined respectively; based on the rear axle turning radius corresponding to each obstacle corner point and the axle distance, the angle data corresponding to each obstacle corner point is determined respectively. The lateral obstacle avoidance data is determined based on the turning radius and angle data corresponding to each corner point of the obstacle.

3. The method according to claim 2, characterized in that, The reference working condition is the outer obstacle bypass in the first rotation direction; The step of determining lateral obstacle avoidance data based on the target vehicle's body information and the obstacle information includes: A turning radius calculation model is obtained, wherein the turning radius calculation model includes a mathematical relationship between the turning radius parameter, the two-dimensional coordinate parameter of the overhanging corner point, and the linear parameter, wherein the linear parameter is the linear parameter of the obstacle edge obtained by fitting the position data of the adjacent obstacle corner points; The two-dimensional coordinate data of the target overhang point and the linear parameter values ​​corresponding to multiple obstacle edges are obtained and substituted into the turning radius calculation model to obtain the turning radius corresponding to each obstacle edge. Based on the turning radius corresponding to each obstacle edge and the axle distance, the angle data corresponding to each obstacle edge is determined. The lateral obstacle avoidance data is determined based on the turning radius and angle data corresponding to the edge lines of each obstacle.

4. The method according to claim 1, characterized in that, The determination of longitudinal obstacle avoidance data based on the target vehicle's key point information, minimum turning radius, and obstacle information includes: The effective collision area of ​​the vehicle under the benchmark condition is obtained from the vehicle body key point information, and the minimum turning radius of the target vehicle at the current moment is obtained; wherein, the effective collision area of ​​the vehicle includes multiple vehicle body regions, and each vehicle body region is formed by connecting at least two vehicle body key points in sequence; For each segment of the vehicle body area, a first distance data is determined based on the key point location information on the vehicle body area, the obstacle information, and the minimum turning radius. The first distance data includes the distance data of multiple obstacle corner points in the obstacle information relative to the instantaneous turning center of the target vehicle. Based on the key point location information on the vehicle body area, the obstacle information, the minimum turning radius, and the first distance data, the first included angle data is determined, wherein the first included angle data includes included angle data corresponding to multiple obstacle corner points, and each included angle is the angle formed by the obstacle corner point and the vehicle body collision point relative to the instantaneous turning center of the target vehicle; Based on the first distance data and the first included angle, the obstacle avoidance distance for each obstacle corner point is determined, and the minimum distance among the obstacle avoidance distances for each obstacle corner point is selected as the longitudinal obstacle avoidance data for the vehicle body area.

5. The method according to any one of claims 1-4, characterized in that, The method for obtaining obstacle information under the aforementioned baseline conditions includes: When the target vehicle is in the non-baseline working condition, the obstacle information in the non-baseline working condition is spatially transformed to obtain the transformed position information in the baseline working condition corresponding to the non-baseline working condition, and the obstacle information is updated based on the transformed position information; The method further comprises: The lateral obstacle avoidance data and / or the longitudinal obstacle avoidance data are inverted to obtain the lateral obstacle avoidance data and / or the longitudinal obstacle avoidance data under the non-baseline working condition.

6. The method according to claim 1, characterized in that, Before determining the longitudinal obstacle avoidance data based on the target vehicle's key point information, minimum turning radius, and obstacle information, the method further includes: Based on the obstacle information and the vehicle body key point information, it is determined whether the obstacle is within the effective collision area. If the obstacle is within the effective collision area, the longitudinal obstacle avoidance data determination continues. If the obstacle is not within the effective collision area, the longitudinal obstacle avoidance data determination does not continue. The method for determining whether an obstacle is within the effective collision area includes one or more of the following: The effective collision area is determined based on the vehicle body key point information. If the obstacle information meets the effective collision area range, the obstacle is determined to be within the effective collision area. The system acquires the instantaneous turning center position data of the target vehicle, determines second distance data based on the obstacle information and the instantaneous turning center position data, determines a distance threshold based on the vehicle body key point information and the instantaneous turning center position data, and determines that the obstacle is within the effective collision area if the second distance data meets the distance threshold.

7. The method according to claim 4, characterized in that, The method also includes: If the longitudinal obstacle avoidance data is less than the preset obstacle avoidance distance threshold, then the collision detection result of the vehicle body area is determined to be a collision risk. Based on the driving conditions, the collision detection results, and the vehicle body area corresponding to the collision detection results, the collision position state of the vehicle body area is determined, and the collision position state is transmitted to the visualization terminal for display.

8. A vehicle obstacle avoidance and bypass device, characterized in that, include: The driving condition acquisition module is used to acquire the driving condition of the target vehicle at the current moment, which includes basic conditions and non-baseline conditions. The obstacle avoidance data determination module is used to acquire the vehicle body information, key point information of the vehicle body, minimum turning radius and obstacle information under the reference working condition of the target vehicle, and determine the lateral obstacle avoidance data based on the vehicle body information and the obstacle information. And / or, longitudinal obstacle avoidance data is determined based on the target vehicle's key body point information, minimum turning radius, and obstacle information, wherein the lateral obstacle avoidance data includes the rear axle turning radius and front axle heading angle; and the longitudinal obstacle avoidance data includes obstacle avoidance distance. The obstacle avoidance processing module is used to perform obstacle avoidance processing on the target vehicle based on the lateral obstacle avoidance data and / or the longitudinal obstacle avoidance data.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the vehicle obstacle avoidance processing method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the vehicle obstacle avoidance method according to any one of claims 1-7.

Images