Vehicle obstacle avoidance travel control method, readable storage medium, and vehicle

Abstract

This disclosure relates to a vehicle obstacle avoidance driving control method, a readable storage medium, and a vehicle. The method includes: acquiring vehicle start-point information, end-point information, and driving boundary information; planning an obstacle avoidance driving path based on the start-point information, the end-point information, the driving boundary information, and pre-acquired vehicle parameters, and acquiring the planned trajectory of the vehicle, the planned trajectory including a single-segment path trajectory or a multi-segment path trajectory; calculating a target front wheel steering angle based on the planned trajectory and the vehicle parameters; controlling the vehicle to steer based on the target front wheel steering angle, and updating the vehicle's position and posture information. This method achieves automatic path planning and automatic obstacle avoidance driving without driver intervention, is applicable to various vehicle driving scenarios, solves the problem that drivers with varying driving skills cannot effectively navigate adverse road conditions, and expands the application scenarios of intelligent driving.

Description

Technical Field

[0001] This disclosure relates to the field of autonomous driving, specifically to a vehicle obstacle avoidance driving control method, a readable storage medium, and a vehicle. Background Technology

[0002] Remote driving is a technology that controls a vehicle's movement via a remote device. Currently, when steering is required in remote driving, manual control is typically used. In practical applications of remote driving, there are low-traffic scenarios, primarily including various adverse road conditions such as roads with standing water, potholes, missing manhole covers, cracks, or roads without clear directions. Drivers with varying skill levels may be unable to effectively navigate such challenging terrains. Current remote driving technology cannot compensate for driver limitations on these low-traffic surfaces, thus restricting its application. Summary of the Invention

[0003] The purpose of this disclosure is to provide a vehicle obstacle avoidance driving control method, a readable storage medium, and a vehicle to solve the problem that drivers with varying driving skills are unable to effectively navigate rough road conditions.

[0004] To achieve the above objectives, firstly, this disclosure provides a vehicle obstacle avoidance driving control method, comprising: Obtain the vehicle's origin, destination, and driving boundary information; Based on the starting point information, the ending point information, the driving boundary information and the pre-acquired vehicle parameters, an obstacle avoidance driving path is planned, and the planned trajectory of the vehicle is obtained. The planned trajectory includes a single-segment path trajectory or a multi-segment path trajectory. Based on the planned trajectory and the vehicle parameters, the target front wheel steering angle is calculated; The vehicle is controlled to steer based on the target front wheel angle, and the vehicle's position and posture information is updated.

[0005] Optionally, obtaining the vehicle's starting point information, ending point information, and driving boundary information includes: The system acquires an environmental image of the vehicle while it is stationary and displays it on the vehicle's interactive interface. The environmental image includes the vehicle's position, environmental obstacles, and the destination. Based on the interactive interface, obtain the driving boundary and destination position drawn on the environmental image; Based on the coordinate system corresponding to the environmental image, as well as the vehicle position, the driving boundary, and the destination position, the starting point information, the destination information, and the driving boundary information are obtained.

[0006] Optionally, the vehicle parameters include front track width, rear track width, and wheelbase, and the calculation of the target front wheel steering angle based on the planned trajectory and the vehicle parameters includes: Obtain the travel distance of each tire in the current control cycle; The vehicle's turning radius is calculated based on the driving distance and the rear wheel track. The target front wheel angle is calculated based on the vehicle's turning radius, the front track width, and the wheelbase.

[0007] Optionally, updating the vehicle pose information includes: Based on the travel distance and the vehicle coordinates and vehicle attitude angles of the previous control cycle, the vehicle coordinates and vehicle attitude angles of the current control cycle are calculated. The vehicle pose information is updated based on the vehicle coordinates and vehicle attitude angles of the current control cycle.

[0008] Optionally, the vehicle includes a steer-by-wire system, the steer-by-wire system including a steering wheel actuator and wheel-end actuators, and controlling the vehicle to steer based on the target front wheel angle includes: Decouple the connection between the steering wheel actuator and the wheel-end actuator; A steering command is issued to the wheel-end actuator, the steering command including the target front wheel angle, so that the wheel-end actuator drives the vehicle to steer based on the target front wheel angle; When the vehicle reaches its destination, the connection between the steering wheel actuator and the wheel-end actuator is restored.

[0009] Optionally, the vehicle parameters include a turning radius threshold, and the process of planning an obstacle avoidance path based on the starting point information, the ending point information, the driving boundary information, and the pre-acquired vehicle parameters, and obtaining the vehicle's planned trajectory, includes: Based on the starting point information, the ending point information, and the driving boundary information, single-segment path planning is performed to determine whether there is a single-segment planned trajectory that satisfies the turning radius threshold. If the single-segment planned trajectory does not exist, multi-segment path planning is performed based on the starting point information, the ending point information, and the driving boundary information to obtain multiple planned trajectories. Collision detection is performed on the single-segment or multi-segment planned trajectory; If the collision detection passes, the single-segment planned trajectory or the multi-segment planned trajectory will be used as the planned trajectory.

[0010] Optionally, the step of performing multi-segment path planning based on the starting point information, the ending point information, and the driving boundary information to obtain multi-segment planned trajectories includes: A constraint space is constructed based on the starting point information, the ending point information, and the driving boundary information; Random sampling is performed within the constrained space to obtain candidate sampling points containing pose information; Based on the collision constraints and reachability constraints of the constraint space, the candidate sampling points are filtered to obtain feasible sampling points; A directed graph is constructed based on the feasible sampling points, where the edges of the directed graph are path segments between the feasible sampling points, and the cost of each edge is the path length. The optimal multi-segment path is obtained based on the directed graph search. The intermediate nodes of the optimal multi-segment path are nonlinearly optimized to obtain the multi-segment planned trajectory.

[0011] In a second aspect, this disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the vehicle obstacle avoidance driving control method described in the first aspect.

[0012] Thirdly, this disclosure provides a vehicle including a control device for the vehicle obstacle avoidance driving control method described in the first aspect.

[0013] Optionally, the vehicle further includes an interactive interface, an image acquisition device, and a steer-by-wire system. The image acquisition device is used to acquire environmental images of the vehicle in a stationary state and send them to the interactive interface for display. The interactive interface is used to acquire the driving boundary and endpoint position drawn on the environmental image. The steer-by-wire system is used to respond to the steering command of the control device and drive the vehicle to steer based on the target front wheel angle in the steering command.

[0014] The above technical solution acquires the vehicle's starting point, ending point, and driving boundary information. Based on these information and vehicle parameters, it plans an obstacle avoidance path, automatically generates the planned path, and initiates a closed-loop control function for vehicle driving. The system automatically calculates the target front wheel angle based on the planned path and the vehicle's current position and orientation, drives the vehicle to automatically steer according to the target front wheel angle, and automatically updates the vehicle's position and orientation information based on the driving route, executing the next control cycle until the vehicle reaches its destination. This achieves automatic path planning and obstacle avoidance without driver intervention, making it suitable for various driving scenarios and solving the problem of drivers with varying skill levels being unable to effectively navigate challenging road conditions.

[0015] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0016] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart illustrating a vehicle obstacle avoidance driving control method according to an exemplary embodiment.

[0017] Figure 2 This is a flowchart illustrating the acquisition of vehicle origin and destination information and driving boundary information according to an exemplary embodiment.

[0018] Figure 3 This is a flowchart illustrating an algorithm for a target front wheel steering angle according to an exemplary embodiment.

[0019] Figure 4 This is a schematic diagram illustrating the turning radius of a vehicle according to an exemplary embodiment.

[0020] Figure 5 This is a flowchart illustrating a vehicle pose information update process according to an exemplary embodiment.

[0021] Figure 6 This is a flowchart illustrating a method for controlling vehicle movement using a steer-by-wire system according to an exemplary embodiment.

[0022] Figure 7 This is a flowchart illustrating an example of obtaining a vehicle planning trajectory.

[0023] Figure 8 This is a flowchart illustrating a multi-segment path planning method according to an exemplary embodiment. Detailed Implementation

[0024] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0025] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0026] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0027] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules, or units, and are not used to limit the order of functions performed by these devices, modules, or units or their interdependencies. It should also be noted that the modifications of "a" and "a plurality of" mentioned in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0028] This disclosure presents a vehicle obstacle avoidance driving control method. The technical solution of this disclosure is described in detail below.

[0029] Figure 1 This is a flowchart illustrating a vehicle obstacle avoidance driving control method according to an exemplary embodiment, such as... Figure 1 As shown, the method includes: Step S101: Obtain the vehicle's starting point information, ending point information, and driving boundary information.

[0030] During vehicle operation, if the driver encounters a road surface with low passability, the vehicle can stop and execute the obstacle avoidance driving control method of this embodiment. Specifically, a road surface with low passability can be a road surface with environmental obstacles such as water accumulation, potholes, missing manhole covers, and cracks.

[0031] For example, the starting point can be the location of the vehicle when it is parked and stationary, and the starting point information can include the coordinates of the starting point in the vehicle coordinate system and the vehicle's facing angle; the ending point can be the target location of the vehicle after passing through the obstacle, and the ending point information can include the coordinates of the ending point in the vehicle coordinate system; the driving boundary can be the path boundary line of the vehicle when it is avoiding the obstacle, and the driving boundary information can include the coordinates of the path boundary line or the sequence of boundary points on the path boundary line in the vehicle coordinate system.

[0032] For example, the starting point and the location of environmental obstacles can be identified through environmental information collection devices mounted on the vehicle, such as cameras and radar devices, and the destination information and driving boundary information can be obtained based on the location of the environmental obstacles. The destination information and driving boundary information can be automatically generated by relevant algorithms, or obtained by relevant personnel such as the vehicle driver through a human-machine interface.

[0033] Step S102: Based on the starting point information, ending point information, driving boundary information and pre-acquired vehicle parameters, plan the obstacle avoidance driving path and obtain the planned trajectory of the vehicle. The planned trajectory includes a single-segment path trajectory or a multi-segment path trajectory.

[0034] For example, vehicle parameters may include wheelbase, track width, minimum turning radius, etc.

[0035] The system uses starting point information, ending point information, and driving boundary information as input parameters, combined with pre-acquired vehicle parameters, to perform path planning. Specifically, the driving boundary information defines the physical boundaries of the vehicle's drivable space; within this constraint, the vehicle's driving path can be calculated based on the vehicle's steering parameters and area restrictions.

[0036] When the drivable space is relatively spacious, the generated planned trajectory can be a continuous single-segment path trajectory without redundant back-and-forth movements. Specifically, the Reeds-Shepp curve analytical solver or other solvers with similar functions can be used to calculate the shortest path that satisfies the minimum turning radius constraint. When the drivable space is relatively narrow or restricted (e.g., when facing a low-passability road surface requiring multiple directional adjustments), the generated planned trajectory can be a multi-segment path trajectory composed of multiple forward and / or backward segments, used to guide the vehicle to safely pass through the obstacle area through multiple steering adjustments. Specifically, random sampling, graph search algorithms, or a combination thereof can be used to generate a planned trajectory that avoids obstacles and satisfies the vehicle's minimum turning radius constraint.

[0037] Step S103: Calculate the target front wheel steering angle based on the planned trajectory and vehicle parameters.

[0038] Based on the vehicle's pose information and the planned trajectory, the geometric deviation between the current vehicle pose and the planned trajectory can be calculated, such as distance deviation or angle deviation. Combining vehicle parameters (e.g., wheelbase and track width), a trajectory tracking control algorithm can be used to calculate the target front wheel steering angle that will allow the vehicle to eliminate this geometric deviation and conform to the planned trajectory. Specifically, the trajectory tracking control algorithm can be a pure tracking control algorithm, a feedforward-feedback control algorithm, a model predictive control algorithm, etc.

[0039] Step S104: Control the vehicle to steer based on the target front wheel angle and update the vehicle position and posture information.

[0040] The calculated target front wheel steering angle is sent to the vehicle's steering control actuator to drive the wheels to turn. Specifically, the steering control actuator may include a steering motor, a transmission device, etc. The steering control actuator drives the wheels to complete the steering process while driving.

[0041] For example, vehicle pose information may include the vehicle's current coordinates and body attitude angles, where the body attitude angles can be considered as the angle between the vehicle's front direction and a specific coordinate axis of the coordinate system. Specifically, the vehicle's current coordinates and body attitude angles can be obtained in real-time through positioning or measurement devices (such as inertial measurement units, wheel speedometers, etc.) and calculated. During controlled vehicle driving, the system continuously monitors and updates the vehicle pose information using the onboard measurement devices at a preset control frequency, and continuously returns the updated vehicle pose information to step S103 for rolling target front wheel angle calculation, forming a closed-loop control until it is determined that the vehicle's pose information has reached its destination, completing the avoidance maneuver against obstacles on low-traffic surfaces.

[0042] Through steps S101-S104, by acquiring the vehicle's starting point information, ending point information, and driving boundary information, an obstacle avoidance driving path is planned based on the starting point information, ending point information, driving boundary information, and vehicle parameters. The planned path is automatically generated, and the closed-loop control function of vehicle driving is activated. The target front wheel angle at the current moment is automatically calculated based on the planned path and the vehicle's current position and posture information. The vehicle is driven to automatically steer based on the target front wheel angle, and the vehicle's position and posture information is automatically updated based on the driving route. The next control cycle is executed until the vehicle reaches the destination. Automatic path planning and automatic obstacle avoidance driving are achieved without driver operation. It is applicable to various vehicle driving scenarios and solves the problem that drivers with varying driving skills cannot effectively pass through the road surface when facing adverse road conditions.

[0043] In some embodiments, specific methods for obtaining vehicle origin and destination information and driving boundary information are also involved. Figure 2 This is a flowchart illustrating the acquisition of vehicle origin-end point information and driving boundary information according to an exemplary embodiment, such as... Figure 2 As shown, this step includes: Step S201: Acquire an environmental image of the vehicle in a stationary state and display it on the vehicle's interactive interface. The environmental image includes the vehicle's position, environmental obstacles, and the destination.

[0044] For example, the vehicle's user interface can be the interface of a display control device mounted on the vehicle. This display control device can communicate with the vehicle's control unit to receive user control commands and forward them to the control unit, as well as receive and display status information sent by the control unit. The display control device can be, for example, a central touchscreen or an instrument panel.

[0045] For example, the environmental image can be a panoramic view including the environment around the vehicle. When the vehicle is stationary, the on-board image acquisition device can be automatically triggered or manually triggered by the driver to capture the environmental image. Specifically, image acquisition devices (such as front-view cameras, rear-view cameras, or surround-view camera systems) installed around the vehicle can be used to acquire environmental images around the vehicle, which can intuitively reflect the distribution of obstacles around the vehicle.

[0046] The environmental image can include the vehicle's position, environmental obstacles, and the destination. Specifically, to facilitate driver operation, when the environmental image is transmitted to the vehicle's interactive interface for display, a virtual projection or geometric outline of the vehicle itself can be overlaid on the image to represent the current vehicle position. In some further embodiments, the system can also mark or highlight automatically identified environmental obstacles and the expected destination range after passing over obstacles on the image based on image recognition algorithms, providing the driver with an intuitive global obstacle avoidance view.

[0047] Step S202: Based on the interactive interface, obtain the driving boundary and endpoint position drawn on the environmental image.

[0048] Drivers can interact with the environment displayed on the interface to determine the vehicle's driving boundaries and destination. Specifically, the vehicle interface can have graphic drawing and interactive response capabilities. Drivers can draw lines directly on the screen using their fingers or a stylus to define the desired driving boundaries for obstacle avoidance, such as drawing one or more lines between obstacles and the vehicle to prevent it from crossing them. Drivers can also click and drag specific icons or markers to determine the desired destination after the vehicle passes through an obstacle.

[0049] Step S203: Based on the coordinate system corresponding to the environmental image, as well as the vehicle position, driving boundary, and end point position, obtain the starting point information, end point information, and driving boundary information.

[0050] The vehicle can establish a coordinate system based on the environmental image. Specifically, for example, a coordinate system can be established with the vehicle's current position as the origin, the front of the vehicle as the positive Y-axis, and the right side of the vehicle as the positive X-axis. Based on the image pixels corresponding to the already marked destination position, coordinates in the vehicle coordinate system are obtained through coordinate system transformation, thus yielding the destination information. Similarly, the sequence of pixels on the driving boundary lines drawn by the driver in the environmental image is converted into a sequence of boundary point coordinates in the vehicle coordinate system, thus obtaining the driving boundary information. This data will collectively serve as the underlying coordinate data source for subsequent path planning algorithms.

[0051] Through steps S201-S203, the real-world environment images surrounding the vehicle are displayed through the in-vehicle interactive interface, allowing the driver to intuitively perceive the shape and location of obstacles in the surrounding environment. The environmental images can be acquired through a camera, eliminating the need for additional environmental sensing devices and reducing vehicle hardware costs. By performing simple touch operations on the human-machine interface, the driving boundary and destination positions can be quickly marked, improving the convenience of human-machine collaborative obstacle avoidance driving. At the same time, it avoids the potential misjudgment problems that may occur when relying solely on image recognition algorithms to identify obstacles and driving boundaries, thus reducing driving risks.

[0052] In some embodiments, a method for calculating the target front wheel steering angle is also involved. Figure 3 This is a flowchart illustrating an algorithm for a target front wheel steering angle according to an exemplary embodiment, such as... Figure 3 As shown, the calculation method includes: Step S301: Obtain the travel distance of each tire in the current control cycle.

[0053] The vehicle control unit can acquire the travel distance of each tire in real time during each control cycle of vehicle operation. Specifically, the travel distance can be represented by the travel arc length of that tire within the current control cycle. Methods for acquiring the travel arc length include, but are not limited to: reading the measurement signals output by the wheel speed sensors deployed at the vehicle's wheel hubs; or directly acquiring the motor speed fed back by the motor drive controller on the wheel hubs and converting it into the corresponding travel arc length. Furthermore, the system can also perform filtering or noise reduction processing on the acquired raw data to improve data accuracy.

[0054] Step S302: Calculate the vehicle's turning radius based on the driving distance and rear wheel track.

[0055] Figure 4 This is a schematic diagram illustrating the turning radius of a vehicle according to an exemplary embodiment, such as... Figure 4 As shown, the wheelbase L is the longitudinal distance between the center lines of the front and rear axles of the vehicle, and the front track B... f It is the lateral distance between the center lines of the left and right wheels. The instantaneous steering center position is a virtual center of rotation point. When the vehicle makes a steering motion at a certain instant, the entire vehicle body can be regarded as moving in a circle around this point. The vehicle's turning radius R is the distance from the instantaneous steering center position to the vehicle reference line (the extended line of the inner rear wheel's axis in the figure), and can also be regarded as the equivalent turning radius corresponding to the instantaneous steering motion of the vehicle.

[0056] Specifically, the rear axle center arc length of the current control cycle can be calculated based on the tire travel arc length. The rear axle center arc length represents the travel arc length of the vehicle's rear axle center within that sampling cycle, and is obtained by averaging the actual travel arc lengths of the left and right rear wheels.

[0057] in, The arc length of the rear axle center. The travel arc length of the left rear wheel. This is the travel arc length of the right rear wheel.

[0058] Then, based on the travel arc lengths of the left and right rear wheels, calculate the change in attitude angle and the vehicle's turning radius:

[0059] in, This is the increment of the vehicle attitude angle. This refers to the rear track width.

[0060]

[0061] Where R is the vehicle's turning radius.

[0062] Step S303: Calculate the target front wheel angle based on the vehicle's turning radius, front track width, and wheelbase.

[0063] Taking into account the vehicle's inherent physical parameters—wheelbase L, front track B f By using trigonometric geometric relationships, it is possible to calculate accurately: Target corner of left front wheel:

[0064] Right front wheel target angle:

[0065] Through steps S301-S303, the deflection angles of the left and right front wheels of the vehicle are calculated using the tire travel distance and the vehicle's physical parameters. This provides a parameter basis for the subsequent steering control actuator to perform precise steering control on the wheels, thereby enabling the vehicle to travel precisely along the planned trajectory to avoid obstacles and improving the accuracy of vehicle control.

[0066] In some embodiments, a process for updating vehicle pose information is also involved. Figure 5 This is a flowchart illustrating a vehicle pose information update process according to an exemplary embodiment, such as... Figure 5 As shown, the update process includes: Step S501: Based on the driving distance and the vehicle coordinates and vehicle attitude angles of the previous control cycle, calculate the vehicle coordinates and vehicle attitude angles of the current control cycle.

[0067] when At that time, it can be obtained through the arc length of the rear axle center. and the attitude angle of the vehicle in the current control cycle Calculate the X-coordinate increment for the current control cycle. Y-coordinate increment :

[0068]

[0069] when When ≠0, the arc length of the rear axle center can be passed. Vehicle attitude angle increment The attitude angle of the vehicle in the current control cycle Calculate the X-coordinate increment for the current control cycle. Y-coordinate increment :

[0070]

[0071]

[0072] Where R is the vehicle's turning radius.

[0073] Then, based on the vehicle coordinates and vehicle attitude angles of the previous control cycle, as well as the vehicle coordinate increments and vehicle attitude angle increments of the current control cycle, the vehicle coordinates and vehicle attitude angles of the current control cycle are calculated.

[0074] Step S502: Update the vehicle pose information based on the vehicle coordinates and vehicle attitude angles of the current control cycle.

[0075] The calculated vehicle coordinates and attitude angles for the current control cycle are written into the system memory, completing the real-time update of the vehicle's latest pose information. Specifically, the updated pose information can be represented as a multi-dimensional state vector containing position and orientation, and can be used as the new "previous control cycle pose" for recursive calculation in the next cycle.

[0076] In a further embodiment, the updated pose data can also be compared or corrected with positioning data from other positioning or measurement devices on the vehicle, such as inertial measurement units or lidar / visual odometry, to reduce the cumulative drift error caused by the incremental recursion method, thereby outputting more accurate vehicle positioning and attitude parameters.

[0077] Through steps S501-S502, the vehicle pose information for the current control cycle is calculated based on the tire travel distance of the current control cycle and the vehicle pose information of the previous control cycle. The calculation method has low complexity and low latency, ensuring the real-time acquisition of vehicle pose information and guaranteeing the response speed and stability of vehicle obstacle avoidance control. Moreover, the calculation can be completed only by the vehicle's own wheel speed sensor, without the need for other positioning equipment, thus expanding the types of vehicles that can be applied to this solution.

[0078] In some embodiments, the method also involves controlling vehicle movement via a steer-by-wire system. The steer-by-wire system includes a steering wheel actuator and wheel-end actuators. In normal manual driving mode, the steering wheel actuator outputs a corresponding steering control signal based on the driver's steering wheel rotation and transmits it to the wheel-end actuators via a data bus. The wheel-end actuators then control the motors to steer the wheels according to the steering control signal.

[0079] Figure 6 This is a flowchart illustrating a method for controlling vehicle movement via a steer-by-wire system according to an exemplary embodiment, such as... Figure 6 As shown, it includes the following steps: Step S601: Decouple the connection between the steering wheel actuator and the wheel-end actuator.

[0080] After planning the obstacle avoidance path, the vehicle can enter the obstacle avoidance control mode, which allows the vehicle to drive automatically without driver intervention. Specifically, in this embodiment, the vehicle uses a steer-by-wire system. In normal manual driving mode, the steering wheel actuator and wheel-end actuators maintain mechanical and electrical coupling. When the vehicle enters the obstacle avoidance control mode, the system decouples the mechanical and electrical coupling between the steering wheel actuator and the wheel-end actuators via a decoupling command. After decoupling, the reaction force from the wheel ends will not be transmitted back to the steering wheel, and the steering wheel will not rotate in tandem with the rotation of the front wheels.

[0081] Step S602: A steering command is issued to the wheel-end actuator, which includes a target front wheel angle, so that the wheel-end actuator drives the vehicle to steer based on the target front wheel angle.

[0082] Specifically, the vehicle's control unit (such as the vehicle controller or the autonomous driving domain controller) sends a steering command containing the target front wheel angle to the wheel-end actuator via a communication bus. The wheel-end actuator controls the steering motor at the wheel end to drive the wheel to deflect.

[0083] Step S603: When the vehicle reaches the destination, restore the connection between the steering wheel actuator and the wheel-end actuator.

[0084] When the vehicle reaches its destination, the connection procedure is restored, allowing the steering wheel actuator and the front wheel actuator to re-enter a state of mechanical and electrical coupling.

[0085] Through steps S601-S603, the connection between the steering wheel actuator and the wheel-end actuator is decoupled in the obstacle avoidance driving control mode, disconnecting the steering wheel's control function for vehicle steering. This allows the vehicle to automatically avoid obstacles along the planned path without driver intervention, thus avoiding the risks associated with driver control during obstacle avoidance. At the same time, after decoupling, the wheel-end actuator does not need to overcome the resistance caused by steering wheel rotation, reducing the load on the wheel-end actuator and improving steering response speed and accuracy.

[0086] In some embodiments, specific steps for obtaining the vehicle's planned trajectory are also involved. Figure 7 This is a flowchart illustrating an exemplary embodiment for obtaining a vehicle's planned trajectory, such as... Figure 7 As shown, it includes the following steps: Step S701: Perform single-segment path planning based on the starting point information, ending point information, and driving boundary information.

[0087] For example, the turning radius threshold can be the vehicle's limit turning radius determined based on physical parameters such as the vehicle's maximum front wheel steering angle and wheelbase.

[0088] For example, single-segment path planning refers to a planned trajectory that extends from the starting point to the end point without the vehicle needing to change its direction of travel; it is a continuous forward unidirectional trajectory.

[0089] Step S702: Determine whether there exists a single-segment planned trajectory that satisfies the turning radius threshold.

[0090] Specifically, based on the vehicle's starting coordinates, attitude angles, and ending coordinates, as well as the restricted areas defined by the driving boundary information, a single-segment planned trajectory can be calculated using algorithms such as the Reeds-Shepp curve algorithm and the Dubins curve algorithm. Then, based on the vehicle's Ackerman steering angle, wheelbase, track width, instantaneous turning radius, and other parameters, it can be determined whether the single-segment planned trajectory meets the turning radius threshold requirement. If it does, the single-segment planned trajectory is determined to exist; otherwise, it is determined not to exist.

[0091] Step S703: In the absence of a single planned trajectory, multi-segment path planning is performed based on the starting point information, ending point information, and driving boundary information to obtain a multi-segment planned trajectory.

[0092] For example, multi-segment path planning refers to path planning that allows vehicles to make frequent back-and-forth adjustments by switching between forward and reverse directions during the driving process.

[0093] Specifically, a multi-segment planned trajectory consisting of multiple connected sub-trajectories can be found between the starting point and the ending point using a hybrid A algorithm or a fast search random tree algorithm based on kinematic constraints. Several algorithms capable of multi-segment path planning exist in related technologies, and will not be elaborated upon in this embodiment.

[0094] Step S704: Perform collision detection on the single-segment or multi-segment planned trajectory.

[0095] For the generated single-segment or multi-segment planned trajectories, sweep detection can be performed using the vehicle envelope to ensure that the driving path does not collide with the driving boundary.

[0096] Step S705: Determine whether the collision detection passes.

[0097] Step S706: If the collision detection passes, use the single-segment or multi-segment planned trajectory as the planned trajectory.

[0098] If the collision detection fails, the system can return to S703 to re-plan the trajectory.

[0099] Through steps S701-S706, when planning the obstacle avoidance driving path, single-segment path planning with low complexity and simple control logic is prioritized. Multi-segment path planning is only triggered when it cannot be solved, which shortens the path optimization time under normal open road conditions and significantly improves the response efficiency of online real-time planning. By using a turning radius threshold, the generated trajectory is ensured to meet the vehicle's own parameter constraints, improving the physical feasibility of the trajectory. Multi-segment path planning expands the vehicle's obstacle avoidance driving capability in narrow spaces and enhances the vehicle's adaptability to complex scenarios. Collision detection ensures the safety of vehicle driving.

[0100] In some embodiments, specific steps for performing multi-segment path planning are also involved. Figure 8 This is a flowchart illustrating a multi-segment path planning method according to an exemplary embodiment, such as... Figure 8 As shown, it includes the following steps: Step S801: Construct a constraint space based on the starting point information, ending point information, and driving boundary information.

[0101] The constraint space can be determined by the starting position coordinates, attitude angles, and the terminal position coordinates and driving boundary coordinates, so as to limit the spatial range of subsequent path planning search and sampling.

[0102] Step S802: Random sampling is performed in the constrained space to obtain candidate sampling points containing pose information.

[0103] Specifically, a random number generator can be used to sample within a constrained space according to a specific probability distribution, such as a uniform distribution or a Gaussian distribution. Each random sample determines a candidate sampling point, and each candidate sampling point contains position coordinates and attitude angles. Sampling can be terminated when the preset number of samples or sampling points is met.

[0104] Step S803: Based on the collision constraints and reachability constraints of the constraint space, candidate sampling points are screened to obtain feasible sampling points.

[0105] Specifically, collision constraints can be determined by calculating the vehicle's geometric profile and the coordinates and attitude angles of candidate sampling points.

[0106] Specifically, the accessibility constraint can be determined by searching for whether there are connecting lines between candidate sampling points and other candidate sampling points, and whether the constraint condition of the turning radius threshold is met.

[0107] Step S804: Construct a directed graph based on feasible sampling points. The edges of the directed graph are path segments between feasible sampling points, and the cost of the edge is the path length.

[0108] Specifically, the starting point, the ending point, and all the selected feasible sampling points can be added to the topological vertex set of the directed graph. It can then be determined whether any two points in the set can be directly connected in a one-way manner under the constraints of vehicle parameters, in order to construct the edge of the directed graph. The cost of the edge is defined as the actual physical path length generated by the vehicle traveling on the connecting curve.

[0109] Step S805: Obtain the optimal multi-segment path based on directed graph search.

[0110] Specifically, a fast exploratory random tree algorithm RTT or a hybrid A / A algorithm can be used. The algorithm searches for the optimal combination of multiple paths, starting from the starting node and aiming to obtain the optimal multiple path by minimizing the cost to reach the ending node.

[0111] Step S806: Perform nonlinear optimization on the intermediate nodes of the optimal multi-segment path to obtain the multi-segment planned trajectory.

[0112] Specifically, nonlinear optimization is performed on the coordinates and attitude angles of intermediate nodes to minimize the total path length and curvature variation, making the path smoother.

[0113] Through steps S801-S806, the sampling range is limited to a reasonable space by constructing a constraint space, avoiding the increase in data computation caused by blind sampling and improving the convergence speed of the algorithm; feasible sampling points are screened through collision constraints and reachability constraints to avoid wasting computing power; the optimal multi-segment path is obtained through directed graph search, and the actual physical path length is used as the cost of the directed graph edge to output the multi-segment planning trajectory with the shortest global path. Nonlinear optimization ensures the continuity and smoothness of the multi-segment planning trajectory.

[0114] Based on the same inventive concept, this disclosure also provides a vehicle obstacle avoidance driving control device, which includes: The acquisition module is used to acquire the vehicle's starting point information, ending point information, and driving boundary information; The planning module is used to plan an obstacle avoidance driving path based on the starting point information, ending point information, driving boundary information and pre-acquired vehicle parameters, and to obtain the planned trajectory of the vehicle, which includes a single-segment path trajectory or a multi-segment path trajectory. The calculation module is used to calculate the target front wheel steering angle based on the planned trajectory and vehicle parameters; The control module is used to control the vehicle to steer based on the target front wheel angle and update the vehicle's position and posture information.

[0115] The vehicle obstacle avoidance driving control device in this embodiment acquires the vehicle's starting point information, ending point information, and driving boundary information through an acquisition module. A planning module plans an obstacle avoidance driving path based on the starting point information, ending point information, driving boundary information, and vehicle parameters, automatically generating the planned path and activating the closed-loop control function of the vehicle's driving. A calculation module automatically calculates the target front wheel angle at the current moment based on the planned path and the vehicle's current position and posture information. A control module drives the vehicle to automatically steer based on the target front wheel angle and automatically updates the vehicle's position and posture information according to the driving route, executing the next control cycle until the vehicle reaches the destination. This achieves automatic path planning and automatic obstacle avoidance driving without driver intervention, applicable to various vehicle driving scenarios, and solves the problem that drivers with varying driving skills cannot effectively navigate rough road conditions.

[0116] Based on the same inventive concept, this disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the vehicle obstacle avoidance driving control method in the above embodiments.

[0117] Based on the same inventive concept, this disclosure also provides a vehicle, including a control device, which is used to execute the steps of the vehicle obstacle avoidance driving control method in the above embodiments.

[0118] In a further embodiment, the vehicle also includes an interactive interface, an image acquisition device, and a steer-by-wire system. The image acquisition device is used to acquire environmental images of the vehicle in a stationary state and send them to the interactive interface for display. The interactive interface is used to acquire the driving boundary and endpoint position drawn on the environmental image. The steer-by-wire system is used to respond to the steering command of the control device and drive the vehicle to steer based on the target front wheel angle in the steering command.

[0119] In this embodiment, the vehicle acquires environmental images of its stationary state through an image acquisition device, intuitively reflecting the distribution of obstacles around the vehicle. Since the environmental images can be acquired directly through the image acquisition device, no additional environmental sensing devices are needed, reducing vehicle hardware costs. By displaying this environmental image on the in-vehicle interactive interface, the driver can intuitively perceive the shape and location of obstacles in the surrounding environment. Simple touch operations on the human-machine interface allow for quick marking of driving boundaries and endpoints, improving the convenience of human-machine collaborative obstacle avoidance. This also avoids potential misjudgments that may occur when relying solely on image recognition algorithms to identify obstacles and driving boundaries, reducing driving risks. The vehicle is controlled automatically by a steer-by-wire system, enabling automatic obstacle avoidance along a planned path without driver intervention. This avoids the risks associated with driver control during obstacle avoidance and improves steering response speed and accuracy.

[0120] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0121] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0122] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A vehicle obstacle avoidance travel control method characterized by comprising: include: The system acquires an environmental image of the vehicle while it is stationary and displays it on the vehicle's interactive interface. The environmental image includes the vehicle's position, environmental obstacles, and the destination. Based on the interactive interface, obtain the driving boundary and destination position drawn on the environmental image; Based on the coordinate system corresponding to the environmental image, as well as the vehicle position, the driving boundary, and the destination position, the starting point information, the destination information, and the driving boundary information are obtained. Based on the starting point information, the ending point information, the driving boundary information and the pre-acquired vehicle parameters, an obstacle avoidance driving path is planned, and the planned trajectory of the vehicle is obtained. The planned trajectory includes a single-segment path trajectory or a multi-segment path trajectory. Based on the planned trajectory and the vehicle parameters, the target front wheel steering angle is calculated; The vehicle is controlled to steer based on the target front wheel angle, and the vehicle's position and posture information is updated.

2. The method of claim 1, wherein, The vehicle parameters include front track width, rear track width, and wheelbase. The target front wheel steering angle calculated based on the planned trajectory and the vehicle parameters includes: Obtain the travel distance of each tire in the current control cycle; The vehicle's turning radius is calculated based on the driving distance and the rear wheel track. The target front wheel angle is calculated based on the vehicle's turning radius, the front track width, and the wheelbase.

3. The method of claim 2, wherein, The updating of the vehicle pose information includes: Based on the travel distance and the vehicle coordinates and vehicle attitude angles of the previous control cycle, the vehicle coordinates and vehicle attitude angles of the current control cycle are calculated. The vehicle pose information is updated based on the vehicle coordinates and vehicle attitude angles of the current control cycle.

4. The method of claim 1, wherein, The vehicle includes a steer-by-wire system, which includes a steering wheel actuator and wheel-end actuators. Controlling the vehicle to steer based on the target front wheel angle includes: Decouple the connection between the steering wheel actuator and the wheel-end actuator; A steering command is issued to the wheel-end actuator, the steering command including the target front wheel angle, so that the wheel-end actuator drives the vehicle to steer based on the target front wheel angle; When the vehicle reaches its destination, the connection between the steering wheel actuator and the wheel-end actuator is restored.

5. The method of claim 1, wherein, The vehicle parameters include a turning radius threshold. The process of planning an obstacle avoidance path based on the starting point information, the ending point information, the driving boundary information, and the pre-acquired vehicle parameters, and obtaining the vehicle's planned trajectory, includes: Based on the starting point information, the ending point information, and the driving boundary information, single-segment path planning is performed to determine whether there is a single-segment planned trajectory that satisfies the turning radius threshold. If the single-segment planned trajectory does not exist, multi-segment path planning is performed based on the starting point information, the ending point information, and the driving boundary information to obtain multiple planned trajectories. Collision detection is performed on the single-segment or multi-segment planned trajectory; If the collision detection passes, the single-segment planned trajectory or the multi-segment planned trajectory will be used as the planned trajectory.

6. The method of claim 5, wherein, The multi-segment path planning based on the starting point information, the ending point information, and the driving boundary information yields multiple planned trajectories, including: A constraint space is constructed based on the starting point information, the ending point information, and the driving boundary information; Random sampling is performed within the constrained space to obtain candidate sampling points containing pose information; Based on the collision constraints and reachability constraints of the constraint space, the candidate sampling points are filtered to obtain feasible sampling points; A directed graph is constructed based on the feasible sampling points, where the edges of the directed graph are path segments between the feasible sampling points, and the cost of each edge is the path length. The optimal multi-segment path is obtained based on the directed graph search. The intermediate nodes of the optimal multi-segment path are nonlinearly optimized to obtain the multi-segment planned trajectory.

7. A computer-readable storage medium having stored thereon a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the vehicle obstacle avoidance driving control method according to any one of claims 1 to 6.

8. A vehicle characterized by comprising: The vehicle includes a control device for performing the vehicle obstacle avoidance driving control method according to any one of claims 1-6.

9. The vehicle of claim 8, wherein, The vehicle also includes an interactive interface, an image acquisition device, and a steer-by-wire system. The image acquisition device is used to acquire environmental images of the vehicle in a stationary state and send them to the interactive interface for display. The interactive interface is used to acquire the driving boundary and endpoint position drawn on the environmental image. The steer-by-wire system is used to respond to the steering command of the control device and drive the vehicle to steer based on the target front wheel angle in the steering command.

Images