Vehicle avoidance method and device
By detecting the target vehicle's status data and generating a reversing path, the safety problem caused by the lack of reversing avoidance ability when the vehicle is driving at low speed is solved, realizing automated reversing avoidance and improving driving safety.
Patent Information
- Application Number
- CN202610385650.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-03-26
- Publication Date
- 2026-05-08
AI Technical Summary
Existing technology lacks the ability to automatically reverse and avoid large vehicles that suddenly encroach on the lane when the vehicle is traveling at low speed, resulting in lower driving safety, especially on narrow roads or construction sections, where conventional braking or lateral avoidance cannot prevent collisions.
By detecting the status data of the target vehicle, it is determined whether the forced reversing avoidance mode is triggered, a reversing path is generated, and the vehicle is controlled to reverse along the path. This involves the coordinated work of environmental perception, decision control, and vehicle control modules to ensure safe avoidance.
It enables automatic obstacle avoidance when obstacles are detected, improving vehicle driving safety and avoiding the risk of collisions caused by tense operation.
Smart Images
Figure CN121989928A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of intelligent driving technology, and more specifically, to a vehicle avoidance method and device. Background Technology
[0002] Currently, vehicle collision avoidance technology mainly revolves around functions such as forward collision warning, automatic emergency braking, lane keeping assist, and automatic parking. Existing technologies already include numerous trajectory planning schemes for vehicle reversing control and obstacle avoidance. For example, one publicly disclosed vehicle reversing collision avoidance control method assesses collision risk by acquiring obstacle height and vehicle rear suspension height, and then performs reversing adjustments, even executing an "extreme reversing mode" to adjust vehicle posture when conventional adjustments fail. Another vehicle reversing driving control method analyzes historical driving trajectories and obstacle outlines to plan lateral and longitudinal reversing trajectories to avoid collisions. Furthermore, for avoiding static obstacles, there are also schemes that combine planning a "reversing path" and a "secondary detour path" to improve safety. These schemes primarily focus on parking, low-speed maneuvering, or scenarios involving static / quasi-static obstacles. Their decision-making premise is that the vehicle is already in or about to enter a reversing state, and the core objective is to optimize the reversing path. For dynamic and dangerous scenarios where a vehicle is traveling forward at low speed and suddenly encounters a large vehicle encroaching on its lane with no lateral space for avoidance, existing technologies lack the decision-making logic and control strategy to actively switch to reverse mode for avoidance. More advanced collision avoidance systems are beginning to consider the motion information of traffic participants from multiple directions. For example, a rear-end collision avoidance system for vehicles behind can control the vehicle to perform avoidance maneuvers by integrating the motion information of vehicles in front, behind, and to the sides to deal with the risk of a rear-end collision. Another patent proposes to comprehensively assess the distance required for steering and braking to avoid obstacles based on the distance between the vehicle and the obstacle, thereby deciding whether to execute lateral or longitudinal avoidance. Although such systems consider the dynamic environment, their response strategies are still limited to steering, braking, or acceleration within the forward range, or they treat reversing as only a sub-step in the parking process. The concept of "actively engaging reverse gear and reversing a controllable distance in a specific dangerous forward scenario" has not yet been defined and implemented as a fundamental active avoidance strategy. For example, related technologies propose distributing wheel torque by independently controlling the torque of each drive motor, enabling the vehicle to avoid collisions without turning the steering wheel, thus solving the "steering wheel fatigue" problem. Torque distribution collision avoidance technology primarily optimizes the execution method of steering avoidance but does not expand the degrees of freedom for avoidance (it remains limited to forward or lateral movement). In summary, in existing technologies, when a vehicle is traveling at low speed in restricted environments such as narrow roads, alleys, or construction zones, and faces a large vehicle (such as a truck or construction vehicle) suddenly appearing ahead that completely or partially encroaches on the vehicle's lane due to its size, making conventional braking insufficient to avoid a collision, and lacking sufficient space for lateral steering avoidance, the vehicle lacks an automated and safe reverse (reversing) avoidance capability. Drivers are prone to misoperation due to tension in such sudden situations, posing a high risk of collision or secondary accidents.
[0003] There is currently no effective solution to the above problems. Summary of the Invention
[0004] This application provides a vehicle avoidance method and apparatus to at least solve the technical problem of low vehicle driving safety due to the lack of a reversing avoidance method during vehicle operation.
[0005] According to one aspect of the embodiments of this application, a vehicle avoidance method is provided, comprising: detecting state data of a target vehicle, wherein the state data includes at least: driving state data of the target vehicle and surrounding environment data of the target vehicle; determining whether the target vehicle has triggered a forced reversing avoidance mode based on the state data, wherein the forced reversing avoidance mode is used to control the target vehicle to reverse and avoid an obstacle; if the target vehicle triggers the forced reversing avoidance mode, determining a reversing path of the target vehicle based on the state data and the lane where the target vehicle is located; and controlling the target vehicle to reverse according to the reversing path of the target vehicle.
[0006] Optionally, determining whether the target vehicle triggers a forced reversing avoidance mode based on the status data includes: determining whether the target vehicle meets a first preset condition based on the status data, wherein the first preset condition includes at least: the target vehicle's speed is less than a preset speed threshold, an obstacle larger than a preset volume is detected in front of the target vehicle, the relative distance between the target vehicle and the obstacle is less than a preset distance, and the collision duration between the target vehicle and the obstacle is less than a preset duration; if the target vehicle meets the first preset condition, determining that the target vehicle has a collision risk; if the target vehicle has a collision risk, determining whether the target vehicle has a lateral avoidance path; if the target vehicle does not have a lateral avoidance path, determining that the target vehicle triggers a forced reversing avoidance mode.
[0007] Optionally, the method further includes: obtaining from the state data whether there is an obstacle on the side of the target vehicle, the minimum turning radius of the target vehicle, and the width of the lane where the target vehicle is located and the width of the adjacent lane; determining the minimum lateral displacement required for the target vehicle to avoid an obstacle based on the minimum turning radius of the target vehicle, and determining the available lateral distance of the target vehicle based on the width of the lane where the target vehicle is located and the width of the adjacent lane; and determining that the target vehicle does not have a lateral avoidance path if the minimum lateral displacement required for the target vehicle to avoid an obstacle is greater than the available lateral distance of the target vehicle.
[0008] Optionally, after the target vehicle determines that it has triggered the forced reversing avoidance mode, the method further includes: outputting alarm information, wherein the alarm information is used to instruct the target vehicle to switch to the forced reversing avoidance mode; acquiring the target vehicle's operation instructions within a preset time period; determining that the target vehicle has a first operation when the operation instructions indicate that the target vehicle's steering torque is greater than a preset torque threshold or the target vehicle's steering angle change rate is greater than a preset steering angle change rate threshold within the preset time period; acquiring the absolute value of the accelerator pedal opening of the target vehicle within the preset time period, and determining that the target vehicle is in a second operation state when the absolute value of the accelerator pedal opening is greater than a preset absolute value threshold; determining that the target vehicle has passed a first safety detection when the target vehicle has not performed a first operation and is not in a second operation state; determining that the target vehicle has passed a second safety detection when there is no obstacle behind the target vehicle; and determining that the target vehicle has switched to the forced reversing avoidance mode when the target vehicle passes both the first and second safety detections simultaneously.
[0009] Optionally, determining the reversing path of the target vehicle based on the status data and the lane where the target vehicle is located includes: determining the position where the target vehicle can avoid the obstacle based on the status data; determining the position where the target vehicle is when it switches to the forced reversing avoidance mode as the starting point of the reversing path, and determining the position where the target vehicle can avoid the obstacle as the ending point of the reversing path; and generating the reversing path with the center line of the lane where the target vehicle is located as the center line of the reversing path of the target vehicle.
[0010] Optionally, the method further includes: generating multiple candidate paths when there are obstacles on the reversing path; obtaining the target distance between the point farthest from the centerline of the reversing path and the centerline of the reversing path in each candidate path, the distance of the sampling point in each candidate path from the obstacle, and the rate of curvature change of each candidate path; determining the cost function value of each candidate path based on the target distance, the distance of the sampling point in each candidate path from the obstacle, and the rate of curvature change of each candidate path; and selecting the candidate path with the smallest cost function value from the candidate paths as the corrected reversing path.
[0011] Optionally, after controlling the target vehicle to reverse along the target vehicle's reversing path, the method further includes: if the distance between the obstacle and the target vehicle is detected to be greater than a preset safe distance, controlling the target vehicle to decelerate and stop at a preset acceleration; after detecting the manual control signal, exiting the forced reversing avoidance mode and responding to the manual control signal; and stopping immediately if a collision risk is detected behind the target vehicle.
[0012] According to another aspect of the embodiments of this application, a vehicle avoidance system is also provided, including: an environmental perception module, a decision control module, and a vehicle control module; the environmental perception module is used to detect the state data of a target vehicle, wherein the state data includes at least: driving state data of the target vehicle and surrounding environment data of the target vehicle; the decision control module is used to determine whether the target vehicle triggers a forced reversing avoidance mode based on the state data, and, if the target vehicle triggers the forced reversing avoidance mode, to determine the reversing path of the target vehicle based on the state data and the lane where the target vehicle is located, wherein the forced reversing avoidance mode is used to control the target vehicle to reverse and avoid obstacles; the vehicle control module is used to control the target vehicle to reverse according to the reversing path of the target vehicle.
[0013] According to another aspect of the embodiments of this application, a computer device is also provided, including: a memory and a processor, wherein the memory is used to store program instructions; and the processor, connected to the memory, is used to execute the above-described vehicle avoidance method.
[0014] According to another aspect of the embodiments of this application, a vehicle is also provided, including: a vehicle avoidance system, wherein the vehicle avoidance system is used to perform the above-described vehicle avoidance method.
[0015] In this embodiment, the system detects the state data of a target vehicle, which includes at least: the driving state data of the target vehicle and the surrounding environment data of the target vehicle. Based on the state data, it determines whether the target vehicle has triggered a forced reversing obstacle avoidance mode, wherein the forced reversing obstacle avoidance mode controls the target vehicle to reverse and avoid obstacles. If the target vehicle triggers the forced reversing obstacle avoidance mode, the system determines the reversing path of the target vehicle based on the state data and the lane in which the target vehicle is located. By controlling the target vehicle to reverse according to the reversing path, the forced reversing obstacle avoidance mode is triggered through the vehicle's state data, achieving the goal of automatically avoiding obstacles while they are detected. This improves vehicle driving safety and solves the technical problem of low vehicle driving safety due to the lack of a reversing obstacle avoidance method during vehicle operation. Attached Figure Description
[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:
[0017] Figure 1 This is a hardware structure block diagram of a computer terminal (or mobile device) for a vehicle avoidance method according to an embodiment of this application;
[0018] Figure 2 This is a flowchart of a vehicle avoidance method according to this application;
[0019] Figure 3 This is a flowchart of another optional vehicle avoidance method according to an embodiment of this application;
[0020] Figure 4 This is a flowchart of an optional forced reversing avoidance mode determination according to an embodiment of this application;
[0021] Figure 5 This is an optional reversing route planning flowchart according to an embodiment of this application;
[0022] Figure 6 This is a schematic diagram of an optional vehicle avoidance system structure according to an embodiment of this application;
[0023] Figure 7 This is an execution flowchart of an optional vehicle control module controlling a target vehicle according to an embodiment of this application;
[0024] Figure 8 This is a schematic diagram of an optional vehicle avoidance device according to an embodiment of this application. Detailed Implementation
[0025] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.
[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application 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 this application 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 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.
[0027] According to an embodiment of this application, an embodiment of a vehicle avoidance method is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.
[0028] The methods and embodiments provided in this application can be executed on mobile terminals, computer terminals, or similar computing devices. Figure 1 A hardware block diagram of a computer terminal (or mobile device) for implementing a vehicle avoidance method is shown. Figure 1 As shown, the computer terminal 10 (or mobile device 10) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission module 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.
[0029] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).
[0030] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the vehicle avoidance method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby implementing the above-mentioned application vulnerability detection method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
[0031] The transmission module 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission module 106 includes a network interface controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission module 106 may be a radio frequency (RF) module, used for wireless communication with the Internet.
[0032] The display may be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).
[0033] According to an embodiment of this application, an embodiment of a vehicle avoidance method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.
[0034] Figure 2This is a flowchart of a vehicle avoidance method according to an embodiment of this application, such as... Figure 2 As shown, the method includes the following steps:
[0035] Step S202: Detect the status data of the target vehicle, wherein the status data includes at least: the driving status data of the target vehicle and the surrounding environment data of the target vehicle;
[0036] In step S202, the target vehicle's state data can be acquired through onboard sensing devices. This data includes at least the vehicle's speed, and the surrounding environment data includes at least whether obstacles are detected around the vehicle, and the relative distance and speed between the vehicle and the obstacles. For example: forward-facing millimeter-wave radar and a visual camera: identify the width, center position, trajectory, and relative distance of obstacles ahead (especially large vehicles); surround-view cameras: acquire pixel-level outlines of static obstacles such as lane boundaries, curbs, guardrails, walls, and green belts on both sides of the vehicle; ultrasonic radar and lateral radar: measure the precise distance (accuracy ±5cm) between the vehicle's left and right sides and adjacent static / dynamic obstacles (such as parked vehicles, pedestrians, and bicycles); high-precision maps: provide prior information such as lane line type (solid / dashed), road width, and road type (urban lanes / highways / construction zones).
[0037] Step S204: Determine whether the target vehicle has triggered the forced reversing obstacle avoidance mode based on the status data, wherein the forced reversing obstacle avoidance mode is used to control the target vehicle to reverse and avoid obstacles;
[0038] In step S204, the forced reversing obstacle avoidance mode can be applied in practical scenarios as the vehicle is in motion or when the vehicle is stopped (at zero speed). For example, when the vehicle encounters a dynamic obstacle while in motion, such as an oncoming or lateral vehicle, or a rolling obstacle.
[0039] Step S206: When the target vehicle triggers the forced reversing avoidance mode, determine the reversing path of the target vehicle based on the status data and the lane where the target vehicle is located.
[0040] Step S208: Control the target vehicle to reverse according to the target vehicle's reversing path.
[0041] Through the above steps, the target vehicle's status data is detected, including at least: the target vehicle's driving status data and the target vehicle's surrounding environment data; based on the status data, it is determined whether the target vehicle triggers a forced reversing avoidance mode, wherein the forced reversing avoidance mode is used to control the target vehicle to reverse and avoid obstacles; if the target vehicle triggers the forced reversing avoidance mode, the target vehicle's reversing path is determined based on the status data and the target vehicle's lane; the target vehicle is controlled to reverse according to the target vehicle's reversing path. By triggering the forced reversing avoidance mode through the vehicle's status data, the purpose of automatically avoiding obstacles while detecting them is achieved, thereby improving vehicle driving safety and solving the technical problem of low vehicle driving safety due to the lack of reversing avoidance methods during vehicle operation.
[0042] To better understand the vehicle avoidance method proposed in the embodiments of this application Figure 3 Another method of vehicle avoidance is shown, such as Figure 3 As shown, the process includes: after the system is powered on, continuously detecting whether the "forced reversing avoidance trigger conditions" are met (i.e., low-speed forward movement, a large obstacle in front, insufficient braking distance, and no lateral avoidance space). Specifically, determining whether the target vehicle triggers the forced reversing avoidance mode based on the status data includes: determining whether the target vehicle meets a first preset condition based on the status data, wherein the first preset condition includes at least: the target vehicle's speed is less than a preset speed threshold, an obstacle larger than a preset volume is detected in front of the target vehicle, the relative distance between the target vehicle and the obstacle is less than a preset distance, and the collision duration between the target vehicle and the obstacle is less than a preset duration; if the target vehicle meets the first preset condition, determining that the target vehicle has a collision risk; if the target vehicle has a collision risk, determining whether the target vehicle has a lateral avoidance path; if the target vehicle does not have a lateral avoidance path, determining that the target vehicle triggers the forced reversing avoidance mode.
[0043] The determination of whether a target vehicle has lateral avoidance space (path) can be made in the following way: From the state data, we obtain whether there are obstacles to the side of the target vehicle, the minimum turning radius of the target vehicle, and the width of the lane where the target vehicle is located and the width of the adjacent lane; based on the minimum turning radius of the target vehicle, we determine the minimum lateral displacement required for the target vehicle to avoid an obstacle, and based on the width of the lane where the target vehicle is located and the width of the adjacent lane, we determine the available lateral distance of the target vehicle; if the minimum lateral displacement required for the target vehicle to avoid an obstacle is greater than the available lateral distance of the target vehicle, we determine that the target vehicle does not have a lateral avoidance path.
[0044] Figure 4 The following describes the judgment process for an optional forced reversing avoidance mode trigger condition, such as... Figure 4 As shown, it includes:
[0045] Step 1, Main Condition Judgment: 1. Vehicle speed is less than a preset speed threshold; 2. A large target vehicle is detected forward; 3. The relative distance between the target vehicle and the large target vehicle is less than the dynamic safety distance; 4. The collision duration, determined based on the relative speed between the target vehicle and the large target vehicle, is less than a preset duration (the duration required for the target vehicle to collide with the obstacle is the collision duration). If all main conditions are met, a lateral avoidance feasibility assessment is triggered; otherwise, it is not. It should be noted that during the lateral avoidance feasibility assessment, the width of the current lane and adjacent lanes is analyzed; static or dynamic obstacles on the side are detected, and the minimum turning radius of the target vehicle is calculated. Based on the above conditions, it is determined whether a feasible lateral avoidance path exists for the target vehicle: if a feasible lateral avoidance path exists, lateral avoidance is prioritized; if no feasible lateral avoidance path exists, a forced reversing avoidance strategy request is generated to generate a reversing path.
[0046] Understandably, after the target vehicle determines that it has triggered the forced reversing avoidance mode, an alarm message is output, wherein the alarm message is used to instruct the target vehicle to switch to the forced reversing avoidance mode; the operation instructions of the target vehicle within a preset time period are obtained; if the operation instructions indicate that the steering torque of the target vehicle is greater than a preset torque threshold or the steering angle change rate of the target vehicle is greater than a preset steering angle change rate threshold within the preset time period, it is determined that the target vehicle has performed a first operation (aggressive operation); the absolute value of the accelerator pedal opening of the target vehicle within the preset time period is obtained, and if the absolute value of the accelerator pedal opening is greater than a preset absolute value threshold, it is determined that the target vehicle is in a second operation (deep acceleration) state; if the target vehicle does not perform the first operation and is not in the second operation state, it is determined that the target vehicle has passed the first safety detection; if there is no obstacle behind the target vehicle, it is determined that the target vehicle has passed the second safety detection; if the target vehicle passes both the first safety detection and the second safety detection simultaneously, it is determined that the target vehicle has switched to the forced reversing avoidance mode.
[0047] In some embodiments of this application, the specific steps for determining the reversing path of the target vehicle based on the state data and the lane where the target vehicle is located are as follows: The position where the target vehicle can avoid the obstacle is determined based on the state data; the position where the target vehicle is when it switches to the forced reversing avoidance mode is determined as the starting point of the reversing path, and the position where the target vehicle can avoid the obstacle is determined as the ending point of the reversing path; the centerline of the lane where the target vehicle is located is used as the centerline of the reversing path to generate the reversing path. Where an obstacle exists on the reversing path, multiple candidate paths are generated; the target distance between the point farthest from the centerline of the reversing path in each candidate path and the centerline of the reversing path, the distance of the sampling point in each candidate path from the obstacle, and the rate of curvature change of each candidate path are obtained respectively; the cost function value of each candidate path is determined based on the target distance, the distance of the sampling point in each candidate path from the obstacle, and the rate of curvature change of each candidate path; the candidate path with the smallest cost function value is selected from the candidate paths and determined as the corrected reversing path.
[0048] like Figure 5 As shown, the process includes: after entering the path planning stage, acquiring the target vehicle's state data, including but not limited to: the target vehicle's position, attitude, and the environmental map behind the target vehicle, and generating a reversing path (initial reversing path) based on the state data. The reversing path is a straight path or a gentle curve path generated with the center line of the current lane where the target vehicle is located as a reference. In practical application scenarios, constraints can also be added, such as: setting lateral safety distance (the minimum distance from the outer edge of the vehicle wheel to static obstacles such as road markings, curbs, and guardrails), longitudinal safety distance (to prevent rear-end collisions, ensuring a safe distance between the rear of the vehicle and any dynamic obstacles during reversing), and vertical safety distance (to prevent scraping against protrusions such as curbs, speed bumps, and manhole covers during reversing, monitored by ultrasonic radar). After generating the reversing path, dynamic obstacles on the path are predicted. These predicted dynamic or static obstacles are projected into the reversing path space to determine if there is a risk of collision between the target vehicle and the obstacle. If a collision risk exists, the reversing path is replanned, for example, by correcting it based on a cost function. This cost function includes the degree to which the candidate path deviates from the road centerline, the distance between the target vehicle and the obstacle, and the rate of curvature change of the reversing path. An optimization algorithm is then used to select the optimal path, and a smooth sequence of path points (position, speed, and steering angle of each path point) is output after the optimal path is selected. The target vehicle is then controlled to reverse according to the corrected reversing path.
[0049] After controlling the target vehicle to reverse along its reversing path, if the distance between the obstacle and the target vehicle is detected to be greater than a preset safe distance, the target vehicle is controlled to decelerate and stop at a preset acceleration; after detecting the manual control signal, the forced reversing avoidance mode is exited and the manual control signal is responded to; if a collision risk is detected behind the target vehicle, the vehicle stops immediately.
[0050] To better understand the vehicle avoidance method proposed in this application, the following example illustrates the process: Assume a sedan equipped with this system is traveling at 20 km / h on a narrow, two-way single-lane road. Suddenly, a large dump truck appears at a bend ahead, with part of its body crossing the center line and encroaching on the sedan's lane. The system instantly performs the following actions: Perception and Recognition: The forward-facing radar and camera detect the large vehicle target, calculating a relative distance of only 15 meters and a TTC (Traffic Time Tolerance) of less than 2 seconds due to the relative speed. Simultaneously, the lateral sensors detect a curb / wall on the right side of the road and an oncoming lane with continuous traffic on the left. Decision Trigger: The system determines: ① Vehicle speed is below a threshold; ② A large vehicle is ahead; ③ The distance is too close, and the braking distance may be insufficient; ④ There is no safe space to avoid the vehicle laterally. If all conditions are met, the "Forced Reverse Avoidance Preparation" mode is triggered. Safety Confirmation and Execution: The system issues a voice and icon warning via HMI stating, "Reversing to avoid a collision is imminent; please remain calm." Simultaneously, it checks that the driver has not made any sudden steering wheel movements or pressed the accelerator hard, and confirms that there are no vehicles or pedestrians within 20 meters behind. After confirmation, the system smoothly decelerates the vehicle to 5 km / h and automatically shifts the gear from D to R. Path Planning and Reversing: Using the current lane lines as a reference, the system plans a straight reverse path, maintaining a safe distance of 0.5 meters from the curb. The vehicle begins to automatically reverse at a speed of 3-5 km / h, with the EPS making minor adjustments to the direction based on the path to maintain a straight line. Exiting Mode: After reversing approximately 10 meters, the dump truck ahead has completely passed, and the side sensors indicate a safe gap on the left. The system determines the threat has been eliminated, automatically controls the vehicle to a smooth stop, then shifts the gear back to D and prompts, "Avoidance complete; please proceed with caution." The system exits the special mode and resumes normal monitoring.
[0051] It is understood that the vehicle avoidance method in this application embodiment is also applicable to the quantitative definition and comprehensive identification algorithm of the specific dangerous scenario of "insufficient braking distance due to large obstacles in front and insufficient lateral avoidance space" at low speeds. The automatic decision-making mechanism of the "forward-reverse" avoidance strategy: After identifying the above core scenario, it actively abandons forward braking or steering and decides to adopt reverse as the optimal avoidance strategy. Fully automatic mode switching and execution control sequence: A complete control sequence and method for automatically, smoothly, and safely switching from forward gear (D) to reverse gear (R) and controlling the vehicle to reverse along the planned path, including deceleration point, shift timing, reverse speed curve, and lateral holding control strategy. Dynamic safety monitoring during reverse avoidance: Real-time monitoring and assessment of newly emerging risks behind during reverse reversing, and corresponding interruption or adjustment strategies (such as emergency braking, pause, and waiting). Before, during, and after automatic system intervention, it provides warnings and status prompts to the driver, and an interactive process for safely handing over control when the driver forcibly intervenes.
[0052] In practical applications, deep learning models can also be used to process multi-frame perception data end-to-end and directly output the decision probability of "needing to reverse and avoid".
[0053] In this application embodiment, the optimized algorithm path planning can be replaced by a spiral or arc path with a preset curvature in simple scenarios, and tracked by algorithms such as Pure Pursuit. For electric vehicles equipped with four independent drive motors, instead of shifting gears through a traditional gearbox, the torque direction of a specific motor can be directly reversed, combined with differential steering to achieve "diagonal" or "rotational" avoidance similar to reversing.
[0054] like Figure 6 As shown, the vehicle avoidance method provided in this application embodiment is also applied to a vehicle avoidance system provided in this application embodiment, including: an environmental perception module 60, a decision control module 62, and a vehicle control module 64;
[0055] The environmental perception module 60 is used to detect the status data of the target vehicle, wherein the status data includes at least: the driving status data of the target vehicle and the surrounding environment data of the target vehicle.
[0056] The decision control module 62 is used to determine whether the target vehicle triggers the forced reversing avoidance mode based on the status data, and to determine the reversing path of the target vehicle based on the status data and the lane where the target vehicle is located when the target vehicle triggers the forced reversing avoidance mode. The forced reversing avoidance mode is used to control the target vehicle to reverse and avoid obstacles.
[0057] The vehicle control module 64 is used to control the target vehicle to reverse according to the target vehicle's reversing path.
[0058] In practical applications, the environmental perception module 60 integrates a forward-facing camera, millimeter-wave radar, ultrasonic radar, and surround-view camera to detect and identify obstacles (especially large vehicles), lane lines, and drivable area boundaries in front of, to the sides, and behind the vehicle in real time. It also calculates the size, relative position, and speed of obstacles, as well as the distance between the vehicle and each obstacle. The decision control module 62, acting as the system's brain, receives data from the environmental perception module and acquires the vehicle's current state (vehicle speed, gear, steering angle, yaw rate, etc.). Internally, it implements scenario risk assessment algorithms, obstacle avoidance strategy decision-making algorithms, and reversing path planning algorithms. The vehicle control module 64 receives instructions from the decision control module 62 and coordinates the control of the powertrain (motor / engine), automatic transmission, Electronic Stability Program (ESP), Electric Power Steering (EPS), and other actuators to precisely execute deceleration, gear shifting, steering, and acceleration / braking control.
[0059] The system also includes a human-machine interface (HMI) module, which includes instrument panel graphic displays and audio prompts to inform the driver of the system's status (such as "preparing to start reversing to avoid obstacles" or "reversing to avoid obstacles") and to request the driver to take over when necessary.
[0060] Figure 7 The document also illustrates the execution process of the vehicle control module controlling the target vehicle, including: parsing instructions and, based on the parsing results, controlling the longitudinal control submodule, lateral control submodule, and gear and drive submodule of the target vehicle respectively: deceleration, steering, and gear shifting. Further control is then performed based on system status feedback.
[0061] The vehicle avoidance method provided in this application embodiment can also be applied to a vehicle avoidance device provided in this application embodiment, such as... Figure 8 As shown, it includes:
[0062] The detection module 80 is used to detect the status data of the target vehicle, wherein the status data includes at least: the driving status data of the target vehicle and the surrounding environment data of the target vehicle;
[0063] The judgment module 82 is used to determine whether the target vehicle has triggered the forced reversing avoidance mode based on the status data, wherein the forced reversing avoidance mode is used to control the target vehicle to reverse and avoid obstacles;
[0064] The determination module 84 is used to determine the reversing path of the target vehicle based on the status data and the lane where the target vehicle is located when the target vehicle triggers the forced reversing avoidance mode.
[0065] The control module 86 is used to control the target vehicle to reverse according to the target vehicle's reversing path.
[0066] The judgment module 82 includes a judgment submodule, used to determine whether the target vehicle has triggered a forced reversing avoidance mode based on the status data, including: determining whether the target vehicle meets a first preset condition based on the status data, wherein the first preset condition includes at least: the target vehicle's speed is less than a preset speed threshold, an obstacle larger than a preset volume is detected in front of the target vehicle, the relative distance between the target vehicle and the obstacle is less than a preset distance, and the collision duration between the target vehicle and the obstacle is less than a preset duration; if the target vehicle meets the first preset condition, determining that the target vehicle has a collision risk; if the target vehicle has a collision risk, determining whether the target vehicle has a lateral avoidance path; if the target vehicle does not have a lateral avoidance path, determining that the target vehicle has triggered a forced reversing avoidance mode.
[0067] The judgment submodule further includes: a judgment unit, used to obtain from the state data whether there is an obstacle on the side of the target vehicle, the minimum turning radius of the target vehicle, and the width of the lane where the target vehicle is located and the adjacent lane; determine the minimum lateral displacement required for the target vehicle to avoid the obstacle based on the minimum turning radius of the target vehicle, and determine the available lateral distance of the target vehicle based on the width of the lane where the target vehicle is located and the adjacent lane; if the minimum lateral displacement required for the target vehicle to avoid the obstacle is greater than the available lateral distance of the target vehicle, determine that the target vehicle does not have a lateral avoidance path.
[0068] The aforementioned vehicle avoidance device further includes: a control submodule, configured to: output alarm information after the target vehicle determines that it has triggered a forced reversing avoidance mode, wherein the alarm information is used to instruct the target vehicle to switch to the forced reversing avoidance mode; acquire the target vehicle's operation instructions within a preset time period; determine that the target vehicle has a first operation if the operation instructions indicate that the target vehicle's steering torque is greater than a preset torque threshold or the target vehicle's steering angle change rate is greater than a preset steering angle change rate threshold within the preset time period; acquire the absolute value of the accelerator pedal opening of the target vehicle within the preset time period, and determine that the target vehicle is in a second operation state if the absolute value of the accelerator pedal opening is greater than a preset absolute value threshold; determine that the target vehicle has passed a first safety detection if the target vehicle has not performed a first operation and is not in a second operation state; determine that the target vehicle has passed a second safety detection if there is no obstacle behind the target vehicle; and determine that the target vehicle switches to the forced reversing avoidance mode if the target vehicle passes both the first and second safety detections simultaneously.
[0069] The control submodule includes a determining unit, configured to determine the reversing path of the target vehicle based on the status data and the lane where the target vehicle is located, including: determining the position where the target vehicle can avoid the obstacle based on the status data; determining the position where the target vehicle is when it switches to the forced reversing avoidance mode as the starting point of the reversing path, and determining the position where the target vehicle can avoid the obstacle as the ending point of the reversing path; and generating the reversing path with the center line of the lane where the target vehicle is located as the center line of the reversing path of the target vehicle. In this process, when obstacles exist on the reversing path, multiple candidate paths are generated. The target distance between the point furthest from the centerline of the reversing path and the centerline, the distance of a sample point in each candidate path from the obstacle, and the rate of curvature change of each candidate path are obtained. A cost function value for each candidate path is determined based on the target distance, the distance of the sample point in each candidate path from the obstacle, and the rate of curvature change of each candidate path. The candidate path with the smallest cost function value is selected as the corrected reversing path. After controlling the target vehicle to reverse along the target vehicle's reversing path, if the distance between the obstacle and the target vehicle is detected to be greater than a preset safety distance, the target vehicle is controlled to decelerate and stop at a preset acceleration. Upon detecting a manual control signal, the forced reversing avoidance mode is exited, and the manual control signal is responded to. If a collision risk is detected behind the target vehicle, the vehicle stops immediately.
[0070] According to another aspect of the embodiments of this application, a non-volatile storage medium is also provided, including a stored program, wherein, when the program is running, it controls the device where the non-volatile storage medium is located to execute the above-described vehicle avoidance method.
[0071] The aforementioned non-volatile storage medium is used to store a program that performs the following functions: detecting the status data of a target vehicle, wherein the status data includes at least: the driving status data of the target vehicle and the surrounding environment data of the target vehicle; determining whether the target vehicle has triggered a forced reversing obstacle avoidance mode based on the status data, wherein the forced reversing obstacle avoidance mode is used to control the target vehicle to reverse and avoid obstacles; if the target vehicle triggers the forced reversing obstacle avoidance mode, determining the reversing path of the target vehicle based on the status data and the lane where the target vehicle is located; and controlling the target vehicle to reverse according to the reversing path of the target vehicle.
[0072] According to another aspect of the embodiments of this application, a processor is also provided, which is used to run a program, wherein the program executes the above-described vehicle avoidance method when it runs.
[0073] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0074] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0075] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.
[0076] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0077] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0078] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.
[0079] The above are merely preferred embodiments of this application. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this application, and these improvements and modifications should also be considered within the scope of protection of this application.
Claims
1. A method for avoiding a vehicle, characterized in that, include: The status data of the target vehicle is detected, wherein the status data includes at least: the driving status data of the target vehicle and the surrounding environment data of the target vehicle; Based on the status data, it is determined whether the target vehicle triggers the forced reversing avoidance mode, wherein the forced reversing avoidance mode is used to control the target vehicle to reverse and avoid obstacles; When the target vehicle triggers the forced reversing avoidance mode, the reversing path of the target vehicle is determined based on the status data and the lane where the target vehicle is located. Control the target vehicle to reverse according to the target vehicle's reversing path.
2. The method according to claim 1, characterized in that, Determining whether the target vehicle has triggered the forced reversing avoidance mode based on the status data includes: Based on the status data, it is determined whether the target vehicle meets the first preset condition, wherein the first preset condition includes at least: the target vehicle's speed is less than a preset speed threshold, an obstacle larger than a preset volume is detected in front of the target vehicle, the relative distance between the target vehicle and the obstacle is less than a preset distance, and the collision duration between the target vehicle and the obstacle is less than a preset duration. If the target vehicle meets the first preset condition, it is determined that the target vehicle poses a collision risk; In the event that the target vehicle is at risk of collision, determine whether the target vehicle has a lateral avoidance path; If the target vehicle does not have a lateral avoidance path, it is determined that the target vehicle has triggered a forced reversing avoidance mode.
3. The method according to claim 2, characterized in that, The method further includes: From the status data, we obtain whether there are obstacles on the side of the target vehicle, the minimum turning radius of the target vehicle, and the width of the lane where the target vehicle is located and the width of the adjacent lane. The minimum lateral displacement required for the target vehicle to avoid the obstacle is determined based on the minimum turning radius of the target vehicle, and the available lateral distance of the target vehicle is determined based on the width of the lane in which the target vehicle is located and the adjacent lane. If the minimum lateral displacement required to avoid the target vehicle is greater than the available lateral distance of the target vehicle, it is determined that the target vehicle does not have a lateral avoidance path.
4. The method according to claim 1, characterized in that, After the target vehicle determines that it has triggered the forced reversing avoidance mode, the method further includes: Output alarm information, wherein the alarm information is used to instruct the target vehicle to switch to the forced reversing avoidance mode; Obtain the operation instructions of the target vehicle within a preset time period; If the operation instruction indicates that the steering torque of the target vehicle is greater than a preset torque threshold or the steering angle change rate of the target vehicle is greater than a preset steering angle change rate threshold within the preset time period, it is determined that the target vehicle has a first operation. The absolute value of the accelerator pedal opening of the target vehicle within a preset time period is obtained. If the absolute value of the accelerator pedal opening is greater than a preset absolute value threshold, the target vehicle is determined to be in a second operation state. If the target vehicle is not in the state of first operation and the target vehicle is not in the state of second operation, it is determined that the target vehicle has passed the first safety check; If there are no obstacles behind the target vehicle, it is determined that the target vehicle has passed the second safety check. If the target vehicle passes both the first safety check and the second safety check simultaneously, the target vehicle is determined to switch to the forced reversing avoidance mode.
5. The method according to claim 4, characterized in that, Determining the reversing path of the target vehicle based on the status data and the lane in which the target vehicle is located includes: Based on the status data, determine the position where the target vehicle can avoid the obstacle; The starting point of the reversing path is determined by the position of the target vehicle when it switches to the forced reversing avoidance mode, and the ending point of the reversing path is determined by the position where the target vehicle can avoid the obstacle. The reversing path is generated by taking the center line of the lane where the target vehicle is located as the center line of the reversing path of the target vehicle.
6. The method according to claim 5, characterized in that, The method further includes: If there are obstacles in the reversing path, multiple candidate paths are generated; The distance between the point farthest from the center line of the reversing path and the target distance of the center line of the reversing path in each candidate path, the distance between the sampling point in each candidate path and the obstacle, and the rate of curvature change of each candidate path are obtained respectively. The cost function value of each candidate path is determined based on the target distance, the distance of the sampling points in the candidate paths from the obstacle, and the rate of curvature change of each candidate path; The candidate path with the smallest cost function value is selected from the candidate paths and determined as the corrected reversing path.
7. The method according to claim 1, characterized in that, After controlling the target vehicle to reverse along the target vehicle's reversing path, the method further includes: If the distance between the obstacle and the target vehicle is detected to be greater than a preset safe distance, the target vehicle is controlled to decelerate and stop at a preset acceleration. Upon detecting a manual control signal, the vehicle exits the forced reversing avoidance mode and responds to the manual control signal. If a collision risk is detected behind the target vehicle, stop immediately.
8. A vehicle avoidance system, characterized in that, include: Environmental perception module, decision control module, and vehicle control module; The environmental perception module is used to detect the status data of the target vehicle, wherein the status data includes at least: the driving status data of the target vehicle and the surrounding environment data of the target vehicle. The decision control module is used to determine whether the target vehicle triggers the forced reversing avoidance mode based on the status data, and to determine the reversing path of the target vehicle based on the status data and the lane where the target vehicle is located when the target vehicle triggers the forced reversing avoidance mode. The forced reversing avoidance mode is used to control the target vehicle to reverse and avoid obstacles. The vehicle control module is used to control the target vehicle to reverse according to the target vehicle's reversing path.
9. A computer device, characterized in that, include: A memory and a processor, wherein the memory is used to store program instructions; The processor, connected to the memory, is used to execute the vehicle avoidance method according to any one of claims 1 to 7.
10. A vehicle, characterized in that, include: A vehicle avoidance system, wherein the vehicle avoidance system is used to perform the vehicle avoidance method according to any one of claims 1 to 7.