Intelligent vehicle obstacle avoidance method and device

Abstract

The present application provides an intelligent vehicle obstacle avoidance method and device. The method includes: real-time detection and identification of obstacles in front of the vehicle, and obtaining the position information of the obstacle and the relative position information of the vehicle and the target point; generating a repulsive potential field related to the obstacle according to the position information of the obstacle; generating a gravitational potential field related to the target point according to the relative position information of the vehicle and the target point; determining the resultant potential field of the vehicle according to the repulsive potential field and the gravitational potential field, and judging whether the vehicle triggers an obstacle avoidance trajectory planning operation according to the resultant potential field; in response to the vehicle triggering the obstacle avoidance trajectory planning operation, calculating the end position of the obstacle avoidance trajectory using a predetermined obstacle avoidance trajectory planning algorithm, and generating the vehicle's obstacle avoidance trajectory according to the lateral offset and slope corresponding to the obstacle avoidance starting position and the obstacle avoidance end position. The present application overcomes the local minimum problem and improves the vehicle's reaction speed and obstacle avoidance efficiency in a dynamic environment.

Description

Technical Field

[0001] The present application relates to the field of new energy vehicle technology, and in particular to an intelligent vehicle obstacle avoidance method and device. Background Art

[0002] In the autonomous driving technology of intelligent vehicles, obstacle avoidance is a core function that ensures that the vehicle can drive safely in a changing traffic environment. The traditional artificial potential field method is widely used in such systems. It guides the vehicle to avoid obstacles by simulating the vehicle as a particle and generating a repulsive potential field around the obstacle. Although this method is simple and intuitive, it has the following limitations in practical applications:

[0003] Local minimum problem: In complex environments, traditional artificial potential field methods may cause the vehicle to fall into a local minimum point, that is, the vehicle cannot find a valid path to the target, and therefore cannot move forward or makes repeated ineffective adjustments.

[0004] Insufficient adaptability to dynamic environments: Traditional potential field methods are mainly applicable to static or highly predictable environments. In dynamically changing environments, such as fast-moving vehicles or sudden obstacles, their reaction speed and adaptability are usually insufficient, and they cannot effectively update the obstacle avoidance path in real time.

[0005] Therefore, there is an urgent technical need to develop an improved intelligent vehicle obstacle avoidance method that can more effectively handle dynamic changes in complex environments, overcome local minima problems, and improve the vehicle's reaction speed and obstacle avoidance efficiency in dynamic environments. Summary of the invention

[0006] In view of this, an embodiment of the present application provides an intelligent vehicle obstacle avoidance method and device to solve the local minimum problem existing in the prior art and the problem of slow vehicle reaction speed and low obstacle avoidance efficiency in a dynamic environment.

[0007] In a first aspect of an embodiment of the present application, a smart vehicle obstacle avoidance method is provided, comprising: real-time detection and identification of obstacles in front of the vehicle, and obtaining the position information of the obstacle and the relative position information of the vehicle and a target point; generating a repulsive potential field associated with the obstacle based on the position information of the obstacle, wherein the size and direction of the repulsive potential field are dynamically adjusted according to the distance and relative speed between the vehicle and the obstacle; generating a gravitational potential field associated with the target point based on the relative position information between the vehicle and the target point, wherein the size and direction of the gravitational potential field are dynamically adjusted according to the distance between the vehicle and the target point; determining a resultant potential field of the vehicle based on the repulsive potential field and the gravitational potential field, and judging whether the vehicle triggers an obstacle avoidance trajectory planning operation based on the resultant potential field; in response to the vehicle triggering an obstacle avoidance trajectory planning operation, calculating the end point position of the obstacle avoidance trajectory using a predetermined obstacle avoidance trajectory planning algorithm, and generating the vehicle's obstacle avoidance trajectory based on the lateral offset and slope corresponding to the obstacle avoidance starting point position and the obstacle avoidance end point position, respectively.

[0008] According to a second aspect of an embodiment of the present application, there is provided an intelligent vehicle obstacle avoidance device, comprising: an acquisition module, configured to detect and identify an obstacle in front of a vehicle in real time, and to acquire the position information of the obstacle and the relative position information between the vehicle and a target point; a first generation module, configured to generate a repulsive potential field associated with the obstacle according to the position information of the obstacle, wherein the magnitude and direction of the repulsive potential field are dynamically adjusted according to the distance and relative speed between the vehicle and the obstacle; a second generation module, configured to generate a gravitational potential field associated with the target point according to the relative position information between the vehicle and the target point, wherein the magnitude and direction of the gravitational potential field are dynamically adjusted according to the distance between the vehicle and the target point; a judgment module, configured to determine the resultant potential field of the vehicle according to the repulsive potential field and the gravitational potential field, and to judge whether the vehicle triggers an obstacle avoidance trajectory planning operation according to the resultant potential field; a calculation module, configured to calculate the end point position of the obstacle avoidance trajectory using a predetermined obstacle avoidance trajectory planning algorithm in response to the vehicle triggering the obstacle avoidance trajectory planning operation, and to generate the obstacle avoidance trajectory of the vehicle according to the lateral offset and slope corresponding to the obstacle avoidance starting point position and the obstacle avoidance end point position, respectively.

[0009] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0010] By real-time detection and identification of obstacles in front of the vehicle, and obtaining the position information of the obstacle and the relative position information of the vehicle and the target point; generating a repulsive potential field related to the obstacle according to the position information of the obstacle, wherein the size and direction of the repulsive potential field are dynamically adjusted according to the distance and relative speed between the vehicle and the obstacle; generating a gravitational potential field related to the target point according to the relative position information between the vehicle and the target point, wherein the size and direction of the gravitational potential field are dynamically adjusted according to the distance between the vehicle and the target point; determining the resultant potential field of the vehicle according to the repulsive potential field and the gravitational potential field, and judging whether the vehicle triggers the obstacle avoidance trajectory planning operation according to the resultant potential field; in response to the vehicle triggering the obstacle avoidance trajectory planning operation, calculating the end position of the obstacle avoidance trajectory using a predetermined obstacle avoidance trajectory planning algorithm, and generating the vehicle's obstacle avoidance trajectory according to the lateral offset and slope corresponding to the obstacle avoidance starting position and the obstacle avoidance end position. This application overcomes the local minimum problem and improves the vehicle's reaction speed and obstacle avoidance efficiency in a dynamic environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0012] Figure 1 It is a flowchart of the intelligent vehicle obstacle avoidance method provided in the embodiment of the present application;

[0013] Figure 2 is a schematic diagram of vehicle obstacle avoidance based on a potential field model provided in an embodiment of the present application;

[0014] Figure 3 is a schematic diagram of the structure of the Frenet coordinate system provided in an embodiment of the present application;

[0015] Figure 4 is a schematic diagram of the structure of an intelligent vehicle obstacle avoidance device provided in an embodiment of the present application;

[0016] Figure 5 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0018] In the field of autonomous driving and intelligent vehicles, vehicle obstacle avoidance is a core technical issue. Obstacle avoidance technology ensures that the vehicle can effectively identify and avoid obstacles in front of it during driving, thereby avoiding collisions and ensuring safe driving. Artificial potential field method is one of the widely used obstacle avoidance technologies. It is based on the concept of physics. By establishing a potential field model, the vehicle is regarded as a particle, and the obstacle generates a force field to push the vehicle to avoid the obstacle.

[0019] Although the traditional artificial potential field method performs well in many basic scenarios, it shows some significant limitations in complex environments, such as:

[0020] 1. There is a local minimum problem: In some cases, the vehicle may get stuck in the local minimum point of the potential field and cannot find a path to the goal, resulting in stagnation.

[0021] 2. Insufficient response to dynamic environments: The traditional potential field method mainly considers static obstacles and is not sensitive and quick enough to respond to sudden changes in the dynamic environment, which is particularly insufficient in high-speed driving or complex traffic scenarios.

[0022] In view of the problems existing in the prior art, the present application proposes a new potential field design strategy. This strategy method not only regards the vehicle as a particle, but also considers its dynamic behavior characteristics, such as speed and acceleration, so that the adjustment of the potential field is more in line with the actual driving state. By real-time perception of obstacles in the environment and their dynamic changes, the shape and parameters of the potential field are automatically adjusted, which enables the vehicle to avoid obstacles more flexibly and accurately. And the spring damping theory in the mechanical model is applied to adjust the size and direction of the potential field force to further improve the efficiency and stability of obstacle avoidance. Therefore, the new potential field design strategy of the present application solves the problems encountered by traditional methods in complex environments through more intelligent environmental perception and dynamic potential field adjustment, and provides a more efficient and safe vehicle obstacle avoidance technology solution.

[0023] Figure 1 It is a flow chart of the intelligent vehicle obstacle avoidance method provided in an embodiment of the present application. Figure 1 The intelligent vehicle obstacle avoidance method can be executed by the intelligent driving system. Figure 1 As shown, the intelligent vehicle obstacle avoidance method may specifically include:

[0024] S101, detecting and identifying obstacles in front of the vehicle in real time, and obtaining the position information of the obstacles and the relative position information between the vehicle and the target point;

[0025] S102, generating a repulsive potential field associated with the obstacle according to the position information of the obstacle, wherein the magnitude and direction of the repulsive potential field are dynamically adjusted according to the distance and relative speed between the vehicle and the obstacle;

[0026] S103, generating a gravitational potential field related to the target point according to the relative position information between the vehicle and the target point, wherein the size and direction of the gravitational potential field are dynamically adjusted according to the distance between the vehicle and the target point;

[0027] S104, determining the resultant potential field of the vehicle according to the repulsive potential field and the gravitational potential field, and judging whether the vehicle triggers an obstacle avoidance trajectory planning operation according to the resultant potential field;

[0028] S105, in response to the vehicle triggering an obstacle avoidance trajectory planning operation, a predetermined obstacle avoidance trajectory planning algorithm is used to calculate an end point position of the obstacle avoidance trajectory, and an obstacle avoidance trajectory of the vehicle is generated according to the lateral offset and slope corresponding to the obstacle avoidance starting point position and the obstacle avoidance end point position respectively.

[0029] In some embodiments, generating a repulsive potential field associated with the obstacle according to the position information of the obstacle includes:

[0030] Taking obstacles and lane lines as repulsive force sources, a virtual spring damping model is constructed according to the vector distance from the vehicle to the obstacle, the virtual spring coefficient and the virtual damper coefficient, and the virtual spring damping model is used as the repulsive force potential field;

[0031] Among them, the intensity of the repulsive potential field increases as the distance between the vehicle and the obstacle decreases, and the intensity of the repulsive potential field corresponding to the obstacle avoidance lane is greater than the intensity of the repulsive potential field corresponding to the obstacle avoidance front lane.

[0032] Specifically, when the intelligent driving system of the smart vehicle determines that there is an obstacle ahead, it regards the obstacle ahead as a repulsive potential field. The closer to the obstacle, the stronger the repulsive force. At the same time, the target point of the smart vehicle (that is, the destination to be traveled to) is regarded as a gravitational potential field, which attracts the vehicle to move toward the target point. By comprehensively considering the effects of these two forces, the smart vehicle can calculate a suitable driving direction to avoid obstacles and move towards the target point. The advantage of this method lies in its simple and intuitive implementation and high real-time performance. Since the artificial potential field method does not require global path planning, but calculates the vehicle's driving direction in real time based on the current scene, it can react faster and avoid obstacles.

[0033] The process of establishing the potential field model provided in the embodiment of the present application is described in detail below in conjunction with the accompanying drawings and specific embodiments. Figure 2 It is a schematic diagram of vehicle obstacle avoidance based on the potential field model provided in an embodiment of the present application.

[0034] like Figure 2 As shown, the process of establishing the potential field model in the embodiment of the present application may include the following contents:

[0035] The intelligent vehicle obstacle avoidance method of this embodiment uses the artificial potential field method and combines it with a virtual spring damping system to optimize the vehicle's obstacle avoidance strategy in complex environments. This method not only responds to static and dynamic obstacles, but also adjusts the potential field according to the layout of the lane itself to ensure that the vehicle can safely return to the original driving trajectory after emergency obstacle avoidance.

[0036] First, the construction process of the repulsive potential field includes considering the lane lines and the obstacles ahead as repulsive sources. The repulsive sources include fixed obstacles (such as roadside obstacles) and temporary obstacles (such as the vehicle in front or pedestrians). A virtual spring damping model is used to define the interaction between the vehicle and the obstacle, including the virtual spring coefficient and the virtual damper coefficient The strength of the potential field increases as the distance between the vehicle and the obstacle decreases, realizing a dynamic adjustment mechanism in which the closer the obstacle is, the stronger the repulsive force becomes.

[0037] It should be noted that if Figure 2 As shown in the schematic diagram of vehicle obstacle avoidance, during the obstacle avoidance operation, since the repulsive potential field strength of the left lane (obstacle avoidance lane) is designed to be higher than that of the right lane (original driving lane), this makes it easier for the vehicle to return to the original lane after avoiding the obstacle.

[0038] That is to say, this embodiment introduces a more physically meaningful model for the obstacle avoidance system of the intelligent vehicle by introducing the spring damping system into the artificial potential field. In this case, the interaction between the vehicle and the obstacle is regarded as a mechanical model of the spring-damper system. The closer the distance to the obstacle, the greater the compression of the spring and the greater the damping force. The direction of the vehicle's movement is affected by this spring-damper system.

[0039] According to the formula of the spring-damper system, the resistance of the vehicle can be calculated. As the distance between the vehicle and the obstacle changes, the resistance will also change accordingly. At the same time, according to the relative position of the vehicle's current position and the target point, the gravity size and direction that the vehicle should face towards the target point can be calculated.

[0040] For example, in one example, the specific expression form of the repulsive potential field proposed in the embodiment of the present application can be represented by the following virtual repulsive function:

[0041]

[0042] in, is the vector representing the repulsive potential field, represents the virtual spring coefficient, represents the virtual damper coefficient, ρ(X, X o ) represents the vector from the vehicle to the obstacle.

[0043] According to the potential field model establishment method of the present embodiment, by introducing a spring damping model with richer physical meaning, the vehicle's adaptability to complex traffic environments is improved. In addition, through the differentiated lane potential field design, the vehicle's driving path after emergency obstacle avoidance is optimized, and the safety and efficiency of obstacle avoidance are improved. This method is suitable for various on-board intelligent systems, especially for applications on highways and complex urban roads, and effectively improves the practicality and reliability of autonomous driving technology.

[0044] In some embodiments, generating a gravitational potential field associated with the target point according to the relative position information between the vehicle and the target point includes:

[0045] Taking the target point as the gravity source, a function model corresponding to the gravitational potential field is constructed according to the vector distance from the vehicle to the target point and the gravity coefficient.

[0046] Specifically, this embodiment also describes how to construct a gravitational potential field related to a target point in the intelligent vehicle obstacle avoidance method to ensure that the vehicle can effectively navigate to a predetermined target position while avoiding obstacles. The following are the detailed steps and methods for constructing a gravitational potential field in this embodiment.

[0047] First, define the gravity source. In this embodiment, the predetermined target point of the intelligent vehicle is regarded as a gravity source. The target point may be the final destination or the next navigation point of the vehicle.

[0048] Furthermore, in order to establish a gravitational potential field model, this embodiment uses a function based on the square of the Euclidean distance to describe the magnitude of gravity. This method reflects the law of gravity in the physical world, that is, the farther the distance, the weaker the gravity.

[0049] In one example, the function model of the gravitational potential field is defined as:

[0050] U gp (X) = k g ρ 2 (X,X g )

[0051] Among them, U gp (X) represents the vector of gravitational potential field, k g represents the gravitational coefficient, ρ(X, X g ) represents the vector from the vehicle to the target point, and its length is the Euclidean distance |XX g |.

[0052] In practical applications, the gravitational coefficient k g It can be a preset constant and adjusted according to the needs of the actual application scenario. In the highway scenario, a larger k may be required. g value to quickly guide the vehicle back to its original position; in dense urban traffic, a smaller k gA higher value can provide more detailed navigation, avoiding approaching the target too quickly and missing the turning point.

[0053] Furthermore, when an intelligent vehicle performs obstacle avoidance operations, it not only needs to consider how to bypass obstacles, but also must maintain guidance to the target point. The gravitational potential field provides a natural and effective way to achieve this, ensuring that the vehicle does not deviate too far from the intended route while avoiding obstacles. Since the distance between the vehicle and the target point will continue to change, the gravitational potential field needs to be updated in real time to adapt to the new vehicle position. This dynamic adjustment helps the vehicle to drive steadily towards the target point even in complex traffic environments.

[0054] Through the method of the present embodiment described above, the intelligent vehicle can utilize the gravitational potential field generated by the target point to optimize its driving route, ensuring that it can effectively navigate to the target point even when performing emergency obstacle avoidance. This method enhances the navigation accuracy and driving safety of the vehicle, and is particularly suitable for the application requirements of the autonomous driving system in a changing environment.

[0055] In some embodiments, determining the resultant potential field of the vehicle according to the repulsive potential field and the gravitational potential field, and judging whether the vehicle triggers an obstacle avoidance trajectory planning operation according to the resultant potential field include:

[0056] The vector of the repulsive potential field is added to the vector of the gravitational potential field to obtain a resultant potential field. When the vector of the repulsive potential field is greater than the vector of the gravitational potential field, it is determined that the vehicle has triggered an obstacle avoidance trajectory planning operation, and the position of the vehicle when the obstacle avoidance trajectory planning operation is triggered is used as the obstacle avoidance starting position.

[0057] Specifically, this embodiment also describes in detail how to determine whether the intelligent vehicle needs to trigger obstacle avoidance trajectory planning by calculating the resultant potential field. This process combines the interaction between the repulsive potential field and the gravitational potential field, providing an effective decision-making mechanism for the vehicle to cope with complex road conditions.

[0058] First, the repulsive potential field is generated by the interaction between the vehicle and the obstacle. Each obstacle generates a repulsive potential field. The magnitude of the repulsive force depends on the distance and relative speed between the vehicle and the obstacle, and is adjusted by the virtual spring coefficient and the virtual damper coefficient. The gravitational potential field is determined by the relative position between the vehicle and the target point, and the magnitude of the force is proportional to the square of the distance from the vehicle to the target point.

[0059] In one example, the resultant potential field is obtained by adding the repulsive force and the gravitational force of all obstacles. The resultant potential field U(X) to which the smart vehicle is subjected is:

[0060]

[0061] Among them, U(X) represents the vector of the resultant potential field, U gp(X) represents the vector of gravitational potential field, U opi (X) represents the vector of the repulsive potential field, and n is the number of obstacles. In actual scenarios, when the vehicle is far away from obstacles, it will not be affected by them. Therefore, the resultant potential field U(X) can also be expressed as:

[0062]

[0063] Furthermore, the trigger condition for determining the obstacle avoidance trajectory is when the repulsive force vector (the total repulsive force generated by the obstacle) is greater than the gravitational force vector, i.e. The vehicle determines that it needs to perform obstacle avoidance trajectory planning. This condition means that the risk of the vehicle approaching an obstacle exceeds the safety of driving straight to the target point, and action needs to be taken to avoid a potential collision.

[0064] It should be noted that the calculation of the potential field depends on the real-time data provided by the vehicle's sensor system, including the vehicle's position, speed, and the position of surrounding obstacles. The system dynamically updates the strength and direction of the potential field based on real-time data to ensure the timeliness and accuracy of decision-making responses.

[0065] Once the obstacle avoidance operation is triggered, the vehicle's navigation system will immediately calculate a new driving path to avoid obstacles while maintaining the original driving goal as much as possible. The trajectory adjustment is optimized based on pre-set safety parameters and the dynamic performance of the vehicle to ensure smooth and safe obstacle avoidance behavior.

[0066] Through the above method of this embodiment, the intelligent vehicle can evaluate and respond to potential collision risks in real time in a complex traffic environment, dynamically calculate the resultant potential field, and trigger accurate obstacle avoidance trajectory planning when necessary. This method enhances the vehicle's autonomous safety performance and improves its ability to respond to sudden traffic situations.

[0067] In some embodiments, in response to the vehicle triggering the obstacle avoidance trajectory planning operation, before calculating the end position of the obstacle avoidance trajectory using a predetermined obstacle avoidance trajectory planning algorithm, the method further includes:

[0068] A curved coordinate system is established with the center line of the road the vehicle is currently traveling on as the reference line, and the coordinates composed of the distance the vehicle travels along the center line of the road and the lateral offset of the vehicle relative to the center line of the road are used as the position of the vehicle in the curved coordinate system.

[0069] Specifically, this embodiment also describes in detail how to use a curvilinear coordinate system (such as a Frenet coordinate system) to implement efficient obstacle avoidance trajectory planning in an intelligent vehicle system. The Frenet coordinate system provides a method for locating the vehicle position based on the centerline of the road for vehicle obstacle avoidance, thereby optimizing the navigation and obstacle avoidance efficiency of the vehicle on a curved road.

[0070] The process of establishing the Frenet coordinate system provided in the embodiment of the present application is described in detail below with reference to the accompanying drawings and specific embodiments. Figure 3 It is a structural diagram of the Frenet coordinate system provided in an embodiment of the present application.

[0071] like Figure 3 As shown, the process of establishing the Frenet coordinate system in the embodiment of the present application may include the following contents:

[0072] In response to the need for the vehicle to avoid obstacles, the Frenet coordinate system is first established based on the center line of the road the vehicle is currently traveling on. This coordinate system not only depends on the actual direction of the road, but also takes into account the curvature of each point of the road. In the Frenet coordinate system, the position of the vehicle is represented by two main parameters: the travel distance s along the center line of the road, and the lateral offset d of the vehicle relative to the center line of the road.

[0073] Furthermore, the Frenet coordinate system provides a more intuitive way to track the vehicle's position when the vehicle is traveling along a straight or curved road. The vehicle's real-time position is converted from the Cartesian coordinate system (x, y) to the Frenet coordinate system (s, d), which takes into account the vehicle's adaptability to the road shape and the current driving state.

[0074] Furthermore, when an obstacle appears in front of the intelligent vehicle during driving, and the calculated vector of the repulsive potential field is greater than the vector of the gravitational potential field, the system determines that the obstacle avoidance trajectory planning operation is triggered. This judgment is based on the resultant potential field U(X).

[0075] Further, in the Frenet coordinate system, calculating the obstacle avoidance trajectory involves determining how the vehicle should adjust its travel distance s and lateral offset d along the road to avoid obstacles. The calculation of the obstacle avoidance trajectory uses the vehicle's current position, a predetermined obstacle avoidance strategy (such as speed adjustment and direction change), and road conditions (such as road width and curvature) as input parameters.

[0076] By adopting the Frenet coordinate system, intelligent vehicles are able to calculate and perform obstacle avoidance maneuvers more accurately, especially on curved roads. The system improves the safety and efficiency of obstacle avoidance maneuvers by reducing reliance on Cartesian coordinates and allowing the vehicle to adapt more naturally to the shape of the road. In addition, the Frenet coordinate system simplifies the management of vehicle dynamics, making obstacle avoidance path planning more intuitive and controllable, especially for complex traffic environments and changing road conditions.

[0077] In some embodiments, the end position of the obstacle avoidance trajectory is calculated using a predetermined obstacle avoidance trajectory planning algorithm, including using the following formula to calculate the obstacle avoidance end position:

[0078]

[0079] Among them, s g represents the obstacle avoidance end position, v0 represents the obstacle avoidance speed of the vehicle, and d i Indicates the current lateral offset of the vehicle, d max Indicates the maximum lateral displacement of the vehicle during obstacle avoidance, t g Indicates the preset obstacle avoidance time, s i Indicates the distance traveled by the vehicle.

[0080] Specifically, this embodiment describes how to use a predetermined obstacle avoidance trajectory planning algorithm to calculate the obstacle avoidance endpoint position of the intelligent vehicle. This algorithm mainly considers the vehicle's current speed, lateral offset, obstacle avoidance time, and road conditions to optimize the obstacle avoidance process and ensure that the vehicle can safely and effectively avoid obstacles.

[0081] In one example, the calculation formula for the obstacle avoidance end point position is as follows:

[0082]

[0083] The meanings of the letters in the above obstacle avoidance endpoint position calculation formula are as follows:

[0084] s g Indicates the obstacle avoidance endpoint, that is, the specific location on the road that the vehicle should reach after completing the obstacle avoidance operation.

[0085] v0 represents the vehicle’s obstacle avoidance speed, which is the average speed of the vehicle during the obstacle avoidance maneuver.

[0086] d i Indicates the current lateral offset of the vehicle, which refers to the initial lateral position of the vehicle relative to the centerline of the road.

[0087] d max It indicates the maximum lateral displacement of the vehicle during obstacle avoidance, and represents the maximum lateral movement distance that the vehicle can achieve to avoid obstacles.

[0088] t g Indicates the preset obstacle avoidance time, which is the time estimated to complete obstacle avoidance based on vehicle speed and road conditions. Generally, it takes about 6-10 seconds for the vehicle to complete obstacle avoidance.

[0089] s i Represents the distance traveled by the vehicle, that is, the position of the vehicle on the road when the obstacle avoidance maneuver begins.

[0090] In the above obstacle avoidance end point calculation formula, the distance the vehicle moves forward while reducing the lateral offset is taken into account, that is, as the vehicle moves closer to the center line, the distance it moves forward on the road decreases accordingly.

[0091] Before the obstacle avoidance operation is initiated, the system first obtains the vehicle's current speed, lateral offset, preset obstacle avoidance time, and distance traveled. These data are provided in real time by the vehicle's sensors and navigation system. When an obstacle is detected ahead and the calculated repulsive force is greater than the gravitational force, the system immediately triggers the obstacle avoidance trajectory planning algorithm. The system uses the above formula to calculate the obstacle avoidance endpoint position based on real-time driving conditions to ensure that the vehicle can avoid obstacles and drive safely as planned.

[0092] Through the above method of this embodiment, the algorithm provides an efficient obstacle avoidance strategy for intelligent vehicles by accurately calculating the end position of the vehicle's obstacle avoidance. It takes into account the dynamic performance of the vehicle and the road conditions to ensure that the obstacle avoidance operation is both fast and safe. Through the precise control of the obstacle avoidance trajectory, the road use efficiency is maximized and traffic interference is reduced.

[0093] In some embodiments, generating an obstacle avoidance trajectory of the vehicle according to the lateral offset and the slope corresponding to the obstacle avoidance starting position and the obstacle avoidance end position respectively includes:

[0094] In the curve coordinate system, a cubic polynomial curve matrix is ​​constructed according to the lateral offset and slope corresponding to the obstacle avoidance starting point, the lateral offset and slope corresponding to the obstacle avoidance end point, the vehicle's travel distance on the road centerline, and the cubic polynomial coefficients;

[0095] The cubic polynomial curve matrix is ​​solved to obtain cubic polynomial coefficients, and the obstacle avoidance trajectory of the vehicle is generated according to the cubic polynomial coefficients. The vehicle is controlled to travel along the obstacle avoidance trajectory so that the vehicle bypasses the obstacle and returns to the predetermined driving route.

[0096] Specifically, this embodiment describes in detail how to use a curved coordinate system (such as the Frenet coordinate system) and a cubic polynomial curve in an intelligent vehicle system to calculate and implement an obstacle avoidance trajectory. By precisely controlling the lateral offset and slope of the starting point and the end point, this method can generate a smooth obstacle avoidance trajectory for the vehicle, enabling it to effectively bypass obstacles and safely return to the intended driving route.

[0097] Furthermore, in the Frenet coordinate system, the vehicle position is described by the travel distance s and the lateral offset d along the centerline of the road. This coordinate system facilitates precise control of the position and movement of the vehicle, especially on curved roads.

[0098] Furthermore, a cubic polynomial curve is used to describe the lateral movement of the vehicle during the obstacle avoidance process. The curve is determined by four coefficients a, b, c, c0, which are based on the lateral displacement d of the vehicle at the starting and ending points of the obstacle avoidance. i ,d g and the slope k i ,k g The general form of the curve is a*s3 +b*s 2 +c*s+c0, where s is the distance the vehicle travels along the road.

[0099] Furthermore, to determine the coefficients a, b, c, c0, matrix operations are used to solve a system of equations based on the lateral offset and slope conditions at the start and end of the obstacle avoidance. These conditions allow the system to precisely control the behavior of the vehicle at the start and end of the obstacle avoidance, ensuring the smoothness of the trajectory.

[0100] Furthermore, once the obstacle avoidance trajectory is calculated, the control system of the intelligent vehicle will guide the vehicle to drive along this trajectory, ensuring that it avoids obstacles and smoothly returns to its original driving route. The implementation of the trajectory relies on the vehicle's dynamic response system, including steering control and speed regulation, to adapt to the calculated path.

[0101] For example, in a specific example, the cubic polynomial obstacle avoidance trajectory planning can adjust the shape of the trajectory by controlling the polynomial coefficients. In this way, different types of trajectories can be generated according to different driving environments and obstacle avoidance requirements to ensure that the vehicle can drive safely and efficiently. Therefore, this application uses a cubic polynomial curve for obstacle avoidance trajectory planning, and uses a cubic polynomial curve to describe the vehicle trajectory before, during, and after obstacle avoidance. The specific algorithm is as follows:

[0102]

[0103]

[0104] Where k represents the slope, and a, b, c, and c0 are the coefficients of the cubic curve. Assume that the current lateral offset is d i , driving distance is s i , the slope is k i , we can get the values ​​of a, b, c, c0:

[0105]

[0106] Among them, d g Represents the lateral offset at the end point of obstacle avoidance, s g The a, b, c, and c0 coefficients are used to generate the actual obstacle avoidance trajectory of the vehicle. Therefore, obstacle avoidance trajectory planning can be regarded as a problem of determining the distance traveled by the vehicle when obstacle avoidance is completed.

[0107] Through the method of the present embodiment described above, by accurately calculating the coefficients of the cubic polynomial, the vehicle can bypass obstacles in the optimal path, minimizing the loss of driving distance and time. The Frenet coordinate system allows the algorithm to easily adapt to different road shapes and traffic conditions, enhancing the vehicle's obstacle avoidance capabilities in complex environments. The smooth obstacle avoidance trajectory reduces the safety risks that may be caused by sudden turns or emergency stops.

[0108] According to the technical solution provided in the embodiment of the present application, the technical solution of the present application innovatively simulates the dynamic interaction between the vehicle and the obstacle by treating the obstacle as a spring damping system, thereby significantly improving the obstacle avoidance performance and driving safety of the intelligent vehicle. The technical solution has at least the following advantages:

[0109] 1. Enhanced obstacle avoidance response performance

[0110] By treating the obstacle as a spring-damping system, the interaction between the vehicle and the obstacle increases as the distance decreases. The practicality of this model lies in that the closer the obstacle is, the greater the repulsive force (simulated as spring compression) and damping force are, which more intuitively reflects the impact of obstacles on vehicle movement in the real world.

[0111] The system adjusts the vehicle's forward direction in real time based on the force calculated by the spring damping model. When it detects that the repulsive force is greater than the attractive force, the vehicle immediately triggers obstacle avoidance behavior to effectively avoid potential collisions.

[0112] 2. Highly interpretable obstacle avoidance planning

[0113] The use of a spring-damper system enhances the explainability of obstacle avoidance planning, providing a clear logic for the vehicle driver or the autonomous driving system to explain why obstacle avoidance is required in a specific situation. This transparent obstacle avoidance logic is critical to improving user trust and system acceptance.

[0114] 3. Flexible obstacle avoidance trajectory planning

[0115] The obstacle avoidance trajectory is planned using a cubic polynomial curve. This method allows for highly flexible trajectory design. The shape of the trajectory can be adjusted according to different driving environments and specific requirements, such as the location of the obstacle avoidance start and end points, speed limits, and other road conditions.

[0116] By precisely adjusting the polynomial coefficients, a variety of trajectories that meet specific path requirements can be generated. This not only ensures that the vehicle can safely bypass obstacles, but also ensures smooth and efficient driving, especially in complex or emergency road situations.

[0117] Therefore, in summary, the technical solution of this application significantly improves the obstacle avoidance capability of intelligent vehicles by combining a dynamic spring damping model with a highly flexible cubic polynomial trajectory planning, enhances the interpretability of obstacle avoidance behavior, and provides an efficient solution for complex road environments. These technical effects make this solution have important practical application value and broad market prospects in the fields of intelligent transportation and autonomous driving.

[0118] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0119] Figure 4 Schematic diagram of the structure of the intelligent vehicle obstacle avoidance device provided in the embodiment of the present application. Figure 4 As shown, the intelligent vehicle obstacle avoidance device comprises:

[0120] The acquisition module 401 is configured to detect and identify obstacles in front of the vehicle in real time, and obtain the position information of the obstacles and the relative position information between the vehicle and the target point;

[0121] A first generating module 402 is configured to generate a repulsive potential field associated with the obstacle according to the position information of the obstacle, wherein the magnitude and direction of the repulsive potential field are dynamically adjusted according to the distance and relative speed between the vehicle and the obstacle;

[0122] The second generating module 403 is configured to generate a gravitational potential field related to the target point according to the relative position information between the vehicle and the target point, wherein the size and direction of the gravitational potential field are dynamically adjusted according to the distance between the vehicle and the target point;

[0123] The judgment module 404 is configured to determine the resultant potential field of the vehicle according to the repulsive potential field and the gravitational potential field, and judge whether the vehicle triggers the obstacle avoidance trajectory planning operation according to the resultant potential field;

[0124] The calculation module 405 is configured to calculate the end position of the obstacle avoidance trajectory using a predetermined obstacle avoidance trajectory planning algorithm in response to the vehicle triggering an obstacle avoidance trajectory planning operation, and generate the vehicle's obstacle avoidance trajectory according to the lateral offset and slope corresponding to the obstacle avoidance starting position and the obstacle avoidance end position respectively.

[0125] In some embodiments, Figure 4 The first generation module 402 takes the obstacle and the lane line as the repulsive source, constructs a virtual spring damping model according to the vector distance from the vehicle to the obstacle, the virtual spring coefficient and the virtual damper coefficient, and uses the virtual spring damping model as the repulsive potential field; wherein the intensity of the repulsive potential field increases as the distance between the vehicle and the obstacle decreases, the intensity of the repulsive potential field corresponding to the obstacle avoidance lane is greater than the intensity of the repulsive potential field corresponding to the lane before obstacle avoidance, and the obstacle avoidance lane represents the lane in which the vehicle travels when avoiding an obstacle.

[0126] In some embodiments, the function model of the repulsive potential field is defined as:

[0127]

[0128] in, is the vector representing the repulsive potential field, represents the virtual spring coefficient, represents the virtual damper coefficient, ρ(X, X o ) represents the vector distance from the vehicle to the obstacle.

[0129] In some embodiments, Figure 4 The second generation module 403 takes the target point as the gravity source and constructs a function model corresponding to the gravitational potential field according to the vector distance from the vehicle to the target point and the gravity coefficient.

[0130] In some embodiments, the function model of the gravitational potential field is defined as:

[0131] U gp (X) = k g ρ 2 (X,X g )

[0132] Among them, U gp (X) represents the vector of gravitational potential field, k g represents the gravitational coefficient, ρ(X, X g ) represents the vector from the vehicle to the target point, and its length is the Euclidean distance |XX g |.

[0133] In some embodiments, Figure 4 The judgment module 404 adds the vector of the repulsive potential field and the vector of the gravitational potential field to obtain a resultant potential field. When the vector of the repulsive potential field is greater than the vector of the gravitational potential field, it is judged that the vehicle triggers the obstacle avoidance trajectory planning operation, and the position of the vehicle when the obstacle avoidance trajectory planning operation is triggered is used as the obstacle avoidance starting position.

[0134] In some embodiments, Figure 4 In response to the vehicle triggering the obstacle avoidance trajectory planning operation, the establishment module 406 uses the center line of the current road of the vehicle as a reference line to establish a curved coordinate system before calculating the end point position of the obstacle avoidance trajectory using a predetermined obstacle avoidance trajectory planning algorithm. The coordinates composed of the vehicle's travel distance along the center line of the road and the vehicle's lateral offset relative to the center line of the road are used as the position of the vehicle in the curved coordinate system.

[0135] In some embodiments, Figure 4 The calculation module 405 uses the following formula to calculate the obstacle avoidance end point position:

[0136]

[0137] Among them, s g represents the obstacle avoidance end position, v0 represents the obstacle avoidance speed of the vehicle, and d i Indicates the current lateral offset of the vehicle, d max Indicates the maximum lateral displacement of the vehicle during obstacle avoidance, t g Indicates the preset obstacle avoidance time, S i Indicates the distance traveled by the vehicle.

[0138] In some embodiments, Figure 4 The calculation module 405 constructs a cubic polynomial curve matrix in the curve coordinate system according to the lateral offset and slope corresponding to the obstacle avoidance starting position, the lateral offset and slope corresponding to the obstacle avoidance end position, the vehicle's travel distance on the road centerline, and the cubic polynomial coefficients; solves the cubic polynomial curve matrix to obtain the cubic polynomial coefficients, generates an obstacle avoidance trajectory of the vehicle according to the cubic polynomial coefficients, and controls the vehicle to travel along the obstacle avoidance trajectory, so that the vehicle bypasses the obstacle and returns to the predetermined driving route.

[0139] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0140] Figure 5 Schematic diagram of the structure of the electronic device 5 provided in the embodiment of the present application. Figure 5 As shown, the electronic device 5 of this embodiment includes: a processor 501, a memory 502, and a computer program 503 stored in the memory 502 and executable on the processor 501. When the processor 501 executes the computer program 503, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 501 executes the computer program 503, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0141] Exemplarily, the computer program 503 may be divided into one or more modules / units, which are stored in the memory 502 and executed by the processor 501 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 503 in the electronic device 5.

[0142] The electronic device 5 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 5 may include, but is not limited to, a processor 501 and a memory 502. Those skilled in the art will appreciate that Figure 5It is only an example of the electronic device 5 and does not constitute a limitation of the electronic device 5. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0143] The processor 501 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0144] The memory 502 may be an internal storage unit of the electronic device 5, for example, a hard disk or memory of the electronic device 5. The memory 502 may also be an external storage device of the electronic device 5, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 5. Further, the memory 502 may also include both an internal storage unit of the electronic device 5 and an external storage device. The memory 502 is used to store computer programs and other programs and data required by the electronic device. The memory 502 may also be used to temporarily store data that has been output or is to be output.

[0145] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0146] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0147] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0148] In the embodiments provided in the present application, it should be understood that the disclosed devices / computer equipment and methods can be implemented in other ways. For example, the device / computer equipment embodiments described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. Multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0149] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0150] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0151] If the integrated module / unit is implemented in the form of 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 present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. The computer program may include computer program code, which may be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0152] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An intelligent vehicle obstacle avoidance method, characterized in that: include: Detect and identify obstacles in front of the vehicle in real time, and obtain the location information of the obstacles and the relative position information between the vehicle and the target point; Generate a repulsive potential field associated with the obstacle according to the position information of the obstacle, wherein the magnitude and direction of the repulsive potential field are dynamically adjusted according to the distance and relative speed between the vehicle and the obstacle; Generate a gravitational potential field related to the target point according to the relative position information between the vehicle and the target point, wherein the size and direction of the gravitational potential field are dynamically adjusted according to the distance between the vehicle and the target point; Determining a resultant potential field of the vehicle according to the repulsive potential field and the gravitational potential field, and judging whether the vehicle triggers an obstacle avoidance trajectory planning operation according to the resultant potential field; In response to the vehicle triggering an obstacle avoidance trajectory planning operation, a predetermined obstacle avoidance trajectory planning algorithm is used to calculate an end point position of the obstacle avoidance trajectory based on the current speed, lateral offset, obstacle avoidance time and road conditions of the vehicle, and an obstacle avoidance trajectory of the vehicle is generated according to the lateral offset and slope corresponding to the obstacle avoidance starting point position and the obstacle avoidance end point position respectively; This includes calculating the obstacle avoidance endpoint using the following formula: Among them, s g represents the obstacle avoidance end position, v0 represents the obstacle avoidance speed of the vehicle, d i Indicates the current lateral offset of the vehicle, d max Indicates the maximum lateral displacement of the vehicle during obstacle avoidance, t g Indicates the preset obstacle avoidance time, s i Indicates the distance traveled by the vehicle.

2. The method according to claim 1, characterized in that The step of generating a repulsive potential field associated with the obstacle according to the position information of the obstacle comprises: Taking the obstacle and the lane line as repulsive force sources, constructing a virtual spring damping model according to the vector distance from the vehicle to the obstacle, the virtual spring coefficient and the virtual damper coefficient, and taking the virtual spring damping model as the repulsive force potential field; Among them, the intensity of the repulsive potential field increases as the distance between the vehicle and the obstacle decreases, the intensity of the repulsive potential field corresponding to the obstacle avoidance lane is greater than the intensity of the repulsive potential field corresponding to the front lane of obstacle avoidance, and the obstacle avoidance lane represents the lane in which the vehicle travels when avoiding an obstacle.

3. The method according to claim 2, characterized in that The function model of the repulsive potential field is defined as: in, is the vector representing the repulsive potential field, represents the virtual spring coefficient, represents the virtual damper coefficient, ρ(X, X o ) represents the vector distance from the vehicle to the obstacle, Indicates the relative speed from the vehicle to the obstacle.

4. The method according to claim 1, characterized in that: The step of generating a gravitational potential field related to the target point according to the relative position information between the vehicle and the target point comprises: The target point is taken as a gravitational source, and a function model corresponding to the gravitational potential field is constructed according to the vector distance from the vehicle to the target point and the gravitational coefficient.

5. The method according to claim 4, characterized in that The function model of the gravitational potential field is defined as: U gp ()=k g ρ 2 (X,X g ) Among them, U gp () represents the vector of gravitational potential field, k g represents the gravitational coefficient, ρ(X, X g ) represents the vector from the vehicle to the target point, and its length is the Euclidean distance |XX g |.

6. The method according to claim 1, characterized in that The determining, according to the repulsive potential field and the gravitational potential field, a resultant potential field of the vehicle, and judging, according to the resultant potential field, whether the vehicle triggers an obstacle avoidance trajectory planning operation, comprises: The vector of the repulsive potential field is added to the vector of the gravitational potential field to obtain the resultant potential field. When the vector of the repulsive potential field is greater than the vector of the gravitational potential field, it is determined that the vehicle has triggered an obstacle avoidance trajectory planning operation, and the position of the vehicle when the obstacle avoidance trajectory planning operation is triggered is used as the obstacle avoidance starting position.

7. The method according to claim 1, characterized in that Before calculating the end position of the obstacle avoidance trajectory using a predetermined obstacle avoidance trajectory planning algorithm in response to the vehicle triggering the obstacle avoidance trajectory planning operation, the method further includes: A curvilinear coordinate system is established with the center line of the road on which the vehicle is currently traveling as a reference line, and coordinates consisting of the distance traveled by the vehicle along the center line of the road and the lateral offset of the vehicle relative to the center line of the road are used as the position of the vehicle in the curvilinear coordinate system.

8. The method according to claim 7, characterized in that The generating the obstacle avoidance trajectory of the vehicle according to the lateral offset and the slope corresponding to the obstacle avoidance starting position and the obstacle avoidance end position respectively includes: In the curvilinear coordinate system, a cubic polynomial curve matrix is ​​constructed according to the lateral offset and slope corresponding to the obstacle avoidance starting position, the lateral offset and slope corresponding to the obstacle avoidance end position, the travel distance of the vehicle on the road centerline, and cubic polynomial coefficients; The cubic polynomial curve matrix is ​​solved to obtain the cubic polynomial coefficients, an obstacle avoidance trajectory of the vehicle is generated according to the cubic polynomial coefficients, and the vehicle is controlled to travel along the obstacle avoidance trajectory so that the vehicle bypasses the obstacle and returns to the predetermined driving route.

9. An intelligent vehicle obstacle avoidance device, characterized in that: include: An acquisition module is configured to detect and identify obstacles in front of the vehicle in real time, and obtain position information of the obstacles and relative position information between the vehicle and the target point; A first generating module is configured to generate a repulsive potential field associated with the obstacle according to the position information of the obstacle, wherein the magnitude and direction of the repulsive potential field are dynamically adjusted according to the distance and relative speed between the vehicle and the obstacle; A second generating module is configured to generate a gravitational potential field related to the target point according to the relative position information between the vehicle and the target point, wherein the size and direction of the gravitational potential field are dynamically adjusted according to the distance between the vehicle and the target point; a judgment module, configured to determine a resultant potential field of the vehicle according to the repulsive potential field and the gravitational potential field, and to judge whether the vehicle triggers an obstacle avoidance trajectory planning operation according to the resultant potential field; a calculation module configured to calculate the end position of the obstacle avoidance trajectory based on the current speed, lateral offset, obstacle avoidance time and road conditions of the vehicle in response to the vehicle triggering the obstacle avoidance trajectory planning operation, and generate the obstacle avoidance trajectory of the vehicle according to the lateral offset and slope corresponding to the obstacle avoidance starting position and the obstacle avoidance end position respectively; This includes calculating the obstacle avoidance endpoint using the following formula: Among them, s g represents the obstacle avoidance end position, v0 represents the obstacle avoidance speed of the vehicle, d i Indicates the current lateral offset of the vehicle, d max Indicates the maximum lateral displacement of the vehicle during obstacle avoidance, t g Indicates the preset obstacle avoidance time, S i Indicates the distance traveled by the vehicle.

Images