Intelligent vehicle obstacle avoidance method based on space-time environment safety scoring model

Abstract

The invention provides an intelligent vehicle obstacle avoidance method based on a space-time environment safety scoring model, and the method comprises the steps: carrying out the fusion of multi-sensor data through employing extended Kalman filtering, obtaining a rasterized environment model, and obtaining the current position of a vehicle, the position of an obstacle, and the target position of the vehicle; establishing a space-time environment safety scoring model by introducing a non-linear regulation factor into an ant colony algorithm to obtain a final probability that each ant path is selected; constructing an enhanced pheromone updating function by adopting an improved genetic algorithm fitness formula to obtain an updated ant path; constructing a preliminary planning path; and constructing an improved gravitational field and repulsive force field function, applying the improved gravitational field and repulsive force field function to the preliminarily planned path, adjusting and updating the path in combination with the driving environment model, and finally obtaining an optimal obstacle avoidance path. According to the invention, the safety and reliability of obstacle avoidance of the vehicle in a complex traffic scene can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of smart cars, and in particular to a smart vehicle obstacle avoidance method based on a spatiotemporal environment safety scoring model. Background Art

[0002] Intelligent vehicle path planning is a cutting-edge technology based on perception, decision-making, planning, and control. Path planning generates an optimal path for a vehicle to smoothly reach its destination from its starting point within a given road environment. This optimal path must meet the following requirements: shortest distance, shortest time, lowest energy consumption, and effective obstacle avoidance.

[0003] Although traditional path planning algorithms can generate feasible paths from the starting point to the end point in the field of intelligent vehicle obstacle avoidance, they do not adequately consider the smoothness and feasibility of the path when faced with complex and dynamic traffic scenarios. The generated path may pose certain safety hazards due to frequent turns or sudden braking. Summary of the Invention

[0004] In view of this, the present invention provides an intelligent vehicle obstacle avoidance method based on a spatiotemporal environment safety scoring model to improve the safety and reliability of vehicle obstacle avoidance in complex traffic scenarios.

[0005] An intelligent vehicle obstacle avoidance method based on a spatiotemporal environment safety scoring model, comprising: Step S1: Using an extended Kalman filter to fuse multi-sensor data to obtain a gridded environment model, and obtaining the vehicle's current position, obstacle positions, and target position based on the gridded environment model; Step S2: By introducing a nonlinear adjustment factor into the ant colony algorithm, a spatiotemporal environment safety scoring model is established to obtain the final probability of each ant path being selected; Step S3, based on the final probability of each ant path being selected, an enhanced pheromone update function is constructed using the improved genetic algorithm fitness formula to obtain an updated ant path; Step S4: Establish a driving environment model based on the vehicle's current position and target position, and calculate the target direction, obstacle direction, and integrated motion direction vector matrix; select feasible paths that meet the target point matching and are collision-free from all updated ant paths, thereby obtaining a preliminary planned path; In step S5, the spatiotemporal environmental safety scoring model established in step S2 is introduced into the artificial potential field to obtain improved gravitational field and repulsive field functions, and the improved gravitational field and repulsive field functions are applied to the preliminary planned path. Then, combined with the driving environment model, the path is adjusted and updated to finally obtain the optimal obstacle avoidance path.

[0006] The intelligent vehicle obstacle avoidance method based on the spatiotemporal environment safety scoring model provided by the present invention has the following beneficial effects: 1. Based on the final probability of each ant path being selected, the present invention uses an improved genetic algorithm fitness formula to construct an enhanced pheromone update function. This function eliminates the need for pheromone updates solely relying on path length, allowing the selection probability and fitness value of a path to comprehensively reflect the quality of the path. Pheromones are dynamically adjusted accordingly, improving the adaptive capability of obstacle avoidance in complex traffic scenarios.

[0007] 2. This invention combines a spatiotemporal environmental safety scoring model to conduct a real-time assessment of the vehicle's driving environment. By dynamically adjusting the magnitude and direction of gravity and repulsion, it plans the optimal obstacle avoidance path, effectively avoiding collision risks, improving the safety and reliability of obstacle avoidance, and reducing the possibility of accidents.

[0008] 3. This invention leverages a spatiotemporal safety scoring model to enable vehicles to flexibly adjust their driving strategies based on the spatiotemporal safety scores of different road conditions and traffic scenarios. In environments with lower safety scores, vehicles can more cautiously plan their routes, increasing the safe distance from surrounding obstacles. In environments with higher safety scores, vehicles can appropriately improve driving efficiency, achieving a balance between safety and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic diagram of a flow chart of an intelligent vehicle obstacle avoidance method based on a spatiotemporal environment safety scoring model provided by an embodiment of the present invention; Figure 2 Path simulation comparison diagram of the method of the present invention, the traditional ACO-GA method and the traditional APF method; Figure 3 This is a comparison chart of the path lengths of the method of the present invention and the traditional APF method at different iteration times. DETAILED DESCRIPTION

[0010] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the embodiments of the present invention, and should not be construed as limiting the present invention.

[0011] See also Figure 1 , an embodiment of the present invention provides an intelligent vehicle obstacle avoidance method based on a spatiotemporal environment safety scoring model, comprising steps S1-S5.

[0012] In step S1, an extended Kalman filter is used to fuse multi-sensor data to obtain a rasterized environment model, and the current position of the vehicle, the position of the obstacle, and the target position of the vehicle are obtained based on the rasterized environment model.

[0013] Among them, the state update equation of the extended Kalman filter is:

[0014] in, It is the fused state estimate, which is the updated state estimate based on the current measurement value and the prior estimate, and is also the posterior state estimate; It is in The prior state estimate at each moment is based on the state estimate at the previous moment and the system model prediction; is the Kalman gain, is the measured value at the current moment, is the measurement matrix; is the weighted coefficient matrix, which is used to adjust the influence of obstacle size on state estimation; Indicates the size parameter of the obstacle.

[0015] In step S2, a spatiotemporal environment safety scoring model is established by introducing a nonlinear adjustment factor into the ant colony algorithm to obtain the final probability of each ant path being selected.

[0016] Wherein, step S2 specifically includes: Step S201: The vehicle speed and the distance between the vehicle and the obstacle are set as target parameters. The convergence speed is measured by comparing the changes in the historical optimal value of each target parameter within a preset period. The corresponding convergence degree is calculated for each target parameter. The convergence degree of each target parameter is normalized to obtain a nonlinear adjustment factor for each target parameter. Step S202: introducing a nonlinear adjustment factor into the ant colony algorithm, constructing a spatiotemporal environment safety score model, and calculating the spatiotemporal environment safety score of the ant path; Step S203: Based on the spatiotemporal environmental safety score, the ant population's initial selection probability for the ant path is calculated, and combined with the vehicle's speed and the distance between the vehicle and the obstacle, the real-time congestion degree of the ant population is obtained; Step S204, introducing the spatiotemporal environment safety score into the ant colony algorithm to obtain an enhanced pheromone value; In step S205 , the mutation probability of the ant population is obtained based on the enhanced pheromone value and the real-time crowding of the ant population. The final selection probability function is constructed in combination with the initial selection probability of the ant population for the ant path to obtain the final probability of each ant path being selected.

[0017] Wherein, step S201 satisfies the following conditional formula:

[0018]

[0019] in, For the Target at the moment The convergence degree of , which indicates the convergence speed of the target; is the maximum convergence degree among all objectives, For the Target at the moment The optimal value of is the observation window size, which indicates the time interval for calculating convergence; For the Target at the moment The optimal value of For the Target at the moment The nonlinear adjustment factor, is the basic regulatory factor. In this embodiment, .

[0020] Step S202 satisfies the following conditional formula:

[0021]

[0022]

[0023] in, For the ant path at time The space-time environment safety score, is the nonlinear adjustment factor of the speed adjustment term, is the nonlinear adjustment factor of the distance adjustment term, is the normalized speed, is the normalized distance between the vehicle and the obstacle, for The speed of the vehicle at that moment, for The distance between the vehicle and the obstacle at any moment, is the target speed, is the safe distance between the vehicle and the obstacle, is the maximum speed of the vehicle, The maximum distance that the vehicle's sensors can sense.

[0024] Step S203 satisfies the following conditional formula:

[0025]

[0026] in, is the ant path at time The primary probability of being selected, For all candidate ant paths at time The maximum space-time environmental safety score, For the The real-time congestion of the ant population at the iteration, For the The number of times the ant path appears in the ant population at the iteration, is the number of ants in the ant population, is the maximum number of iterations, is the weight coefficient of obstacle avoidance urgency, is the weight coefficient of speed sensitivity, is the distance between the vehicle and the nearest obstacle, is the speed adjustment coefficient.

[0027] Step S204 satisfies the following conditional formula:

[0028] in, for Enhanced pheromone value, is the original pheromone value.

[0029] Step S205 satisfies the following conditional formula:

[0030]

[0031] in, for The first in the ant population The mutation probability of an ant, is the maximum pheromone value, is the attenuation coefficient, is the adjustment factor for the primary election probability, for The final probability of the ant path being selected.

[0032] When , it is in a simple non-interaction state, indicating a basic state without additional regulation. When , there is a reinforcing interaction in the system, and the probability will be further amplified as its own value increases, forming a mechanism of priority reinforcement. When , there is an inhibitory interaction in the system, and the probability will be inhibited by itself. As the probability increases, its amplified effect will weaken, playing a role in stabilizing or balancing the system.

[0033] Step S3: Based on the final probability of each ant path being selected, an enhanced pheromone update function is constructed using the improved genetic algorithm fitness formula to obtain an updated ant path.

[0034] Among them, the expression of the improved genetic algorithm fitness formula is:

[0035]

[0036]

[0037] in, is the fitness of the genetic algorithm, is the weight coefficient of path length, is the weight coefficient of the comfort index, is the weight coefficient of driving safety, is the normalized ant path length, is the normalized vehicle acceleration, is the current ant path length, and are the maximum and minimum lengths of ant paths, is the current vehicle acceleration, and are the maximum and minimum values ​​of vehicle acceleration respectively; The expression of the enhanced pheromone update function is:

[0038]

[0039] in, For the An ant is at the edge of the obstacle The increase in pheromone released is the total amount of pheromone, For the The length of the path taken by the ants; is the indicator function, if ants pass through the edge of the obstacle in this iteration ,but ,otherwise, ; is the pheromone volatility coefficient; 、 is the weight coefficient, which is used to balance the fitness of the genetic algorithm and the urgency of obstacle avoidance; for The pheromone value after constant enhancement.

[0040] In step S4, a driving environment model is established based on the current position and target position of the vehicle, and the target direction, obstacle direction, and integrated motion direction vector matrix are calculated; feasible paths that meet target point matching and are collision-free are selected from all updated ant paths to obtain a preliminary planned path.

[0041] Among them, the target direction vector matrix Represents the direction from the vehicle's current position to the target position, expressed as:

[0042] in, is the current position of the vehicle, is the target position of the vehicle, is the heading angle, is the time interval; Obstacle direction vector matrix Represents the direction from the vehicle's current position to each obstacle, expressed as:

[0043] in, is the steering angle of the vehicle relative to the nearest obstacle; Comprehensive motion direction vector matrix It is the weighted sum of the target direction vector and all obstacle direction vectors, and its expression is:

[0044]

[0045]

[0046] in, is the target factor, is the obstacle factor, is the number of obstacles.

[0047] In step S5, the spatiotemporal environmental safety scoring model established in step S2 is introduced into the artificial potential field to obtain improved gravitational field and repulsive field functions, and the improved gravitational field and repulsive field functions are applied to the preliminary planned path. Then, combined with the driving environment model, the path is adjusted and updated to finally obtain the optimal obstacle avoidance path.

[0048] Traditional potential field methods are prone to falling into extreme values ​​and optimality in complex obstacle scenarios, making it impossible to reach the target point. In this invention, a spatiotemporal environmental safety score is introduced for improvement. In the gravitational field, the spatiotemporal environmental safety score model dynamically adjusts the target attraction, allowing the vehicle to take into account environmental safety while reaching the target, avoiding potential dangers caused by excessive pursuit of speed; in the repulsive field, the spatiotemporal environmental safety score model enhances or weakens the repulsive force in real time according to the safety of the environment, enabling the vehicle to more effectively cope with obstacles in dynamic and complex environments, improving the safety and reliability of obstacle avoidance.

[0049] Specifically, in this embodiment, the improved expression of the gravitational field is:

[0050] in, for The gravitational field strength at that moment, is the gravitational strength coefficient, for The distance between the vehicle and the target position at the moment; The expression of the improved repulsive field function is:

[0051] in, for The size of the repulsive field at any moment, is the repulsive strength coefficient, is the range of potential field.

[0052] Figure 2 This is a path comparison diagram of the method of the present invention, the traditional ACO-GA method (traditional ant colony-genetic fusion method) and the traditional APF method (traditional artificial potential field method). The simulation experiment uses MatlabR2024a version. In the simulation, the black solid squares represent obstacles, and the coordinates of some obstacles are (5, 7), (5.5, 0.5), (2, 14), (12, 14); the circle is the starting point, and the coordinates are (0.5, 0.5); the five-pointed star represents the target point, and the coordinates are (19.5, 19.5). Figure 2 It can be seen that compared with the traditional APF method, the method of the present invention can effectively solve the problem of unreachable targets, and the planned obstacle avoidance path is smoother and more stable; compared with the traditional ACO-GA method, the present invention takes into account factors such as the actual size of the vehicle and the vehicle turning radius, is more in line with the physical constraints of vehicle motion, and has higher feasibility in practical applications.

[0053] Figure 3 This is a comparison diagram of the path length between the present invention and the traditional APF method (traditional artificial potential field method) at different iteration times. Figure 3It can be seen that the method of the present invention can quickly find a high-quality path and maintain stability, effectively avoid the problem of falling into the local optimum, and has a faster convergence speed and better stability.

[0054] comprehensive Figure 2 and Figure 3 It can be seen that compared with the traditional method, the present invention not only effectively solves the problem that the algorithm is prone to falling into local optimality, but also obtains an obstacle avoidance path with shorter distance and higher smoothness, which can achieve safe and efficient obstacle avoidance.

[0055] In summary, the intelligent vehicle obstacle avoidance method based on the spatiotemporal environment safety scoring model according to the above embodiment has the following beneficial effects: 1. Based on the final probability of each ant path being selected, the present invention uses an improved genetic algorithm fitness formula to construct an enhanced pheromone update function. This function eliminates the need for pheromone updates solely relying on path length, allowing the selection probability and fitness value of a path to comprehensively reflect the quality of the path. Pheromones are dynamically adjusted accordingly, improving the adaptive capability of obstacle avoidance in complex traffic scenarios.

[0056] 2. This invention combines a spatiotemporal environmental safety scoring model to conduct a real-time assessment of the vehicle's driving environment. By dynamically adjusting the magnitude and direction of gravity and repulsion, it plans the optimal obstacle avoidance path, effectively avoiding collision risks, improving the safety and reliability of obstacle avoidance, and reducing the possibility of accidents.

[0057] 3. This invention leverages a spatiotemporal safety scoring model to enable vehicles to flexibly adjust their driving strategies based on the spatiotemporal safety scores of different road conditions and traffic scenarios. In environments with lower safety scores, vehicles can more cautiously plan their routes, increasing the safe distance from surrounding obstacles. In environments with higher safety scores, vehicles can appropriately improve driving efficiency, achieving a balance between safety and efficiency.

[0058] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the patent for this invention shall be determined by the appended claims.

Claims

1. An intelligent vehicle obstacle avoidance method based on a spatiotemporal environment safety scoring model, characterized in that: include: Step S1: Using an extended Kalman filter to fuse multi-sensor data to obtain a gridded environment model, and obtaining the vehicle's current position, obstacle positions, and target position based on the gridded environment model; Step S2: By introducing a nonlinear adjustment factor into the ant colony algorithm, a spatiotemporal environment safety scoring model is established to obtain the final probability of each ant path being selected; Step S3, based on the final probability of each ant path being selected, an enhanced pheromone update function is constructed using the improved genetic algorithm fitness formula to obtain an updated ant path; Step S4: Establish a driving environment model based on the vehicle's current position and target position, and calculate the target direction, obstacle direction, and integrated motion direction vector matrix; select feasible paths that meet the target point matching and are collision-free from all updated ant paths, thereby obtaining a preliminary planned path; In step S5, the spatiotemporal environmental safety scoring model established in step S2 is introduced into the artificial potential field to obtain improved gravitational field and repulsive field functions, and the improved gravitational field and repulsive field functions are applied to the preliminary planned path. Then, combined with the driving environment model, the path is adjusted and updated to finally obtain the optimal obstacle avoidance path.

2. The intelligent vehicle obstacle avoidance method based on the spatiotemporal environment safety scoring model according to claim 1 is characterized in that: Step S2 specifically includes: Step S201: The vehicle speed and the distance between the vehicle and the obstacle are set as target parameters. The convergence speed is measured by comparing the changes in the historical optimal value of each target parameter within a preset period. The corresponding convergence degree is calculated for each target parameter. The convergence degree of each target parameter is normalized to obtain a nonlinear adjustment factor for each target parameter. Step S202: introducing a nonlinear adjustment factor into the ant colony algorithm, constructing a spatiotemporal environment safety score model, and calculating the spatiotemporal environment safety score of the ant path; Step S203: Based on the spatiotemporal environmental safety score, the ant population's initial selection probability for the ant path is calculated, and combined with the vehicle's speed and the distance between the vehicle and the obstacle, the real-time congestion degree of the ant population is obtained; Step S204, introducing the spatiotemporal environment safety score into the ant colony algorithm to obtain an enhanced pheromone value; In step S205 , the mutation probability of the ant population is obtained based on the enhanced pheromone value and the real-time crowding of the ant population. The final selection probability function is constructed in combination with the initial selection probability of the ant population for the ant path to obtain the final probability of each ant path being selected.

3. The intelligent vehicle obstacle avoidance method based on the spatiotemporal environment safety scoring model according to claim 2 is characterized in that: Step S201 satisfies the following conditional formula: in, For the Target at the moment The convergence of is the maximum convergence degree among all objectives, For the Target at the moment The optimal value of is the observation window size, For the Target at the moment The optimal value of For the Target at the moment The nonlinear adjustment factor, Basic regulatory factor.

4. The intelligent vehicle obstacle avoidance method based on the spatiotemporal environment safety scoring model according to claim 3 is characterized in that: Step S202 satisfies the following conditional formula: in, For the ant path at time The space-time environment safety score, is the nonlinear adjustment factor of the speed adjustment term, is the nonlinear adjustment factor of the distance adjustment term, is the normalized speed, is the normalized distance between the vehicle and the obstacle, for The speed of the vehicle at that moment, for The distance between the vehicle and the obstacle at any moment, is the target speed, is the safe distance between the vehicle and the obstacle, is the maximum speed of the vehicle, The maximum distance that the vehicle's sensors can sense.

5. The intelligent vehicle obstacle avoidance method based on the spatiotemporal environment safety scoring model according to claim 4 is characterized in that: Step S203 satisfies the following conditional formula: in, is the ant path at time The primary probability of being selected, For all candidate ant paths at time The maximum space-time environmental safety score, For the The real-time congestion of the ant population at the iteration, For the The number of times the ant path appears in the ant population at the iteration, is the number of ants in the ant population, is the maximum number of iterations, is the weight coefficient of obstacle avoidance urgency, is the weight coefficient of speed sensitivity, is the distance between the vehicle and the nearest obstacle, is the speed adjustment coefficient.

6. The intelligent vehicle obstacle avoidance method based on the spatiotemporal environment safety scoring model according to claim 5 is characterized in that: Step S204 satisfies the following conditional formula: in, for Enhanced pheromone value, is the original pheromone value.

7. The intelligent vehicle obstacle avoidance method based on the spatiotemporal environment safety scoring model according to claim 6 is characterized in that: Step S205 satisfies the following conditional formula: in, for The first in the ant population The mutation probability of an ant, is the maximum pheromone value, is the attenuation coefficient, is the adjustment factor for the primary election probability, for The final probability of the ant path being selected.

8. The intelligent vehicle obstacle avoidance method based on the spatiotemporal environment safety scoring model according to claim 7 is characterized in that: In step S3, the improved genetic algorithm fitness formula is expressed as: in, is the fitness of the genetic algorithm, is the weight coefficient of path length, is the weight coefficient of the comfort index, is the weight coefficient of driving safety, is the normalized ant path length, is the normalized vehicle acceleration, is the current ant path length, and are the maximum and minimum lengths of ant paths, is the current vehicle acceleration, and are the maximum and minimum values ​​of vehicle acceleration respectively; The expression of the enhanced pheromone update function is: in, For the An ant is at the edge of the obstacle The increase in pheromone released is the total amount of pheromones, For the The length of the path taken by the ants, is the indicator function, is the pheromone volatility coefficient, 、 is the weight coefficient, for The pheromone value after constant enhancement.

9. The intelligent vehicle obstacle avoidance method based on the spatiotemporal environment safety scoring model according to claim 8, characterized in that: In step S4, the target direction vector matrix The expression is: in, is the current position of the vehicle, is the target position of the vehicle, is the heading angle, is the time interval; Obstacle direction vector matrix The expression is: in, is the steering angle of the vehicle relative to the nearest obstacle; Comprehensive motion direction vector matrix The expression is: in, is the target factor, is the obstacle factor, is the number of obstacles.

10. The intelligent vehicle obstacle avoidance method based on the spatiotemporal environment safety scoring model according to claim 9, characterized in that: In step S5, the improved expression of the gravitational field is: in, for The gravitational field strength at that moment, is the gravitational strength coefficient, for The distance between the vehicle and the target position at the moment; The expression of the improved repulsive field function is: in, for The size of the repulsive field at any moment, is the repulsive strength coefficient, is the range of potential field.

Images