Intelligent logistics guide vehicle and obstacle avoidance path generation method thereof

Abstract

The invention provides a logistics intelligent guide vehicle and an obstacle avoidance path generation method thereof. The method comprises the following steps: acquiring environment sensing information of a cargo loading and unloading area in a driving process of the intelligent guide vehicle; further extracting the spatial position relationship between each dynamic obstacle in the cargo loading and unloading area and the intelligent guide vehicle; further determining a motion constraint condition of the intelligent guide vehicle beside each dynamic obstacle; determining the confidence boundary of the path deviation degree of each dynamic obstacle in the moving process according to the safe obstacle avoidance distance of the intelligent guided vehicle beside each dynamic obstacle; and according to the motion constraint condition of the intelligent guided vehicle beside each dynamic obstacle and the confidence boundary of the path deviation degree of each dynamic obstacle in the motion process, determining a collision penalty coefficient of the intelligent guided vehicle beside each dynamic obstacle, and further generating an obstacle avoidance path of the intelligent guided vehicle according to all the collision penalty coefficients. By adopting the scheme of the invention, the obstacle avoidance control of the intelligent guided vehicle can be optimized under the condition of multi-obstacle interaction conflict.

Description

Technical Field

[0001] This application relates to the field of intelligent guided vehicle control technology, and more specifically, to a logistics intelligent guided vehicle and a method for generating obstacle avoidance paths thereon. Background Technology

[0002] Automated Guided Vehicle (AGV) control is an automated transportation system applied in logistics, warehousing, and production lines. By precisely controlling the movement of the guided vehicles, it improves the efficiency of material handling and transportation. Its core control technologies include path planning, positioning and navigation, obstacle avoidance algorithms, and vehicle scheduling. Path planning technology ensures that AGVs can efficiently select the best route in complex environments and avoid collisions with obstacles. The positioning and navigation system uses technologies such as LiDAR, visual sensors, magnetic tape, or laser positioning to enable AGVs to monitor their own position in real time and make adjustments. Obstacle avoidance algorithms allow AGVs to automatically detect and avoid static or dynamic obstacles during operation, ensuring the safety of the transportation process. Vehicle scheduling technology coordinates and schedules multiple AGVs through a centralized control system to ensure their efficient and orderly operation. The application of AGV control technology not only improves the automation level of material transportation but also optimizes production and logistics management, improving overall operational efficiency and flexibility.

[0003] In practical applications, such as logistics warehousing, smart factories, or autonomous driving systems, guided vehicles often face situations where multiple dynamic obstacles (such as other mobile robots, pedestrians, or vehicles) approach simultaneously. The trajectories of these dynamic obstacles may form a conflict domain in a certain area, i.e., multiple paths intersect or tend to surround the guided vehicle. This multi-obstacle interaction conflict is difficult to resolve with a simple single obstacle avoidance strategy because multiple obstacles may affect each other, making traditional obstacle avoidance methods too conservative (premature braking, excessive detour distance) or risky (ignoring potential conflicts, leading to collision risks). In addition, since obstacles may have cooperative movements (such as queuing, vehicle crossing, etc.), avoidance methods based solely on the individual characteristics of obstacles cannot effectively quantify the impact of the joint interference of multiple obstacles. Therefore, how to optimize the obstacle avoidance control of intelligent guided vehicles under multi-obstacle interaction conflict conditions has become a challenge for the industry. Summary of the Invention

[0004] This application provides a logistics intelligent guided vehicle and its obstacle avoidance path generation method, which can optimize the obstacle avoidance control of the intelligent guided vehicle under the condition of multiple obstacle interaction and conflict.

[0005] In a first aspect, this application provides a method for generating obstacle avoidance paths for a logistics intelligent guided vehicle, used for obstacle avoidance control of the intelligent guided vehicle. The method involves the logistics intelligent guided vehicle continuously monitoring the path deviation of each dynamic obstacle within the cargo loading and unloading area during operation. When the path deviation of a dynamic obstacle exceeds a preset dynamic deviation threshold, a path replanning instruction is triggered and an obstacle avoidance path is generated. The method includes the following steps: The intelligent guided vehicle acquires environmental perception information of the cargo loading and unloading area during its operation; The spatial relationship between each dynamic obstacle and the intelligent guided vehicle in the cargo loading and unloading area is extracted from the environmental perception information. The interference impact value of each dynamic obstacle on the intelligent guided vehicle is determined based on the motion trajectory characteristics of each dynamic obstacle. The motion constraints of the intelligent guided vehicle next to each dynamic obstacle are determined by all the interference impact values ​​and the spatial positional relationship between each dynamic obstacle and the intelligent guided vehicle. The confidence boundary for the path deviation of each dynamic obstacle during its movement is determined based on the collision sensitivity of each dynamic obstacle during its movement and the safe obstacle avoidance distance of the intelligent guided vehicle next to each dynamic obstacle. The collision penalty coefficient of the intelligent guided vehicle is determined based on the motion constraints of the intelligent guided vehicle next to each dynamic obstacle and the confidence boundary of the path deviation of each dynamic obstacle during its motion. Then, the obstacle avoidance path of the intelligent guided vehicle is generated based on all the collision penalty coefficients.

[0006] In some embodiments, extracting the spatial positional relationship between each dynamic obstacle in the cargo loading and unloading area and the intelligent guided vehicle from the environmental perception information specifically includes: The geometric bounding box of each dynamic obstacle in the cargo loading and unloading area is determined based on the environmental image data within the environmental perception information. The locational correlation characteristics between various dynamic obstacles in the cargo loading and unloading area are determined by radar reflection data within the environmental perception information. The spatial relationship between each dynamic obstacle and the intelligent guided vehicle within the cargo loading and unloading area is determined based on the geometric bounding box of each dynamic obstacle and the positional association features between each dynamic obstacle.

[0007] In some embodiments, determining the interference impact value of each dynamic obstacle on the intelligent guided vehicle based on the motion trajectory characteristics of each dynamic obstacle specifically includes: Determine the trajectory characteristics of each dynamic obstacle; The collision risk value between each dynamic obstacle and the intelligent guided vehicle is determined based on the motion trajectory characteristics of each dynamic obstacle. The interference impact value of each dynamic obstacle on the intelligent guided vehicle is determined by the collision risk value between each dynamic obstacle and the intelligent guided vehicle.

[0008] In some embodiments, determining the motion constraints of the intelligent guided vehicle next to each dynamic obstacle by using all interference impact values ​​and the spatial positional relationship between each dynamic obstacle and the intelligent guided vehicle specifically includes: The stability margin of the intelligent guided vehicle's motion state next to each dynamic obstacle is determined by all the disturbance impact values; Based on all stability margins and the spatial relationship between each dynamic obstacle and the intelligent guided vehicle, determine the motion constraints of the intelligent guided vehicle next to each dynamic obstacle.

[0009] In some embodiments, determining the confidence boundary of the path deviation of each dynamic obstacle during its movement, based on the collision sensitivity of each dynamic obstacle during its movement and the safe obstacle avoidance distance of the intelligent guided vehicle next to each dynamic obstacle, specifically includes: Determine the collision sensitivity of each dynamic obstacle during its movement; The degrees of freedom of motion for each dynamic obstacle during its movement are determined based on all collision sensitivities and the safe obstacle avoidance distance of the intelligent guided vehicle next to each dynamic obstacle. Obtain the path deviation of each dynamic obstacle during its movement; Based on the degrees of freedom of movement of each dynamic obstacle during its motion, a confidence assessment is performed on the path deviation of each dynamic obstacle during its motion, thus obtaining the confidence boundary of the path deviation of each dynamic obstacle during its motion.

[0010] In some embodiments, determining the collision penalty coefficient of the intelligent guided vehicle next to each dynamic obstacle based on the motion constraints of the intelligent guided vehicle next to each dynamic obstacle and the confidence boundary of the path deviation of each dynamic obstacle during motion specifically includes: The collision risk of the intelligent guided vehicle next to each dynamic obstacle is determined by the confidence boundary of the path deviation during the movement of each dynamic obstacle. The collision penalty coefficient of the intelligent guided vehicle at each dynamic obstacle is determined based on the motion constraints of the intelligent guided vehicle at each dynamic obstacle and the collision risk of the intelligent guided vehicle at each dynamic obstacle.

[0011] In some embodiments, generating the obstacle avoidance path for the intelligent guided vehicle based on all collision penalty coefficients specifically includes: The obstacle avoidance cost of the intelligent guided vehicle at each dynamic obstacle is determined based on all collision penalty coefficients. The obstacle avoidance path of the intelligent guided vehicle is determined by the obstacle avoidance cost at each dynamic obstacle.

[0012] Secondly, this application provides a logistics intelligent guided vehicle, which includes an obstacle avoidance path generation unit, the obstacle avoidance path generation unit comprising: The acquisition module is used by the intelligent guided vehicle to acquire environmental perception information of the cargo loading and unloading area during its operation; The processing module is used to extract the spatial positional relationship between each dynamic obstacle in the cargo loading and unloading area and the intelligent guided vehicle from the environmental perception information; The processing module is also used to determine the interference impact value of each dynamic obstacle on the intelligent guided vehicle based on the motion trajectory characteristics of each dynamic obstacle, and to determine the motion constraint conditions of the intelligent guided vehicle next to each dynamic obstacle by using all the interference impact values ​​and the spatial positional relationship between each dynamic obstacle and the intelligent guided vehicle. The processing module is also used to determine the confidence boundary of the path deviation of each dynamic obstacle during its movement based on the collision sensitivity of each dynamic obstacle during its movement and the safe obstacle avoidance distance of the intelligent guided vehicle next to each dynamic obstacle. The execution module is used to determine the collision penalty coefficient of the intelligent guided vehicle next to each dynamic obstacle based on the motion constraints of the intelligent guided vehicle next to each dynamic obstacle and the confidence boundary of the path deviation of each dynamic obstacle during the motion, and then generate the obstacle avoidance path of the intelligent guided vehicle based on all the collision penalty coefficients.

[0013] Thirdly, this application provides a computer device, the computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the above-described obstacle avoidance path generation method for intelligent logistics guided vehicles.

[0014] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for generating obstacle avoidance paths for intelligent logistics guide vehicles.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: The intelligent guided vehicle and its obstacle avoidance path generation method provided in this application acquire environmental perception information of the cargo loading and unloading area during the intelligent guided vehicle's operation; extract the spatial positional relationship between each dynamic obstacle in the cargo loading and unloading area and the intelligent guided vehicle from the environmental perception information; determine the interference impact value of each dynamic obstacle on the intelligent guided vehicle based on the motion trajectory characteristics of each dynamic obstacle; determine the motion constraint conditions of the intelligent guided vehicle next to each dynamic obstacle based on all interference impact values ​​and the spatial positional relationship between each dynamic obstacle and the intelligent guided vehicle; determine the confidence boundary of the path deviation of each dynamic obstacle during its movement based on the collision sensitivity of each dynamic obstacle during its movement and the safe obstacle avoidance distance of the intelligent guided vehicle next to each dynamic obstacle; determine the collision penalty coefficient of the intelligent guided vehicle next to each dynamic obstacle based on the motion constraint conditions of the intelligent guided vehicle next to each dynamic obstacle and the confidence boundary of the path deviation of the intelligent guided vehicle during its movement; and then generate the obstacle avoidance path of the intelligent guided vehicle based on all collision penalty coefficients.

[0016] Therefore, this application can determine the collision penalty coefficient of the intelligent guided vehicle (ARTV) at each dynamic obstacle based on the motion constraints of the ARTV at each dynamic obstacle and the confidence boundary of the path deviation of each dynamic obstacle during its movement. Firstly, extracting the spatial relationship between each dynamic obstacle and the ARTV from environmental perception information helps to accurately characterize the dynamic interaction in a multi-obstacle environment, thereby assessing the joint interference effect between various dynamic obstacles. Secondly, by analyzing the trajectory characteristics of each dynamic obstacle and determining its interference effect on the ARTV, the degree of influence of obstacles in complex interactive environments can be accurately assessed. Furthermore, determining the motion constraints of the ARTV at each dynamic obstacle helps to optimize obstacle avoidance control in a multi-obstacle interaction conflict environment. By dynamically adjusting the motion constraints, the ARTV can flexibly avoid conflict areas in complex environments, reduce unnecessary detours, and improve path planning. The system optimizes obstacle avoidance control under conditions of multiple obstacle interactions and conflicts. First, it determines the confidence boundary of the path deviation of each dynamic obstacle during its movement. This confidence boundary allows the intelligent guided vehicle to distinguish the risk levels of different obstacles and rationally adjust its obstacle avoidance strategy. This avoids excessive avoidance that could affect traffic efficiency while reducing collision risk, thus achieving safer obstacle avoidance control in complex multi-obstacle environments. Second, it determines the collision penalty coefficient for the intelligent guided vehicle next to each dynamic obstacle. This collision penalty coefficient represents the increased constraint strength added to reduce the risk of collision between the intelligent guided vehicle and dynamic obstacles under the influence of multiple obstacle interactions and conflicts. The collision penalty coefficient balances avoidance distance and driving efficiency, avoiding excessive detours and improving the accuracy of obstacle avoidance decisions, thus achieving efficient multi-obstacle obstacle avoidance control. Finally, it generates the obstacle avoidance path for the intelligent guided vehicle based on all collision penalty coefficients. In summary, the solution of this application can optimize obstacle avoidance control of intelligent guided vehicles under conditions of multiple obstacle interactions and conflicts. Attached Figure Description

[0017] Figure 1 This is an exemplary flowchart of a method for generating obstacle avoidance paths for a logistics intelligent guided vehicle according to some embodiments of this application; Figure 2 This is a flowchart illustrating the determination of spatial positional relationships according to some embodiments of this application; Figure 3 This is a flowchart illustrating the determination of confidence boundaries for path deviation according to some embodiments of this application; Figure 4 This is a schematic diagram of the structure of an obstacle avoidance path generation unit according to some embodiments of this application; Figure 5This is a schematic diagram of the structure of a computer device for implementing an obstacle avoidance path generation method for intelligent logistics guide vehicles, according to some embodiments of this application. Detailed Implementation

[0018] To better understand the technical solution of this application, the technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0019] refer to Figure 1 The figure is an exemplary flowchart of an obstacle avoidance path generation method for a logistics intelligent guided vehicle according to some embodiments of this application. The obstacle avoidance path generation method 100 for the logistics intelligent guided vehicle mainly includes the following steps: In step 101, the intelligent guided vehicle acquires environmental perception information of the cargo loading and unloading area during its journey.

[0020] In practice, the intelligent guided vehicle acquires environmental perception information of the cargo loading and unloading area through built-in visual and radar sensors during its journey.

[0021] It should be noted that the environmental perception information described in this application consists of environmental image data and radar reflection data of the cargo loading and unloading area. The environmental image data consists of multiple environmental images collected by various visual sensors built into the intelligent guided vehicle, and the radar reflection data consists of the spatial coordinates and velocities of various dynamic obstacles collected by various lidars built into the intelligent guided vehicle.

[0022] It should also be noted that while acquiring environmental perception information of the cargo loading and unloading area during its operation, the intelligent guided vehicle continuously monitors the path deviation of dynamic obstacles. When the path deviation of a dynamic obstacle exceeds a preset dynamic deviation threshold, a path replanning command is triggered, and an obstacle avoidance path is generated. Specifically, the various visual sensors built into the intelligent guided vehicle identify each dynamic obstacle in the cargo loading and unloading area using existing target detection technologies (such as the YOLOv7 model). Then, the various LiDARs built into the intelligent guided vehicle acquire the real-time continuously changing spatial coordinates and velocity of each dynamic obstacle. These real-time continuously changing spatial coordinates and velocities of each dynamic obstacle are combined into a vector, and the resulting vector is used as the state vector of each dynamic obstacle. The time interval for continuous change can be set to 0.2 seconds. Finally, a Kalman filter algorithm is used to analyze the path deviation of each dynamic obstacle. The state vectors of obstacles are predicted to obtain the predicted state vectors of each dynamic obstacle. Further, for each dynamic obstacle, the Euclidean distance between the dynamic obstacle's state vector and the predicted state vector is calculated, and this Euclidean distance is used as the path deviation of the dynamic obstacle, thus obtaining the path deviation of each dynamic obstacle. The path deviation represents the degree of difference between the actual trajectory and the predicted trajectory of the dynamic obstacle. The preset dynamic deviation threshold in this application represents the parameter value for the adaptive path replanning instruction. The dynamic deviation threshold can be set as the average of each path deviation. The path replanning instruction is a control instruction triggered when the intelligent guided vehicle detects a safety risk in the current driving path during operation. The purpose of this control instruction is to require the intelligent guided vehicle to recalculate a new driving path to avoid obstacles and ensure the driving safety of the intelligent guided vehicle.

[0023] In step 102, the spatial positional relationship between each dynamic obstacle in the cargo loading and unloading area and the intelligent guided vehicle is extracted from the environmental perception information.

[0024] In some embodiments, reference Figure 2 As shown in the figure, this is a flowchart illustrating the determination of spatial relationships in some embodiments of this application. In this embodiment, the extraction of the spatial relationship between each dynamic obstacle in the cargo loading and unloading area and the intelligent guided vehicle from the environmental perception information can be achieved through the following steps. The geometric bounding box of each dynamic obstacle in the cargo loading and unloading area is determined based on the environmental image data within the environmental perception information. The locational correlation characteristics between various dynamic obstacles in the cargo loading and unloading area are determined by radar reflection data within the environmental perception information. The spatial relationship between each dynamic obstacle and the intelligent guided vehicle within the cargo loading and unloading area is determined based on the geometric bounding box of each dynamic obstacle and the positional association features between each dynamic obstacle.

[0025] In specific implementation, determining the geometric bounding box of each dynamic obstacle in the cargo loading and unloading area based on the environmental image data within the environmental perception information can be achieved in the following way: First, acquire each identified dynamic obstacle in the cargo loading and unloading area. Then, use existing target detection technology (YOLOv7 model) to perform target detection on each environmental image in the environmental image data to obtain the bounding box of the dynamic obstacle in each environmental image. Furthermore, if the dynamic obstacle appears in multiple environmental images simultaneously, select the largest bounding box from the multiple environmental images as the geometric bounding box of the dynamic obstacle in the cargo loading and unloading area, thereby obtaining the geometric bounding box of each dynamic obstacle in the cargo loading and unloading area. Other methods can also be used in other embodiments, which will not be elaborated here.

[0026] It should be noted that the geometric bounding box described in this application represents the geometric data information of the bounding box of a dynamic obstacle, wherein the geometric bounding box is represented by four coordinates (the upper left corner coordinate and the lower right corner coordinate).

[0027] In specific implementation, determining the positional association characteristics between various dynamic obstacles in the cargo loading and unloading area using radar reflection data within the environmental perception information can be achieved in the following way: First, the distance between every two dynamic obstacles in the cargo loading and unloading area is calculated using radar reflection data. For each dynamic obstacle, the distance between the two closest dynamic obstacles is taken as the nearest neighbor distance, thus obtaining multiple nearest neighbor distances. Then, the sum of the distances between the intelligent guided vehicle and each dynamic obstacle is divided by the sum of all nearest neighbor distances, and the value obtained by division is taken as the positional association characteristics between various dynamic obstacles in the cargo loading and unloading area. Other methods can also be used in other embodiments, which are not limited here.

[0028] It should be noted that the location association features described in this application represent feature parameters that describe the location distribution among various dynamic obstacles around the intelligent guided vehicle.

[0029] In specific implementation, the spatial positional relationship between each dynamic obstacle and the intelligent guided vehicle in the cargo loading and unloading area can be determined based on the geometric bounding box of each dynamic obstacle and the positional association features between each dynamic obstacle. This can be achieved in the following way: For each dynamic obstacle, the distance between the dynamic obstacle and the intelligent guided vehicle is divided by the area of ​​the geometric bounding box of the dynamic obstacle. The result of this division is then multiplied by the positional association features between each dynamic obstacle, and the multiplied value is used as the spatial positional relationship between the dynamic obstacle and the intelligent guided vehicle in the cargo loading and unloading area. This yields the spatial positional relationship between each dynamic obstacle and the intelligent guided vehicle in the cargo loading and unloading area. Other methods can also be used in other embodiments, which will not be elaborated here.

[0030] It should be noted that the spatial relationship described in this application refers to the parameter of the degree of spatial congestion between the intelligent guided vehicle and dynamic obstacles in the cargo loading and unloading area.

[0031] In step 103, the interference impact value of each dynamic obstacle on the intelligent guided vehicle is determined based on the motion trajectory characteristics of each dynamic obstacle. The motion constraint conditions of the intelligent guided vehicle next to each dynamic obstacle are determined by all the interference impact values ​​and the spatial positional relationship between each dynamic obstacle and the intelligent guided vehicle.

[0032] In some embodiments, determining the interference impact value of each dynamic obstacle on the intelligent guided vehicle based on the motion trajectory characteristics of each dynamic obstacle can be achieved through the following steps: Determine the trajectory characteristics of each dynamic obstacle; The collision risk value between each dynamic obstacle and the intelligent guided vehicle is determined based on the motion trajectory characteristics of each dynamic obstacle. The interference impact value of each dynamic obstacle on the intelligent guided vehicle is determined by the collision risk value between each dynamic obstacle and the intelligent guided vehicle.

[0033] In specific implementation, the motion trajectory characteristics of each dynamic obstacle can be determined in the following way: For each dynamic obstacle, the state vector of the dynamic obstacle is obtained, and an existing spline interpolation algorithm (such as cubic spline interpolation) is used to perform spline interpolation on the state vector of the dynamic obstacle. The spline interpolated curve is used as the spline interpolation curve. Then, the curvature at each position of the spline interpolation curve is calculated, and the mean of all curvatures is calculated. The mean value is used as the motion trajectory characteristics of the dynamic obstacle, thus obtaining the motion trajectory characteristics of each dynamic obstacle. Other methods can also be used in other embodiments, which are not limited here.

[0034] It should be noted that the motion trajectory features described in this application represent feature parameters that describe the complexity of the motion of dynamic obstacles.

[0035] In specific implementation, the collision risk value between each dynamic obstacle and the intelligent guided vehicle can be determined based on the motion trajectory characteristics of each dynamic obstacle in the following way: For each dynamic obstacle, the distance between the dynamic obstacle and the intelligent guided vehicle is divided by the absolute value of the speed difference between the dynamic obstacle and the intelligent guided vehicle. The value obtained by division is then multiplied by the motion trajectory characteristics of the dynamic obstacle, and the result of the multiplication is taken as the collision risk value between the dynamic obstacle and the intelligent guided vehicle, thereby obtaining the collision risk value between each dynamic obstacle and the intelligent guided vehicle. Other methods can also be used in other embodiments, which are not limited here.

[0036] It should be noted that the collision risk value described in this application represents an indicator of the probability of a collision between a dynamic obstacle and the intelligent guided vehicle.

[0037] In specific implementation, determining the interference impact value of each dynamic obstacle on the intelligent guided vehicle by the collision risk value between each dynamic obstacle and the intelligent guided vehicle can be achieved in the following way: For each dynamic obstacle, divide the distance between the dynamic obstacle and the intelligent guided vehicle by the speed of the dynamic obstacle, multiply the value obtained by the collision risk value between the dynamic obstacle and the intelligent guided vehicle, and use the multiplied value as the interference impact value of the dynamic obstacle on the intelligent guided vehicle, thereby obtaining the interference impact value of each dynamic obstacle on the intelligent guided vehicle. Other methods can also be used in other embodiments, which will not be elaborated here.

[0038] It should be noted that the interference impact value described in this application represents a quantitative indicator of the potential interference caused by dynamic obstacles to the intelligent guided vehicle.

[0039] In some embodiments, determining the motion constraints of the intelligent guided vehicle next to each dynamic obstacle by using all disturbance impact values ​​and the spatial positional relationship between each dynamic obstacle and the intelligent guided vehicle can be achieved through the following steps: The stability margin of the intelligent guided vehicle's motion state next to each dynamic obstacle is determined by all the disturbance impact values; Based on all stability margins and the spatial relationship between each dynamic obstacle and the intelligent guided vehicle, determine the motion constraints of the intelligent guided vehicle next to each dynamic obstacle.

[0040] In practice, determining the stability margin of the intelligent guided vehicle's motion state next to each dynamic obstacle by using all interference impact values ​​can be achieved through the following steps: Based on the sliding window technique, the square root of the total number of dynamic obstacles is taken down, and this down-rounded value is used as the length of the sliding window. The sliding step size is set to 1. All interference impact values ​​are sorted in ascending order, and this sorted sequence is used as the interference impact value sequence. The sliding window is then aligned with the first interference impact value in the sequence. The interference impact value of the maximum value covered by the sliding window is subtracted from the interference impact value of the minimum value covered by the sliding window. This subtraction is then divided by the first interference impact value, and the resulting value is used as the motion state of the intelligent guided vehicle next to the dynamic obstacle corresponding to the first interference impact value. To determine the stability margin of the intelligent guided vehicle's motion state near the dynamic obstacle corresponding to the second interference value in the interference influence value sequence, the sliding window is moved to align with the second interference influence value in the interference influence value sequence. The interference influence value of the maximum value covered by the sliding window is subtracted from the interference influence value of the minimum value covered by the sliding window. The result of the subtraction is then divided by the second interference influence value, and the result of the division is used as the stability margin of the intelligent guided vehicle's motion state near the dynamic obstacle corresponding to the second interference influence value. The sliding window is moved sequentially to obtain the stability margin of the intelligent guided vehicle's motion state near the dynamic obstacle corresponding to the remaining interference influence values, until the sliding window aligns with the second-to-last interference influence value in the interference influence value sequence. Finally, the stability margin of the intelligent guided vehicle's motion state near the dynamic obstacle corresponding to the last interference influence value is set to 0. Other methods can also be used in other embodiments, which are not limited here.

[0041] It should be noted that the stability margin mentioned in this application refers to the ability of the intelligent guided vehicle to maintain stability when passing by dynamic obstacles in its current state of motion.

[0042] In specific implementation, the motion constraints of the intelligent guided vehicle next to each dynamic obstacle can be determined based on all stability margins and the spatial positional relationship between each dynamic obstacle and the intelligent guided vehicle. This can be achieved in the following way: First, all stability margins are normalized, and the normalized values ​​are used as the standard values ​​of the stability margins of the intelligent guided vehicle's motion state next to each dynamic obstacle. Then, for each dynamic obstacle, the standard value of the stability margin of the intelligent guided vehicle's motion state next to the dynamic obstacle is multiplied by the spatial positional relationship between the dynamic obstacle and the intelligent guided vehicle. The multiplied value is then used to calculate a negative exponential function with the natural logarithm e as the base. The value obtained after calculating the negative exponential function with the natural logarithm e as the base is used as the motion constraint of the intelligent guided vehicle next to the dynamic obstacle. Thus, the motion constraint of the intelligent guided vehicle next to each dynamic obstacle is obtained. Other methods can also be used in other embodiments, which will not be elaborated here.

[0043] It should be noted that the motion constraint conditions described in this application refer to the parameters that constrain the intelligent guided vehicle's motion state next to the dynamic obstacles when multiple dynamic obstacles interact and conflict. The motion state includes speed, acceleration, steering angle, and angular velocity.

[0044] In step 104, the confidence boundary of the path deviation of each dynamic obstacle during movement is determined based on the collision sensitivity of each dynamic obstacle during movement and the safe obstacle avoidance distance of the intelligent guided vehicle next to each dynamic obstacle.

[0045] In some embodiments, reference Figure 3 As shown in the figure, this is a flowchart illustrating the process of determining the confidence boundary of path deviation in some embodiments of this application. In this embodiment, the confidence boundary of path deviation of each dynamic obstacle during its movement can be determined based on the collision sensitivity of each dynamic obstacle during its movement and the safe obstacle avoidance distance of the intelligent guided vehicle next to each dynamic obstacle using the following steps: First, in step 1041, the collision sensitivity of each dynamic obstacle during its motion is determined; Secondly, in step 1042, the degrees of freedom of motion of each dynamic obstacle during the movement are determined based on all collision sensitivities and the safe obstacle avoidance distance of the intelligent guided vehicle next to each dynamic obstacle; Then, in step 1043, the path deviation of each dynamic obstacle during its movement is obtained; Finally, in step 1044, the confidence assessment of the path deviation of each dynamic obstacle during its motion is performed based on the degree of freedom of motion of each dynamic obstacle during its motion, thereby obtaining the confidence boundary of the path deviation of each dynamic obstacle during its motion.

[0046] It should be noted that the collision sensitivity described in this application represents the ability of a dynamic obstacle to respond to the threat of collision with other dynamic obstacles during its movement. Collision sensitivity measures the sensitivity and reaction degree of a dynamic obstacle to potential collisions when it approaches other dynamic obstacles. As a preferred embodiment, the collision sensitivity of each dynamic obstacle during its movement can be determined in the following way: a dynamic obstacle is selected as the selected dynamic obstacle, and the intelligent guided vehicle is used as the dynamic obstacle. The dynamic obstacle closest to the selected dynamic obstacle is selected from the vicinity of the selected dynamic obstacle as the nearest dynamic obstacle. The distance between the selected dynamic obstacle and the nearest dynamic obstacle is divided by the sum of the speeds of the selected dynamic obstacle and the nearest dynamic obstacle. The value obtained by the division is used as the collision sensitivity of the selected dynamic obstacle during its movement. The collision sensitivity of the remaining dynamic obstacles during their movement is then determined. Other methods can also be used in other embodiments, which are not limited here.

[0047] Additionally, it should be noted that the safe obstacle avoidance distance described in this application represents the minimum space range that the intelligent guided vehicle needs to maintain to avoid collisions with dynamic obstacles. Specifically, the safe obstacle avoidance distance of the intelligent guided vehicle next to each dynamic obstacle can be determined in the following way: the speed value of the intelligent guided vehicle is squared, the squared value is divided by the maximum deceleration of the intelligent guided vehicle, and the result of the division is multiplied by the reaction time of the intelligent guided vehicle. The reaction time can be set to 0.5 seconds, which is not limited here. The result of the multiplication is further added to the median distance between the intelligent guided vehicle and the dynamic obstacle, and the sum is taken as the safe obstacle avoidance distance of the intelligent guided vehicle next to the dynamic obstacle. Thus, the safe obstacle avoidance distance of the intelligent guided vehicle next to each dynamic obstacle is obtained. Other methods can also be used in other embodiments, which are not limited here.

[0048] In specific implementation, the degree of freedom of motion of each dynamic obstacle during its movement can be determined based on all collision sensitivities and the safe obstacle avoidance distance of the intelligent guided vehicle next to each dynamic obstacle. This can be achieved in the following way: for each dynamic obstacle, the collision sensitivity of the dynamic obstacle during its movement is added to the safe obstacle avoidance distance of the intelligent guided vehicle next to the dynamic obstacle, and the sum is taken as the degree of freedom of motion of the dynamic obstacle during its movement. Thus, the degree of freedom of motion of each dynamic obstacle during its movement can be obtained. Other methods can also be used in other embodiments, which will not be elaborated here.

[0049] It should be noted that the degrees of freedom of motion described in this application refer to the degree to which a dynamic obstacle can move freely during the movement of the cargo loading and unloading area.

[0050] In specific implementation, the confidence assessment of the path deviation of each dynamic obstacle during its motion is performed based on its degrees of freedom. The confidence boundary for the path deviation of each dynamic obstacle can be obtained in the following way: First, an existing linear fitting algorithm (such as the least squares support vector machine algorithm) is used to linearly fit all degrees of freedom, and the fitted curve is taken as the degree of freedom curve. Each value on the degree of freedom curve is taken as the fitted value of the degree of freedom, and each fitted value corresponds to one degree of freedom. It should be noted that each dynamic obstacle corresponds to one degree of freedom, and each degree of freedom corresponds to one fitted value; that is, each dynamic obstacle corresponds to one fitted value. Then, for each dynamic obstacle, the fitted value of the corresponding degree of freedom is... Subtract the degrees of freedom corresponding to the dynamic obstacle, then take the absolute value of the subtraction and multiply it by the path deviation of the dynamic obstacle during movement. Use the multiplied value as the deviation confidence value of the dynamic obstacle. Further, add the path deviation confidence value of the dynamic obstacle to the path deviation during movement, and use the sum as the upper confidence boundary of the path deviation during movement. Subtract the deviation confidence value of the dynamic obstacle from the path deviation during movement, and use the subtraction value as the lower confidence boundary of the path deviation during movement. Thus, the interval formed by the lower confidence boundary and the upper confidence boundary is used as the confidence boundary of the path deviation during movement, thereby obtaining the confidence boundary of the path deviation of each dynamic obstacle during movement. Other methods can be used in other embodiments, which will not be elaborated here.

[0051] It should be noted that the confidence boundary mentioned in this application represents the error range of the path deviation of a dynamic obstacle during its movement under conditions of multi-obstacle interaction and conflict.

[0052] In step 105, the collision penalty coefficient of the intelligent guided vehicle next to each dynamic obstacle is determined based on the motion constraints of the intelligent guided vehicle next to each dynamic obstacle and the confidence boundary of the path deviation of each dynamic obstacle during the motion. Then, the obstacle avoidance path of the intelligent guided vehicle is generated based on all the collision penalty coefficients.

[0053] In some embodiments, determining the collision penalty coefficient of the intelligent guided vehicle next to each dynamic obstacle based on the motion constraints of the intelligent guided vehicle next to each dynamic obstacle and the confidence boundary of the path deviation of each dynamic obstacle during motion can be achieved by the following steps: The collision risk of the intelligent guided vehicle next to each dynamic obstacle is determined by the confidence boundary of the path deviation during the movement of each dynamic obstacle. The collision penalty coefficient of the intelligent guided vehicle at each dynamic obstacle is determined based on the motion constraints of the intelligent guided vehicle at each dynamic obstacle and the collision risk of the intelligent guided vehicle at each dynamic obstacle.

[0054] In practice, the collision risk of the intelligent guided vehicle next to each dynamic obstacle can be determined by the confidence boundary of the path deviation during the movement of each dynamic obstacle in the following way: For each dynamic obstacle, the upper confidence boundary of the path deviation during the movement of the dynamic obstacle is subtracted from the lower confidence boundary of the path deviation during the movement of the dynamic obstacle. The value obtained by subtraction is then divided by the distance between the intelligent guided vehicle and the dynamic obstacle. The value obtained by division is taken as the collision risk of the intelligent guided vehicle next to the dynamic obstacle, thus obtaining the collision risk of the intelligent guided vehicle next to each dynamic obstacle.

[0055] It should be noted that the collision risk level mentioned in this application refers to the degree of potential collision risk caused by the uncertainty of the path deviation of the dynamic obstacle when the intelligent guided vehicle passes by the dynamic obstacle.

[0056] In practice, the collision penalty coefficient of the intelligent guided vehicle next to each dynamic obstacle can be determined based on the motion constraints of the intelligent guided vehicle next to each dynamic obstacle and the collision risk of the intelligent guided vehicle next to each dynamic obstacle in the following way: For each dynamic obstacle, the collision risk of the intelligent guided vehicle next to the dynamic obstacle is multiplied by the motion constraints of the intelligent guided vehicle next to the dynamic obstacle, and the value obtained by multiplication is used as the collision penalty coefficient of the intelligent guided vehicle next to the dynamic obstacle, thereby obtaining the collision penalty coefficient of the intelligent guided vehicle next to each dynamic obstacle.

[0057] It should be noted that the collision penalty coefficient mentioned in this application represents the increased constraint strength to reduce the risk of collision between the intelligent guided vehicle and dynamic obstacles under the influence of multi-obstacle interaction conflicts.

[0058] In some embodiments, generating an obstacle avoidance path for the intelligent guided vehicle based on all collision penalty coefficients can be achieved through the following steps: The obstacle avoidance cost of the intelligent guided vehicle at each dynamic obstacle is determined based on all collision penalty coefficients. The obstacle avoidance path of the intelligent guided vehicle is determined by the obstacle avoidance cost at each dynamic obstacle.

[0059] In specific implementation, the obstacle avoidance cost of the intelligent guided vehicle next to each dynamic obstacle can be determined based on all collision penalty coefficients in the following manner: For each dynamic obstacle, the speed of the dynamic obstacle is added to the speed of the intelligent guided vehicle, and then a negative exponential function with the natural logarithm e as the base is calculated on the sum. The value obtained after calculating the negative exponential function with the natural logarithm e as the base is used as the speed cost of the dynamic obstacle. Then, a negative exponential function with the natural logarithm e as the base is calculated on the distance between the intelligent guided vehicle and the dynamic obstacle, and the value obtained after calculating the negative exponential function with the natural logarithm e as the distance cost of the dynamic obstacle is used as the distance cost of the dynamic obstacle. Further, the reciprocals of the distance cost of the dynamic obstacle and the distance cost of the dynamic obstacle are taken respectively, and the two values ​​obtained after taking the reciprocals are added together. Then, the sum is multiplied by the collision penalty coefficient of the intelligent guided vehicle next to the dynamic obstacle, and the multiplied value is used as the obstacle avoidance cost of the intelligent guided vehicle next to the dynamic obstacle. Thus, the obstacle avoidance cost of the intelligent guided vehicle next to each dynamic obstacle is obtained. Other methods can also be used in other embodiments, which are not limited here.

[0060] It should be noted that the obstacle avoidance cost mentioned in this application represents the cost that the intelligent guided vehicle needs to pay in order to avoid colliding with dynamic obstacles. The obstacle avoidance cost can reflect the degree of difficulty for the intelligent guided vehicle to perform obstacle avoidance operations next to dynamic obstacles.

[0061] In practical implementation, determining the obstacle avoidance path of the intelligent guided vehicle (ARTV) based on the obstacle avoidance cost at each dynamic obstacle can be achieved in the following way: Using the dynamic window algorithm from existing dynamic obstacle avoidance algorithms, firstly, the dynamic window algorithm generates multiple candidate trajectories based on the speed and acceleration of the ARTV. The speed pair of each candidate trajectory consists of linear velocity and angular velocity. One candidate trajectory is selected as the chosen candidate trajectory. Then, one dynamic obstacle is selected from all dynamic obstacles as the chosen dynamic obstacle. The minimum distance between the chosen candidate trajectory and the chosen dynamic obstacle is added to the proximity of the chosen candidate trajectory to the target point. Finally, the sum is added to... The smoothness of the selected candidate trajectory is further multiplied by the obstacle avoidance cost of the intelligent guided vehicle next to the selected dynamic obstacle, and the multiplied value is used as the trajectory evaluation value of the selected candidate trajectory next to the selected dynamic obstacle. The trajectory evaluation values ​​of the selected candidate trajectory next to the remaining dynamic obstacles are then determined, and the trajectory evaluation values ​​of the remaining candidate trajectories next to each dynamic obstacle are determined. Then, the candidate trajectory corresponding to the smallest trajectory evaluation value is selected as the optimal trajectory. The intelligent guided vehicle will travel along the path of the optimal trajectory, and the traveled path is used as the obstacle avoidance path of the intelligent guided vehicle. Other methods can be used in other embodiments, which will not be elaborated here.

[0062] Furthermore, in another aspect of this application, in some embodiments, this application provides a logistics intelligent guided vehicle, which includes an obstacle avoidance path generation unit, referring to... Figure 4 The figure is a schematic diagram of the structure of an obstacle avoidance path generation unit according to some embodiments of this application. The obstacle avoidance path generation unit 400 includes: an acquisition module 401, a processing module 402, and an execution module 403, which are described below: The acquisition module 401 in this application is mainly used for the intelligent guided vehicle to acquire environmental perception information of the cargo loading and unloading area during the driving process; Processing module 402, in this application, is used to extract the spatial positional relationship between each dynamic obstacle in the cargo loading and unloading area and the intelligent guided vehicle from the environmental perception information; It should be noted that the processing module 402 described in this application is also used to determine the interference impact value of each dynamic obstacle on the intelligent guided vehicle based on the motion trajectory characteristics of each dynamic obstacle, and to determine the motion constraint conditions of the intelligent guided vehicle next to each dynamic obstacle by using all the interference impact values ​​and the spatial positional relationship between each dynamic obstacle and the intelligent guided vehicle. In addition, the processing module 402 described in this application is also used to determine the confidence boundary of the path deviation of each dynamic obstacle during movement based on the collision sensitivity of each dynamic obstacle during movement and the safe obstacle avoidance distance of the intelligent guided vehicle next to each dynamic obstacle. The execution module 403 in this application is mainly used to determine the collision penalty coefficient of the intelligent guided vehicle next to each dynamic obstacle based on the motion constraints of the intelligent guided vehicle next to each dynamic obstacle and the confidence boundary of the path deviation of each dynamic obstacle during the motion process, and then generate the obstacle avoidance path of the intelligent guided vehicle based on all the collision penalty coefficients.

[0063] In addition, this application also provides a computer device, the computer device including a memory and a processor, the memory storing code, the processor being configured to acquire the code and execute the above-described obstacle avoidance path generation method for intelligent logistics guided vehicles.

[0064] In some embodiments, reference Figure 5 This figure is a schematic diagram of the structure of a computer device for implementing an obstacle avoidance path generation method for a logistics intelligent guided vehicle, according to some embodiments of this application. The obstacle avoidance path generation method for the logistics intelligent guided vehicle in the above embodiments can be achieved through... Figure 5 The computer device shown is used to implement this, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503, and at least one communication interface 504.

[0065] The processor 501 can be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more devices used to control the execution of the obstacle avoidance path generation method of the intelligent logistics guided vehicle in this application.

[0066] The communication bus 502 can be used to transmit information between the aforementioned components.

[0067] Memory 503 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile optical discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory 503 may exist independently and be connected to processor 501 via communication bus 502. Memory 503 may also be integrated with processor 501.

[0068] The memory 503 stores program code for executing the scheme of this application, and its execution is controlled by the processor 501. The processor 501 executes the program code stored in the memory 503. The program code may include one or more software modules. The method described in the above method embodiments can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0069] Communication interface 504 uses any transceiver-like device to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0070] In a specific implementation, as one example, a computer device may include multiple processors, each of which may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0071] The aforementioned computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a portable computer, a network server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. This application does not limit the type of computer device.

[0072] In addition, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described obstacle avoidance path generation method for intelligent logistics guided vehicles.

[0073] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0074] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for generating an obstacle-avoiding path of a logistics intelligent guided vehicle, for obstacle-avoiding control of the intelligent guided vehicle, wherein, The method comprises the following steps: The intelligent guide vehicle obtains the environment perception information of the cargo loading and unloading area during driving; The spatial position relationship between each dynamic obstacle in the cargo loading and unloading area and the intelligent guide vehicle is extracted from the environment perception information; The interference influence value of each dynamic obstacle on the intelligent guide vehicle is determined according to the motion trajectory characteristics of each dynamic obstacle, and the motion constraint condition of the intelligent guide vehicle near each dynamic obstacle is determined through all the interference influence values and the spatial position relationship between each dynamic obstacle and the intelligent guide vehicle; The confidence boundary of the path deviation degree of each dynamic obstacle in the motion process is determined according to the collision sensitivity of each dynamic obstacle in the motion process and the safe obstacle avoidance distance of the intelligent guide vehicle near each dynamic obstacle; The collision penalty coefficient of the intelligent guide vehicle near each dynamic obstacle is determined according to the motion constraint condition of the intelligent guide vehicle near each dynamic obstacle and the confidence boundary of the path deviation degree of each dynamic obstacle in the motion process, and then the obstacle avoidance path of the intelligent guide vehicle is generated according to all the collision penalty coefficients.

2. The method of claim 1, wherein, The spatial position relationship between each dynamic obstacle in the cargo loading and unloading area and the intelligent guide vehicle extracted from the environment perception information specifically comprises: The geometric bounding box of each dynamic obstacle in the cargo loading and unloading area is determined according to the environment image data in the environment perception information; The position correlation characteristics between each dynamic obstacle in the cargo loading and unloading area are determined through the radar reflection data in the environment perception information; The spatial position relationship between each dynamic obstacle in the cargo loading and unloading area and the intelligent guide vehicle is determined according to the geometric bounding box of each dynamic obstacle and the position correlation characteristics between each dynamic obstacle.

3. The method of claim 1, wherein, Determining the interference influence value of each dynamic obstacle on the intelligent guide vehicle according to the motion trajectory characteristics of each dynamic obstacle specifically comprises: Determining the motion trajectory characteristics of each dynamic obstacle; Determining the collision risk value between each dynamic obstacle and the intelligent guide vehicle according to the motion trajectory characteristics of each dynamic obstacle; Determining the interference influence value of each dynamic obstacle on the intelligent guide vehicle through the collision risk value between each dynamic obstacle and the intelligent guide vehicle.

4. The method of claim 1, wherein, Determining the motion constraint condition of the intelligent guide vehicle near each dynamic obstacle through all the interference influence values and the spatial position relationship between each dynamic obstacle and the intelligent guide vehicle specifically comprises: Determining the stability margin of the motion state of the intelligent guide vehicle near each dynamic obstacle through all the interference influence values; Determining the motion constraint condition of the intelligent guide vehicle near each dynamic obstacle according to all the stability margins and the spatial position relationship between each dynamic obstacle and the intelligent guide vehicle.

5. The method of claim 1, wherein, Determining the confidence boundary of the path deviation degree of each dynamic obstacle in the motion process according to the collision sensitivity of each dynamic obstacle in the motion process and the safe obstacle avoidance distance of the intelligent guide vehicle near each dynamic obstacle specifically comprises: determine a collision sensitivity of each dynamic obstacle in the movement process; determine a motion freedom of each dynamic obstacle in the movement process according to all the collision sensitivities and the safe obstacle avoidance distance of the intelligent guided vehicle beside each dynamic obstacle; obtain a path deviation degree of each dynamic obstacle in the movement process; perform a confidence evaluation on the path deviation degree of each dynamic obstacle in the movement process according to the motion freedom of each dynamic obstacle in the movement process, to obtain a confidence boundary of the path deviation degree of each dynamic obstacle in the movement process.

6. The method of claim 1, wherein, determine a collision penalty coefficient of the intelligent guided vehicle beside each dynamic obstacle according to the motion constraint condition of the intelligent guided vehicle beside each dynamic obstacle and the confidence boundary of the path deviation degree of each dynamic obstacle in the movement process, specifically including: determine a collision risk of the intelligent guided vehicle beside each dynamic obstacle through the confidence boundary of the path deviation degree of each dynamic obstacle in the movement process; determine a collision penalty coefficient of the intelligent guided vehicle beside each dynamic obstacle according to the motion constraint condition of the intelligent guided vehicle beside each dynamic obstacle and the collision risk of the intelligent guided vehicle beside each dynamic obstacle.

7. The method of claim 1, wherein, generate an obstacle avoidance path of the intelligent guided vehicle according to all the collision penalty coefficients, specifically including: determine an obstacle avoidance cost of the intelligent guided vehicle beside each dynamic obstacle according to all the collision penalty coefficients; determine the obstacle avoidance path of the intelligent guided vehicle through the obstacle avoidance cost of the intelligent guided vehicle beside each dynamic obstacle.

8. A logistics intelligent guide vehicle comprising an obstacle-avoiding path generation unit, characterized in that, The obstacle avoidance path generation unit includes: an acquisition module, configured to acquire environmental perception information of the cargo loading and unloading area in the driving process of the intelligent guided vehicle; a processing module, configured to extract a spatial position relationship between each dynamic obstacle in the cargo loading and unloading area and the intelligent guided vehicle from the environmental perception information; the processing module is further configured to determine an interference influence value of each dynamic obstacle on the intelligent guided vehicle according to a movement trajectory feature of each dynamic obstacle, and determine a motion constraint condition of the intelligent guided vehicle beside each dynamic obstacle through all the interference influence values and the spatial position relationship between each dynamic obstacle and the intelligent guided vehicle; the processing module is further configured to determine a confidence boundary of a path deviation degree of each dynamic obstacle in the movement process according to the collision sensitivity of each dynamic obstacle in the movement process and the safe obstacle avoidance distance of the intelligent guided vehicle beside each dynamic obstacle; an execution module, configured to determine a collision penalty coefficient of the intelligent guided vehicle beside each dynamic obstacle according to the motion constraint condition of the intelligent guided vehicle beside each dynamic obstacle and the confidence boundary of the path deviation degree of each dynamic obstacle in the movement process, and further generate an obstacle avoidance path of the intelligent guided vehicle according to all the collision penalty coefficients. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor implements the obstacle avoidance path generation method of the intelligent guided vehicle of any one of claims 1 to 7 when executing the computer program.

10. A computer readable storage medium storing a computer program, characterized in that, The computer program is executed by the processor to implement the obstacle avoidance path generation method of the intelligent guided vehicle of any one of claims 1 to 7.

Images