Traffic cone movement control method and system and robot

Abstract

The invention discloses a traffic cone movement control method and system and a robot, and relates to the technical field of robots. Receiving a moving instruction, and detecting the to-be-detected area according to the moving instruction to obtain an obstacle distribution diagram; generating a prediction path according to the obstacle distribution map, and optimizing the prediction path to obtain an optimized path; executing path optimization, determining control parameters, and sending the control parameters to the next adjacent traffic moving cone for moving; a moving instruction is received, a to-be-detected area is detected, the system can accurately obtain an obstacle distribution map, a prediction path is generated and optimized, and an optimized path with curvature is obtained. The system can accurately control the movement of the traffic moving cones, including the control time and the operation power of the left and right wheel motors, and realizes the cooperative movement of a plurality of traffic moving cones, thereby improving the efficiency of traffic dispersion and management.

Description

Technical Field

[0001] The invention belongs to the technical field of robots, and in particular relates to a traffic cone movement control method, a system and a robot. Background Art

[0002] As an important road safety device, traffic cones are mainly used at construction sites, traffic accident sites, road maintenance areas or other places where temporary traffic guidance or restriction is required. Traffic cones can not only alert drivers to changes ahead and slow down in advance, but also guide vehicles to bypass safely, reduce the occurrence of traffic accidents, and ensure the safety of construction workers, passing vehicles and pedestrians. Traffic cones are light and easy to carry, and can be quickly deployed, which greatly improves the flexibility and efficiency of traffic management.

[0003] There are still some problems in the automated deployment process of traffic cones, mainly manifested in the slow deployment speed, which limits the timeliness of traffic diversion to a certain extent; due to the lack of precision in the moving path planning, especially when the turning angle is too large, the traffic cones are prone to tipping over during the movement, which not only affects the deployment efficiency, but also may lead to the interruption of traffic diversion work, further weakening the effect of traffic management; the collaborative control effect between multiple traffic cones is not good, and it is difficult to achieve efficient collaborative operation. Summary of the invention

[0004] The purpose of the present invention is to solve the problems that the existing traffic cone automation deployment is slow, and the traffic cone is easy to tip over during the movement because the turning angle in the moving path is too large, resulting in poor management efficiency and poor collaborative control effect, and to propose a traffic cone movement control method, system and robot.

[0005] In a first aspect of the present invention, a traffic cone movement control method is first proposed, the method comprising:

[0006] Receive a movement instruction, and detect the area to be detected according to the movement instruction to obtain an obstacle distribution map; the movement instruction is the movement coordinates of the traffic moving cone, and the area to be detected is the area between the starting coordinates and the movement coordinates;

[0007] Generate a predicted path according to the obstacle distribution map, and optimize the predicted path to obtain an optimized path; the optimized path is a path with curvature;

[0008] The optimized path is executed and control parameters are determined, and the control parameters are sent to the next adjacent traffic moving cone for movement; the control parameters are the control time and operating power of the left and right wheel motors of the traffic moving cone.

[0009] Optionally, detecting the area to be detected according to the movement instruction to obtain an obstacle distribution map includes:

[0010] Obtain a target image set of the area to be detected through a binocular camera, and input the images in the target image set into an obstacle detection model for obstacle detection; the target image set includes multiple groups of images, each group of images includes two images;

[0011] If an obstacle is detected in any set of images, the pixel difference of the same point in the set of images in the X-axis direction is calculated, and the obstacle coordinates of the obstacle in the camera coordinate system are calculated based on the pixel difference;

[0012] The obstacle coordinates are converted into a world coordinate system to obtain actual coordinates, and obstacles are marked in the area to be detected according to the actual coordinates to obtain an obstacle distribution map.

[0013] Optionally, optimizing the predicted path to obtain an optimized path includes:

[0014] Dividing the predicted path according to the deflection angle to obtain a path data set, determining the driving direction of each path data in the path data set as a direction vector, and obtaining a direction vector data set;

[0015] Calculating the vector angle between adjacent direction vectors in the direction vector data set, if the vector angle is greater than a preset angle, determining that the vector angle is a right-angle turn, and marking the right-angle turn in the predicted path to obtain a path to be optimized;

[0016] The path to be optimized is used to generate multiple groups of search vectors through a preset algorithm, and the vector angles between the search vectors of each group are calculated. When the vector angles are all smaller than the preset angle, a path is output and the path is used as the optimized path.

[0017] Optionally, executing the optimization path and determining the control parameters includes:

[0018] Determine the vector angle between the current node and the target node according to the optimization path, obtain the tire parameters of the traffic moving cone, and calculate the speed difference according to the vector angle and the tire parameters; the tire parameters include: tire diameter and left and right tire spacing;

[0019] The operating power and control time of the left and right wheel motors are determined according to the speed difference, and the optimized path, the operating power and control time of the left and right wheel motors are sent as control parameters to the next traffic moving cone.

[0020] In a second aspect of the present invention, a traffic cone movement control system is proposed, including: an obstacle detection module, a path optimization module and a command control module:

[0021] The obstacle detection module is used to receive a movement instruction, and detect the area to be detected according to the movement instruction to obtain an obstacle distribution map; the movement instruction is the movement coordinates of the traffic moving cone, and the area to be detected is the area between the starting coordinates and the movement coordinates;

[0022] The path optimization module is used to generate a predicted path according to the obstacle distribution map, and optimize the predicted path to obtain an optimized path; the optimized path is a path with curvature;

[0023] The command control module is used to execute the optimized path and determine the control parameters, and send the control parameters to the next adjacent traffic moving cone for movement; the control parameters are the control time and operating power of the left and right wheel motors of the traffic moving cone.

[0024] Optionally, the obstacle detection module includes: an image acquisition module, a pixel calculation module and an obstacle marking module:

[0025] The image acquisition module is used to obtain a target image set of the area to be detected through a binocular camera, and input the images in the target image set into the obstacle detection model for obstacle detection; the target image set includes multiple groups of images, each group of images includes two images;

[0026] The pixel calculation module is used to calculate the pixel difference of the same point in the group of images in the X-axis direction if an obstacle is detected in any group of images, and obtain the obstacle coordinates of the obstacle in the camera coordinate system according to the pixel difference;

[0027] The obstacle marking module is used to convert the obstacle coordinates into a world coordinate system to obtain actual coordinates, and mark obstacles in the area to be detected according to the actual coordinates to obtain an obstacle distribution map.

[0028] Optionally, the path optimization module includes: a vector generation module, a right-angle bend judgment module and an iterative optimization module:

[0029] The vector generation module is used to divide the predicted path according to the deflection angle to obtain a path data set, determine the driving direction of each path data in the path data set as a direction vector, and obtain a direction vector data set;

[0030] The right-angle bend judgment module is used to calculate the vector angle between adjacent direction vectors in the direction vector data set, and if the vector angle is greater than a preset angle, the vector angle is determined to be a right-angle bend, and the right-angle bend in the predicted path is marked to obtain a path to be optimized;

[0031] The iterative optimization module is used to generate multiple groups of search vectors for the path to be optimized through a preset algorithm, calculate the vector angles between the search vectors of each group, and output a path until the vector angles are all less than a preset angle, and use the path as the optimized path.

[0032] Optionally, the command control module includes: a speed difference calculation module and a control parameter sending module:

[0033] The speed difference calculation module is used to determine the vector angle between the current node and the target node according to the optimized path, obtain the tire parameters of the traffic moving cone, and calculate the speed difference according to the vector angle and the tire parameters; the tire parameters include: tire diameter and left and right tire spacing;

[0034] The control parameter sending module is used to determine the operating power and control time of the left and right wheel motors according to the speed difference, and send the optimized path, the operating power and control time of the left and right wheel motors as control parameters to the next traffic moving cone.

[0035] The third aspect of the present application provides a robot, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any one of the methods provided in the first aspect of the present application are implemented.

[0036] The fourth aspect of the present application provides a computer storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods provided in the first aspect of the present application.

[0037] Beneficial effects of the present invention:

[0038] The present invention proposes a traffic cone movement control method, which receives movement instructions, detects the area to be detected according to the movement instructions to obtain an obstacle distribution map; generates a predicted path according to the obstacle distribution map, optimizes the predicted path to obtain an optimized path; executes the optimized path and determines the control parameters, and sends the control parameters to the next adjacent traffic cone for movement; receives movement instructions and detects the area to be detected, the system can accurately obtain the obstacle distribution map, generate and optimize the predicted path, and obtain an optimized path with curvature. The system can accurately control the movement of traffic cones, including the control time and operating power of the left and right wheel motors, and realize the coordinated movement of multiple traffic cones, thereby improving the efficiency of traffic diversion and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The present invention will be further described below in conjunction with the accompanying drawings.

[0040] Figure 1 A flow chart of a traffic cone movement control method is provided for an embodiment of the present invention;

[0041] Figure 2 A framework diagram of another traffic cone movement control system is provided for an embodiment of the present invention;

[0042] Figure 3 A structural schematic diagram of a traffic cone movement control robot is provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The term "and / or" herein is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the present invention, the description of "first", "second", etc. is only used for descriptive purposes, and cannot be understood as indicating or implying its relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" can explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0044] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative work shall fall within the scope of protection of the present invention.

[0045] The embodiment of the present invention provides a method for controlling the movement of traffic cones. Figure 1 , Figure 1 A flow chart of a traffic cone movement control method provided by an embodiment of the present invention. The method comprises the following steps:

[0046] S101, receiving a movement instruction, and detecting the area to be detected according to the movement instruction to obtain an obstacle distribution map;

[0047] S102, generating a predicted path according to the obstacle distribution map, and optimizing the predicted path to obtain an optimized path;

[0048] S103, executing the optimized path and determining the control parameters, and sending the control parameters to the next adjacent traffic moving cone for movement;

[0049] The moving instruction is the moving coordinates of the traffic moving cone, and the area to be detected is the area between the starting coordinates and the moving coordinates; the optimized path is a path with curvature; the control parameters are the control time and operating power of the left and right wheel motors of the traffic moving cone;

[0050] Based on the traffic cone movement control method provided by the embodiment of the present invention, by receiving movement instructions and detecting the area to be detected, the system can accurately obtain the obstacle distribution map, generate and optimize the predicted path, and obtain an optimized path with curvature. The system can accurately control the movement of traffic cones, including the control time and operating power of the left and right wheel motors, and realize the coordinated movement of multiple traffic cones, thereby improving the efficiency of traffic diversion and management.

[0051] In one implementation, the traffic cone determines the starting point and destination during the movement, but the first traffic cone needs to detect obstacles in the area to be detected. The traffic cone cannot detect all the areas to be detected at one time, so it needs to be detected in sections, and the predicted path also needs to be generated and optimized in sections; the predicted path is generated according to the obstacle distribution map, and the path is optimized to obtain an optimized path with curvature. This optimized path not only takes into account the need to avoid obstacles, but also minimizes the length and complexity of the path, thereby improving the movement efficiency and flexibility of the traffic cone.

[0052] In one implementation, by determining control parameters (including the control time and operating power of the left and right wheel motors of the traffic cone), the system can achieve precise control of the movement of the traffic cone. This precise control helps the traffic cone to maintain stable movement in complex environments and accurately reach the designated location.

[0053] In one implementation, the control parameters are sent to the next adjacent traffic moving cone for movement, so that the coordinated movement between multiple traffic moving cones can be achieved. When multiple traffic moving cones are needed to complete a task together, the overall work efficiency and effect can be significantly improved; only the first traffic moving cone performs detection and path planning, and the subsequent traffic moving cones are only responsible for receiving the instructions of the first traffic moving cone and moving.

[0054] In one embodiment, step S101 includes:

[0055] Obtain a target image set of the area to be detected through a binocular camera, and input the images in the target image set into an obstacle detection model for obstacle detection; the target image set includes multiple groups of images, each group of images includes two images;

[0056] If an obstacle is detected in any set of images, the pixel difference of the same point in the set of images in the X-axis direction is calculated, and the obstacle coordinates in the camera coordinate system are calculated based on the pixel difference;

[0057] The obstacle coordinates are converted into the world coordinate system to obtain the actual coordinates, and the obstacles in the detection area are marked according to the actual coordinates to obtain an obstacle distribution map.

[0058] In one implementation, the binocular camera includes two RGB cameras, which are installed on the same horizontal plane of the traffic cone. Obstacles in the image are identified by an obstacle detection model. The obstacle detection model is pre-trained. It is a deep learning model such as a convolutional neural network (CNN) that learns the feature representation of obstacles through a large amount of training data to achieve an accurate obstacle recognition model. The distance of the object is calculated by the difference in the imaging position of the same object under two different viewing angles (left and right cameras). For example: the camera focal length is f = 800 pixels, the baseline B = 0.54 meters (that is, the distance between the origins of the two cameras, or the distance between the optical centers of the two cameras), the left camera: (x l ,y l )=(80,400) pixels, right camera: (x r ,y r ) = (780, 400) pixels (y l and r equal, because the object is on the midline of the camera horizontally, the parallax D is the pixel difference between the corresponding points in the left and right images in the x direction, D = x l -x r = 800-780 = 20 pixels, the position of the obstacle in the left camera coordinate system, x l The units of B are the same as those of D (pixels), and x is in meters. c It represents the horizontal distance of the obstacle relative to the left camera; z c is the actual distance from the obstacle to the left camera; The same is true; converting the camera coordinate system to the world coordinate system is a rigid body transformation achieved through rotation and translation, for example: R is the product of the rotation matrix in the X, Y, and Z directions, and T is the translation matrix.

[0059] In one implementation, when an obstacle is detected in any set of images, the system calculates the pixel difference of the same point in the set of images in the X-axis direction. By measuring the parallax of the corresponding points in the left and right images, the position of the obstacle in the camera coordinate system can be inferred. Based on the parallax and the known parameters of the camera (such as focal length, baseline, etc.), the three-dimensional coordinates of the obstacle in the camera coordinate system can be calculated. After obtaining the coordinates of the obstacle in the camera coordinate system, the system will convert these coordinates to the world coordinate system to obtain the actual coordinates of the obstacle. The above conversion steps involve the conversion of coordinate systems, such as rotation and translation, to ensure that the coordinates of the obstacle match the actual position in the world coordinate system. According to the actual coordinates of the obstacle, the system will mark the obstacle in the area to be detected and generate an obstacle distribution map. The obstacle distribution map shows the location and distribution of obstacles in the area to be detected, which is helpful for subsequent path planning.

[0060] In one embodiment, step S102 includes:

[0061] The predicted path is divided according to the deflection angle to obtain a path data set, and the driving direction of each path data in the path data set is determined as a direction vector to obtain a direction vector data set;

[0062] Calculate the vector angle between adjacent direction vectors in the direction vector data set. If the vector angle is greater than a preset angle, the vector angle is determined to be a right-angle turn, and the right-angle turn in the predicted path is marked to obtain the path to be optimized.

[0063] The path to be optimized is generated into multiple groups of search vectors through a preset algorithm, and the vector angles between each group of search vectors are calculated. When the vector angles are all less than the preset angle, the path is output and used as the optimized path.

[0064] In one implementation, by dividing the predicted path according to the deflection angle (taking the deflection angle as the node, taking the forward direction of the traffic moving cone in the path segment as the direction to obtain the direction vector, and the predicted path having multiple direction vectors to obtain a direction vector data set), the path can be accurately decomposed into multiple path data segments, and the driving direction of each path data segment can be determined as the direction vector; that is, because the predicted path is not smooth enough (the path between the starting point and the destination is a straight line, not smooth or round enough), the traffic moving cone is easy to fall over during the movement (especially turning), so the path needs to be re-optimized.

[0065] In one implementation, by calculating the vector angles of adjacent direction vectors in a direction vector data set and setting a preset angle to determine whether it is a right-angle turn, the right-angle turn in the path can be accurately identified. The right-angle turn here refers to the angle with a large turning arc. In path planning, the right-angle turn is often the part of the path that needs to be optimized. For the marked right-angle turn, a plurality of groups of search vectors are generated by a preset algorithm (for example, ant colony algorithm, A* algorithm, genetic algorithm, etc.), and the vector angles between each group of search vectors are calculated until the vector angles are all less than the preset angle, thereby outputting the optimized path. That is, if there are many vector angles in a curve and the angles are all less than the preset angle, it means that the curve is very smooth, and the search vector is equivalent to the direction in which the traffic moving cone moves. The above optimization process is implemented by calculating the vector angle and generating the search vector. This method is not only efficient, but also can automatically adapt to different path characteristics, thereby improving the efficiency and accuracy of path optimization.

[0066] In one embodiment, step S103 includes:

[0067] Determine the vector angle between the current node and the target node according to the optimized path, obtain the tire parameters of the traffic moving cone, and calculate the speed difference according to the vector angle and the tire parameters; the tire parameters include: tire diameter and left and right tire spacing;

[0068] The operating power and control time of the left and right wheel motors are determined according to the speed difference, and the optimized path, the operating power and control time of the left and right wheel motors are sent as control parameters to the next traffic moving cone.

[0069] In one implementation, the current node is the location of the traffic cone at the current moment, and the target node is the location to be reached. There is a bend (curve) between the two locations. Subsequent calculations are performed using the vector angle, tire diameter, and the distance between the left and right tires. For example, the turning radius r is determined as:

[0070] Among them, axle is the wheelbase (the distance between the left and right tires), the steering angle θ (the vector angle), and the speed difference Δv is the speed difference (the absolute value of the speed difference between the left and right wheels), v 0 is the linear velocity of the center line of the traffic moving cone (measured by the speed sensor); when the wheelbase axle = 0.5 meters, the linear velocity v of the center line of the traffic moving cone 0 = 0.3 m / s Turning angle θ = 30° (converted to radians radian), the turning radius is calculated to be r≈0.866, the speed difference is calculated to be Δv≈0.173, the speed difference between the left and right wheels is controlled at about 0.173 m / s. If the traffic cone turns left, the motor of the right wheel will have to increase power and extend the working time.

[0071] In one implementation, by combining tire parameters (tire diameter and left and right tire spacing) with the vector angle, the technology can calculate the speed difference required for the left and right wheels, thereby dynamically adjusting the vehicle speed to adapt to different steering angles and path changes, improving driving flexibility and response speed; based on the calculated speed difference, the operating power and control time of the left and right wheel motors can be determined to achieve precise control of the motors, and the optimized path, operating power and control time of the left and right wheel motors and other information can be sent to the next traffic moving cone to achieve mobile following of the traffic moving cone, providing support for the collaborative work between multiple moving cones and the optimized scheduling of the overall traffic system.

[0072] Based on the same inventive concept, the present invention also provides a traffic cone movement control system. Figure 2 , Figure 2 The schematic diagram of the structure of the traffic cone mobile control system provided by the embodiment of the present invention includes: an obstacle detection module, a path optimization module and a command control module:

[0073] The obstacle detection module is used to receive a movement instruction and detect the area to be detected according to the movement instruction to obtain an obstacle distribution map; the movement instruction is the movement coordinates of the traffic moving cone, and the area to be detected is the area between the starting coordinates and the movement coordinates;

[0074] A path optimization module is used to generate a predicted path according to an obstacle distribution map, and optimize the predicted path to obtain an optimized path; the optimized path is a path with curvature;

[0075] The command control module is used to execute the optimized path and determine the control parameters, and send the control parameters to the next adjacent traffic moving cone for movement; the control parameters are the control time and operating power of the left and right wheel motors of the traffic moving cone.

[0076] Based on the traffic cone movement control system provided by the embodiment of the present invention, by receiving movement instructions and detecting the area to be detected, the system can accurately obtain the obstacle distribution map, generate and optimize the predicted path, and obtain an optimized path with curvature. The system can accurately control the movement of traffic cones, including the control time and operating power of the left and right wheel motors, and realize the coordinated movement of multiple traffic cones, thereby improving the efficiency of traffic diversion and management.

[0077] In one embodiment, the obstacle detection module includes: an image acquisition module, a pixel calculation module and an obstacle marking module:

[0078] The image acquisition module is used to obtain a target image set of the area to be detected through a binocular camera, and input the images in the target image set into the obstacle detection model for obstacle detection; the target image set includes multiple groups of images, each group of images includes two images;

[0079] The pixel calculation module is used to calculate the pixel difference of the same point in the group of images in the X-axis direction if an obstacle is detected in any group of images, and obtain the obstacle coordinates in the camera coordinate system based on the pixel difference;

[0080] The obstacle marking module is used to convert the obstacle coordinates into the world coordinate system to obtain the actual coordinates, and mark the obstacles in the detection area according to the actual coordinates to obtain an obstacle distribution map.

[0081] In one embodiment, the path optimization module includes: a vector generation module, a right-angle bend judgment module, and an iterative optimization module:

[0082] A vector generation module is used to divide the predicted path according to the deflection angle to obtain a path data set, determine the driving direction of each path data in the path data set as a direction vector, and obtain a direction vector data set;

[0083] The right-angle bend judgment module is used to calculate the vector angle between adjacent direction vectors in the direction vector data set. If the vector angle is greater than a preset angle, the vector angle is determined to be a right-angle bend, and the right-angle bend in the predicted path is marked to obtain a path to be optimized;

[0084] The iterative optimization module is used to generate multiple groups of search vectors for the path to be optimized through a preset algorithm, calculate the vector angles between each group of search vectors, and output the path until the vector angles are all less than the preset angle, and use the path as the optimized path.

[0085] In one embodiment, the command control module includes: a speed difference calculation module and a control parameter sending module:

[0086] The speed difference calculation module is used to determine the vector angle between the current node and the target node according to the optimized path, obtain the tire parameters of the traffic moving cone, and calculate the speed difference according to the vector angle and the tire parameters; the tire parameters include: tire diameter and left and right tire spacing;

[0087] The control parameter sending module is used to determine the operating power and control time of the left and right wheel motors according to the speed difference, and send the optimized path, the operating power and control time of the left and right wheel motors as control parameters to the next traffic moving cone.

[0088] The embodiment of the present invention further provides a robot 300, Figure 3 , including a processor 301, a memory 302, and a computer program stored in the memory 302 and executable on the processor 301, wherein when the processor executes the program, the steps of any one of the methods provided in the first aspect of the present application are implemented.

[0089] In another embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, the traffic cone movement control method of any one of the above embodiments is implemented.

[0090] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A traffic cone movement control method, characterized in that: The method comprises: Receive a movement instruction, and detect the area to be detected according to the movement instruction to obtain an obstacle distribution map; the movement instruction is the movement coordinates of the traffic moving cone, and the area to be detected is the area between the starting coordinates and the movement coordinates; Generate a predicted path according to the obstacle distribution map, and optimize the predicted path to obtain an optimized path; the optimized path is a path with curvature; The optimized path is executed and control parameters are determined, and the control parameters are sent to the next adjacent traffic moving cone for movement; the control parameters are the control time and operating power of the left and right wheel motors of the traffic moving cone.

2. The traffic cone movement control method according to claim 1, characterized in that: Detecting the area to be detected according to the movement instruction to obtain an obstacle distribution map includes: Obtain a target image set of the area to be detected through a binocular camera, and input the images in the target image set into an obstacle detection model for obstacle detection; the target image set includes multiple groups of images, each group of images includes two images; If an obstacle is detected in any set of images, the pixel difference of the same point in the set of images in the X-axis direction is calculated, and the obstacle coordinates of the obstacle in the camera coordinate system are calculated based on the pixel difference; The obstacle coordinates are converted into a world coordinate system to obtain actual coordinates, and obstacles are marked in the area to be detected according to the actual coordinates to obtain an obstacle distribution map.

3. The traffic cone movement control method according to claim 1, characterized in that: Optimizing the predicted path to obtain an optimized path includes: Dividing the predicted path according to the deflection angle to obtain a path data set, determining the driving direction of each path data in the path data set as a direction vector, and obtaining a direction vector data set; Calculating the vector angle between adjacent direction vectors in the direction vector data set, if the vector angle is greater than a preset angle, determining that the vector angle is a right-angle turn, and marking the right-angle turn in the predicted path to obtain a path to be optimized; The path to be optimized is used to generate multiple groups of search vectors through a preset algorithm, and the vector angles between the search vectors of each group are calculated. When the vector angles are all smaller than the preset angle, a path is output and the path is used as the optimized path.

4. The traffic cone movement control method according to claim 1, characterized in that: Executing the optimization path and determining the control parameters includes: Determine the vector angle between the current node and the target node according to the optimization path, obtain the tire parameters of the traffic moving cone, and calculate the speed difference according to the vector angle and the tire parameters; the tire parameters include: tire diameter and left and right tire spacing; The operating power and control time of the left and right wheel motors are determined according to the speed difference, and the optimized path, the operating power and control time of the left and right wheel motors are sent as control parameters to the next traffic moving cone.

5. Traffic cone mobile control system, characterized in that: The system includes: an obstacle detection module, a path optimization module and a command control module: The obstacle detection module is used to receive a movement instruction, and detect the area to be detected according to the movement instruction to obtain an obstacle distribution map; the movement instruction is the movement coordinates of the traffic moving cone, and the area to be detected is the area between the starting coordinates and the movement coordinates; The path optimization module is used to generate a predicted path according to the obstacle distribution map, and optimize the predicted path to obtain an optimized path; the optimized path is a path with curvature; The command control module is used to execute the optimized path and determine the control parameters, and send the control parameters to the next adjacent traffic moving cone for movement; the control parameters are the control time and operating power of the left and right wheel motors of the traffic moving cone.

6. The traffic cone movement control system according to claim 5, characterized in that: The obstacle detection module includes: an image acquisition module, a pixel calculation module and an obstacle marking module: The image acquisition module is used to obtain a target image set of the area to be detected through a binocular camera, and input the images in the target image set into the obstacle detection model for obstacle detection; the target image set includes multiple groups of images, each group of images includes two images; The pixel calculation module is used to calculate the pixel difference of the same point in the group of images in the X-axis direction if an obstacle is detected in any group of images, and obtain the obstacle coordinates of the obstacle in the camera coordinate system according to the pixel difference; The obstacle marking module is used to convert the obstacle coordinates into a world coordinate system to obtain actual coordinates, and mark obstacles in the area to be detected according to the actual coordinates to obtain an obstacle distribution map.

7. The traffic cone movement control system according to claim 5, characterized in that: The path optimization module includes: a vector generation module, a right-angle bend judgment module and an iterative optimization module: The vector generation module is used to divide the predicted path according to the deflection angle to obtain a path data set, determine the driving direction of each path data in the path data set as a direction vector, and obtain a direction vector data set; The right-angle bend judgment module is used to calculate the vector angle between adjacent direction vectors in the direction vector data set, and if the vector angle is greater than a preset angle, the vector angle is determined to be a right-angle bend, and the right-angle bend in the predicted path is marked to obtain a path to be optimized; The iterative optimization module is used to generate multiple groups of search vectors for the path to be optimized through a preset algorithm, calculate the vector angles between the search vectors in each group, and output a path until the vector angles are all less than a preset angle, and use the path as the optimized path.

8. The traffic cone movement control system according to claim 5, characterized in that: The command control module includes: a speed difference calculation module and a control parameter sending module: The speed difference calculation module is used to determine the vector angle between the current node and the target node according to the optimized path, obtain the tire parameters of the traffic moving cone, and calculate the speed difference according to the vector angle and the tire parameters; the tire parameters include: tire diameter and left and right tire spacing; The control parameter sending module is used to determine the operating power and control time of the left and right wheel motors according to the speed difference, and send the optimized path, the operating power and control time of the left and right wheel motors as control parameters to the next traffic moving cone.

9. A robot comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method according to any one of claims 1 to 4 are implemented.

10. A computer storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images