Robot path planning method and system based on adaptive path adjustment
Through real-time environment model construction and machine learning algorithm evaluation, combined with path smoothing processing, the problem of traditional path planning not responding in a timely manner in a dynamic environment is solved, and the accuracy and stability of robot paths are achieved.
Patent Information
- Application Number
- CN202411840409.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-13
- Publication Date
- 2025-03-28
AI Technical Summary
Traditional robot path planning algorithms cannot respond to environmental changes in a timely manner in a dynamic environment, resulting in path deviations or inability to reach the destination. They rely on a single sensor and cannot make full use of multi-sensor data, with high computational complexity, affecting real-time and efficiency.
The sensor obtains the surrounding environment information in real time, establishes a real-time dynamic environmental model, uses machine learning algorithms to evaluate environmental changes, re-plan local paths to avoid obstacles, and smoothly process them during the path planning process.
It realizes rapid response to environmental changes in a dynamic environment, ensures the accuracy and real-time nature of the path, reduces sharp turns and bumps in the path, and improves the driving stability and autonomous learning ability of the robot.
Smart Images
Figure CN119717809A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of path planning, and specifically refers to a robot path planning method and system based on adaptive path adjustment. Background Art
[0002] With the development of science and technology, robots are increasingly used in daily life and industrial production. However, in a dynamically changing environment, traditional path planning algorithms often fail to respond to environmental changes in a timely manner, resulting in path deviation or failure to reach the destination.
[0003] However, there are still certain defects in the existing robot path planning. The existing robot path planning relies on a pre-built static environment model and cannot reflect the changes in the environment in real time. When new obstacles appear in the environment or obstacles move, these methods cannot update the environment model in time, resulting in the failure of path planning. Relying on a single type of sensor, it is impossible to fully utilize the advantages of multi-sensor data fusion, which affects the comprehensiveness and accuracy of environmental perception. The existing path planning algorithms often take a long time to calculate the initial path, especially in large-scale environments. The computational complexity is high, which affects the real-time and efficiency of path planning. When a new obstacle is detected, the existing methods usually need to recalculate the entire path, which is time-consuming and inefficient. They lack the ability to adjust the local path and cannot respond to environmental changes quickly. When facing dynamic obstacles, the accuracy of the path is often not guaranteed, which can easily cause the robot to collide or deviate from the predetermined path. The generated path often has sharp turns and bumps, which affect the driving stability of the robot. Therefore, a robot path planning method and system based on adaptive path adjustment are proposed. Summary of the invention
[0004] The purpose of the present invention is to provide a robot path planning method and system based on adaptive path adjustment to solve the problems raised in the above background technology.
[0005] To achieve the above object, the present invention provides the following technical solution: a robot path planning method based on adaptive path adjustment, comprising the following steps:
[0006] S1. Obtain surrounding environment information in real time through sensors and establish a real-time dynamic environment model;
[0007] S2. Calculate the initial path from the starting point to the target point through the path planning algorithm according to the constructed environment model;
[0008] S3, while the robot moves along the preliminary path, it continuously collects environmental data and monitors changes in obstacles on the path;
[0009] S4, when a new obstacle is detected on the path, the impact of the environmental change is evaluated through a machine learning algorithm, and the local path is replanned to avoid the obstacle;
[0010] S5. During the path planning process, the path planning system smoothes the path using a smoothing algorithm;
[0011] S6. Execute the planned or adjusted path through the path control system, control the robot to move along the planned path, and monitor its state and position in real time during the movement;
[0012] S7. Optimize the path planning strategy by continuously learning environmental characteristics and path selection results.
[0013] Among them, S1 obtains the surrounding environment information in real time through sensors and establishes a real-time dynamic environment model; obtains the environmental information in real time based on the integrated sensor, pre-processes the collected data, including filtering, denoising, and calibration, and divides the robot's working environment into a series of grids of equal size, each grid represents an environmental unit, and determines the state of each grid based on the sensor data.
[0014] Among them, S1, when the robot moves and the sensor continuously collects data, updates the status of the grid map in real time. When a new obstacle is detected, it immediately updates the status of the relevant grid. Through the camera and lidar sensor, it identifies and models the obstacles in the environment, and fuses the data from different sensors. By comparing the sensor data and the environmental model, the accuracy of the model is verified, and the environmental model is optimized according to the verification results.
[0015] Among them, S2, according to the constructed environment model, calculates the initial path from the starting point to the target point through the path planning algorithm; determines the current position of the robot, sets the position of the target point according to the task requirements, obtains the latest environment model from the environment perception module, converts the environment model into the format required by the path planning algorithm, and the actual cost from the starting point to the current node and the estimated cost from the current node to the target point. The total cost is realized by the formula:
[0016] f(n)=g(n)+h(n),
[0017] In the formula, f(n) represents the total cost, g(n) represents the estimated cost, and h(n) represents the actual cost. The actual cost is the cumulative cost from the starting point s to the current node n.
[0018] Among them, S2, in each iteration, selects the node with the smallest f(n) in the open list for expansion, generates its adjacent nodes, adds the adjacent node n′ to the open list, and if n is already in the open list, updates its f(n′) value. If the target node t is added to the closed list, the algorithm terminates, starting from the target node t, traces back along the parent node to the starting point s, constructs a path from the starting point to the target point, represents the final path as a series of coordinate points, and stores the path in the robot's memory for use by the path control system.
[0019] Among them, in S3, while the robot moves along the preliminary path, it continuously collects environmental data and monitors changes in obstacles on the path; obtains the preliminary path according to the path planning module, determines the current starting position of the robot, sets the next target point of the robot, and controls the robot to move along the path according to the result of path planning, ensures that the robot moves along the predetermined path through the PID controller, and updates the current position of the robot in real time through the positioning system.
[0020] Among them, S4, when a new obstacle is detected on the path, the impact of environmental changes is evaluated through a machine learning algorithm, and the local path is replanned to avoid the obstacle. During the movement of the robot, the data of the surrounding environment is continuously collected. The sensor data should include the location, shape and size information of the obstacle. The environment changes are monitored in real time, and the obstacle situation on the current path is checked in real time. If a new obstacle is detected on the path, the location and size of the obstacle are recorded, the impact of the new obstacle on the current path is evaluated, and it is determined whether the path needs to be replanned;
[0021] Based on the location and size of the obstacle, determine whether the robot needs to stop immediately or continue moving forward. When the path needs to be adjusted, the path planning module is triggered to replan the local path to avoid obstacles, and the new path is updated to the robot's path tracking system. According to the new path, the robot is controlled to continue moving, and its status and position are monitored in real time during the movement.
[0022] Wherein, in the process of path planning, the path planning system smoothes the path through a smoothing algorithm; obtains a preliminary path from the path planning module, and represents the path as a point sequence P = {(x1, y1), (x2, y2), ..., (x i ,y i )}, set the smoothing factor as α to control the smoothness of the path, set the weight factor β to balance the smoothness and length of the path, and gradually adjust the position of the path points through iterative optimization. i ,y i ), calculate the smoothed coordinates (x i ′,y i ′), let the initial path point be (xi ,y i ), the smoothed path point is (x i ′,y i ′), the realization formula is:
[0023]
[0024] In the formula, x i-1 ,y i-1 Indicates the coordinates of the previous path point, x i+1 ,y i+1 Represents the coordinates of the next path point, and represents the smoothed path as a series of coordinate points P = {(x1′, y1′), (x′2, y′2), ..., (x i ′,y i ′)}, the smoothed path is stored in the robot’s memory for use by the path control system.
[0025] In which, S6 executes the planned or adjusted path through the path control system, controls the robot to move along the planned path, monitors its state and position in real time during the movement, obtains the final path, controls the robot to move along the path according to the path point sequence, updates the current position of the robot in real time through the positioning system, and checks whether the robot has reached the current target point (x i ′,y i ′), if the robot reaches the current target point, the next path point is set as the new target point, the error between the current position and the target point is calculated, the control signal is calculated according to the error, and the calculated control signal is sent to the robot's drive system to control the robot's speed and direction. During the robot's movement, the robot's status is monitored in real time, and the monitored status information is fed back to the path control system. When the robot reaches the last point of the path, it checks whether the path has been completed. When the path is completed, the path tracking task is ended and the task management system is notified.
[0026] Among them, the robot path planning system based on adaptive path adjustment is characterized by: including an environment perception and modeling module, a path planning module, a path execution monitoring module, an adaptive path adjustment module and a path optimization module.
[0027] Compared with the prior art, the present invention has the following beneficial effects:
[0028] 1. The present invention obtains the surrounding environment information in real time through sensors, establishes a real-time dynamic environment model, and can accurately reflect the changes in the environment. With the movement of the robot and the continuous collection of sensors, the state of the grid map is updated in real time to ensure the accuracy and timeliness of the environment model;
[0029] 2. The present invention improves the efficiency of path planning by quickly calculating the initial path from the starting point to the target point through the path planning algorithm according to the constructed environmental model. When a new obstacle is detected on the path, the impact of environmental changes is evaluated through the machine learning algorithm, and the local path is replanned to avoid the obstacle, thereby ensuring the accuracy of the path;
[0030] 3. In the process of path planning, the present invention uses a smoothing algorithm to smooth the path, thereby reducing sharp turns and bumps in the path, improving the smoothness and comfort of the path, and ensuring that the robot moves along the predetermined path through control strategies such as PID controllers, thereby improving the stability and accuracy of path tracking;
[0031] 4. The present invention improves the robot's intelligence level and autonomous learning ability by continuously learning environmental characteristics and path selection results and optimizing path planning strategies. During the robot's movement, its status and position are monitored in real time, and abnormal situations can be discovered and handled in a timely manner to ensure the robot's safe operation. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] Figure 1 The process of the robot path planning method based on adaptive path adjustment of the present invention is as follows Figure 1 ;
[0033] Figure 2 The process of the robot path planning method based on adaptive path adjustment of the present invention is as follows Figure 2 ;
[0034] Figure 3 The process of the robot path planning method based on adaptive path adjustment of the present invention is as follows Figure 3 ;
[0035] Figure 4 It is a structural schematic diagram of a robot path planning system based on adaptive path adjustment of the present invention. DETAILED DESCRIPTION
[0036] 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. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0037] Example
[0038] See also Figure 1-Figure 4 As shown, the present invention provides a technical solution: comprising the following steps:
[0039] S1. Obtain surrounding environment information in real time through sensors and establish a real-time dynamic environment model;
[0040] S2. Calculate the initial path from the starting point to the target point through the path planning algorithm according to the constructed environment model;
[0041] S3, while the robot moves along the preliminary path, it continuously collects environmental data and monitors changes in obstacles on the path;
[0042] S4, when a new obstacle is detected on the path, the impact of the environmental change is evaluated through a machine learning algorithm, and the local path is replanned to avoid the obstacle;
[0043] S5. During the path planning process, the path planning system smoothes the path using a smoothing algorithm;
[0044] S6. Execute the planned or adjusted path through the path control system, control the robot to move along the planned path, and monitor its state and position in real time during the movement;
[0045] S7. Optimize the path planning strategy by continuously learning environmental characteristics and path selection results.
[0046] Among them, S1 obtains the surrounding environment information in real time through sensors and establishes a real-time dynamic environment model; obtains the environmental information in real time based on the integrated sensor, pre-processes the collected data, including filtering, denoising, and calibration, and divides the robot's working environment into a series of grids of equal size, each grid represents an environmental unit, and determines the state of each grid based on the sensor data.
[0047] Among them, S1, when the robot moves and the sensor continuously collects data, updates the status of the grid map in real time. When a new obstacle is detected, it immediately updates the status of the relevant grid. Through the camera and lidar sensor, it identifies and models the obstacles in the environment, and fuses the data from different sensors. By comparing the sensor data and the environmental model, the accuracy of the model is verified, and the environmental model is optimized according to the verification results.
[0048] Among them, S2, according to the constructed environment model, calculates the initial path from the starting point to the target point through the path planning algorithm; determines the current position of the robot, sets the position of the target point according to the task requirements, obtains the latest environment model from the environment perception module, converts the environment model into the format required by the path planning algorithm, and the actual cost from the starting point to the current node and the estimated cost from the current node to the target point. The total cost is realized by the formula:
[0049] f(n)=g(n)+h(n),
[0050] In the formula, f(n) represents the total cost, g(n) represents the estimated cost, and h(n) represents the actual cost. The actual cost is the cumulative cost from the starting point s to the current node n.
[0051] Among them, S2, in each iteration, selects the node with the smallest f(n) in the open list for expansion, generates its adjacent nodes, adds the adjacent node n′ to the open list, and if n is already in the open list, updates its f(n′) value. If the target node t is added to the closed list, the algorithm terminates, starting from the target node t, traces back along the parent node to the starting point s, constructs a path from the starting point to the target point, represents the final path as a series of coordinate points, and stores the path in the robot's memory for use by the path control system.
[0052] Among them, in S3, while the robot moves along the preliminary path, it continuously collects environmental data and monitors changes in obstacles on the path; obtains the preliminary path according to the path planning module, determines the current starting position of the robot, sets the next target point of the robot, and controls the robot to move along the path according to the result of path planning, ensures that the robot moves along the predetermined path through the PID controller, and updates the current position of the robot in real time through the positioning system.
[0053] Among them, S4, when a new obstacle is detected on the path, the impact of environmental changes is evaluated through a machine learning algorithm, and the local path is replanned to avoid the obstacle. During the movement of the robot, the data of the surrounding environment is continuously collected. The sensor data should include the location, shape and size information of the obstacle. The environment changes are monitored in real time, and the obstacle situation on the current path is checked in real time. If a new obstacle is detected on the path, the location and size of the obstacle are recorded, the impact of the new obstacle on the current path is evaluated, and it is determined whether the path needs to be replanned;
[0054] Based on the location and size of the obstacle, determine whether the robot needs to stop immediately or continue moving forward. When the path needs to be adjusted, the path planning module is triggered to replan the local path to avoid obstacles, and the new path is updated to the robot's path tracking system. According to the new path, the robot is controlled to continue moving, and its status and position are monitored in real time during the movement.
[0055] Wherein, in the process of path planning, the path planning system smoothes the path through a smoothing algorithm; obtains a preliminary path from the path planning module, and represents the path as a point sequence P = {(x1, y1), (x2, y2), ..., (x i ,y i)}, set the smoothing factor as α to control the smoothness of the path, set the weight factor β to balance the smoothness and length of the path, and gradually adjust the position of the path points through iterative optimization. i ,y i ), calculate the smoothed coordinates (x i ′,y i ′), let the initial path point be (x i ,y i ), the smoothed path point is (x i ′,y i ′), the realization formula is:
[0056]
[0057] In the formula, x i-1 ,y i-1 Indicates the coordinates of the previous path point, x i+1 ,y i+1 Represents the coordinates of the next path point, and represents the smoothed path as a series of coordinate points P = {(x1′, y1′), (x′2, y′2), ..., (x i ′,y i ′)}, the smoothed path is stored in the robot’s memory for use by the path control system.
[0058] In which, S6 executes the planned or adjusted path through the path control system, controls the robot to move along the planned path, monitors its state and position in real time during the movement, obtains the final path, controls the robot to move along the path according to the path point sequence, updates the current position of the robot in real time through the positioning system, and checks whether the robot has reached the current target point (x i ′,y i ′), if the robot reaches the current target point, the next path point is set as the new target point, the error between the current position and the target point is calculated, the control signal is calculated according to the error, and the calculated control signal is sent to the robot's drive system to control the robot's speed and direction. During the robot's movement, the robot's status is monitored in real time, and the monitored status information is fed back to the path control system. When the robot reaches the last point of the path, it checks whether the path has been completed. When the path is completed, the path tracking task is ended and the task management system is notified.
[0059] Among them, the robot path planning system based on adaptive path adjustment is characterized by: including an environment perception and modeling module, a path planning module, a path execution monitoring module, an adaptive path adjustment module and a path optimization module.
[0060] Working principle: The robot collects information about the surrounding environment in real time through integrated sensors, filters, denoises and calibrates the collected data, and divides the robot's working environment into a series of grids of equal size. Each grid represents an environmental unit. The state of each grid is determined based on the sensor data. As the robot moves and the sensors continue to collect data, the state of the grid map is updated in real time.
[0061] According to the task requirements, the current position of the robot is determined as the starting point, the position of the target point is set, and the initial path from the starting point to the target point is calculated by the path planning algorithm using the constructed environmental model. The actual cost from the starting point to the current node and the estimated cost from the current node to the target point are calculated to determine the optimal path. According to the preliminary path provided by the path planning module, the robot is controlled to move along the path. The current position of the robot is updated in real time through the positioning system, the environmental data is continuously collected, and the changes of obstacles on the path are monitored. During the movement of the robot, the data of the surrounding environment is continuously collected to monitor the changes of the environment in real time. If a new obstacle is detected on the path, the position and size of the obstacle are recorded. Evaluate its impact on the current path, and trigger the path planning module to re-plan the local path according to the position and size of the obstacle to avoid the obstacle. During the path planning process, the preliminary path is smoothed by a smoothing algorithm, and the smoothing factor and weight factor are set to control the smoothness of the path and balance the smoothness and length of the path. According to the planned or adjusted path, the robot is controlled to move along the path, and the status and position of the robot are monitored in real time during the movement. When the robot reaches the last point of the path, it checks whether the path has been completed. If it has been completed, the path tracking task is terminated and the task management system is notified. The path planning strategy is optimized by continuously learning environmental characteristics and path selection results.
[0062] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
[0063] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.
Claims
1. A robot path planning method based on adaptive path adjustment, characterized in that: The following steps are involved: S1. Obtain surrounding environment information in real time through sensors and establish a real-time dynamic environment model; S2. Calculate the initial path from the starting point to the target point through the path planning algorithm according to the constructed environment model; S3, while the robot moves along the preliminary path, it continuously collects environmental data and monitors changes in obstacles on the path; S4, when a new obstacle is detected on the path, the impact of the environmental change is evaluated through a machine learning algorithm, and the local path is replanned to avoid the obstacle; S5. During the path planning process, the path planning system smoothes the path using a smoothing algorithm; S6. Execute the planned or adjusted path through the path control system, control the robot to move along the planned path, and monitor its state and position in real time during the movement; S7. Optimize the path planning strategy by continuously learning environmental characteristics and path selection results.
2. The robot path planning method based on adaptive path adjustment according to claim 1, characterized in that: The S1 acquires the surrounding environment information in real time through sensors and establishes a real-time dynamic environment model; obtains the environmental information in real time based on the integrated sensors, pre-processes the collected data, including filtering, denoising, and calibration, and divides the robot's working environment into a series of grids of equal size, each grid representing an environmental unit, and determines the state of each grid based on the sensor data.
3. The robot path planning method based on adaptive path adjustment according to claim 2, characterized in that: The S1 updates the state of the grid map in real time through the movement of the robot and the continuous collection of sensors. When a new obstacle is detected, the state of the relevant grid is updated immediately. The obstacles in the environment are identified and modeled through cameras and lidar sensors. The data from different sensors are fused, and the accuracy of the model is verified by comparing the sensor data and the environmental model. According to the verification results, the environmental model is optimized.
4. The robot path planning method based on adaptive path adjustment according to claim 1, characterized in that: S2, according to the constructed environment model, calculates the initial path from the starting point to the target point through the path planning algorithm; determines the current position of the robot, sets the position of the target point according to the task requirements, obtains the latest environment model from the environment perception module, converts the environment model into the format required by the path planning algorithm, and calculates the actual cost from the starting point to the current node and the estimated cost from the current node to the target point. The total cost is realized by the formula: f(n)=g(n)+h(n), In the formula, f(n) represents the total cost, g(n) represents the estimated cost, and h(n) represents the actual cost. The actual cost is the cumulative cost from the starting point s to the current node n.
5. The robot path planning method based on adaptive path adjustment according to claim 4, characterized in that: In S2, in each iteration, the node with the smallest f(n) in the open list is selected for expansion, its neighboring nodes are generated, and the neighboring node n′ is added to the open list. If n is already in the open list, its f(n′) value is updated. If the target node t is added to the closed list, the algorithm terminates, starting from the target node t, backtracking along the parent node to the starting point s, constructing a path from the starting point to the target point, representing the final path as a series of coordinate points, and storing the path in the robot's memory for use by the path control system.
6. The robot path planning method based on adaptive path adjustment according to claim 1, characterized in that: In S3, while the robot moves along the preliminary path, it continuously collects environmental data and monitors changes in obstacles on the path; obtains the preliminary path according to the path planning module, determines the current starting position of the robot, sets the next target point of the robot, and controls the robot to move along the path according to the result of path planning, ensures that the robot moves along the predetermined path through the PID controller, and updates the current position of the robot in real time through the positioning system.
7. The robot path planning method based on adaptive path adjustment according to claim 6, characterized in that: Said S4, when a new obstacle is detected on the path, the impact of environmental changes is evaluated through a machine learning algorithm, and the local path is replanned to avoid the obstacle. During the movement of the robot, the data of the surrounding environment is continuously collected. The sensor data should include the location, shape and size information of the obstacle. The changes in the environment are monitored in real time, and the obstacle situation on the current path is checked in real time. If a new obstacle is detected on the path, the location and size of the obstacle are recorded, the impact of the new obstacle on the current path is evaluated, and it is determined whether the path needs to be replanned; Based on the location and size of the obstacle, determine whether the robot needs to stop immediately or continue moving forward. When the path needs to be adjusted, the path planning module is triggered to replan the local path to avoid obstacles, and the new path is updated to the robot's path tracking system. According to the new path, the robot is controlled to continue moving, and its status and position are monitored in real time during the movement.
8. The robot path planning method based on adaptive path adjustment according to claim 1, characterized in that: In S5, during the path planning process, the path planning system smoothes the path using a smoothing algorithm; obtains a preliminary path from the path planning module, and represents the path as a point sequence P = {(x1, y1), (x2, y2), ..., (x i ,y i )}, set the smoothing factor as α to control the smoothness of the path, set the weight factor β to balance the smoothness and length of the path, and gradually adjust the position of the path points through iterative optimization. i ,y i ), calculate the smoothed coordinates (x i ′,y i ′), let the initial path point be (x i ,y i ), the smoothed path point is (x i ′,y i ′), the realization formula is: In the formula, x i-1 ,y i-1 Indicates the coordinates of the previous path point, x i+1 ,y i+1 Represents the coordinates of the next path point, and represents the smoothed path as a series of coordinate points P = {(x1′, y1′), (x′2, y′2), ..., (x i ′,y i ′)}, the smoothed path is stored in the robot’s memory for use by the path control system.
9. The robot path planning method based on adaptive path adjustment according to claim 1, characterized in that: S6, executes the planned or adjusted path through the path control system, controls the robot to move along the planned path, monitors its state and position in real time during the movement, obtains the final path, controls the robot to move along the path according to the path point sequence, updates the current position of the robot in real time through the positioning system, and checks whether the robot has reached the current target point (x i ′,y i ′), if the robot reaches the current target point, the next path point is set as the new target point, the error between the current position and the target point is calculated, the control signal is calculated according to the error, and the calculated control signal is sent to the robot's drive system to control the robot's speed and direction. During the robot's movement, the robot's status is monitored in real time, and the monitored status information is fed back to the path control system. When the robot reaches the last point of the path, it checks whether the path has been completed. When the path is completed, the path tracking task is ended and the task management system is notified.
10. A robot path planning system based on adaptive path adjustment, characterized in that: It includes environment perception and modeling module, path planning module, path execution monitoring module, adaptive path adjustment module and path optimization module.