A Path Planning Method for Mobile Robots in Unknown Environments
By using an improved dynamic window method and adaptive simulation time optimization path planning, the problem of obstacle avoidance difficulties for robots in unknown environments was solved, enabling robots to quickly and safely reach the target location in unknown environments.
Patent Information
- Application Number
- CN202311757193.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-19
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2043-12-19
AI Technical Summary
Existing path planning algorithms struggle to avoid obstacles in real time in unknown environments, which may cause robots to get stuck in obstacle traps or fail to reach their target location.
An improved dynamic window method is adopted, which uses direction, obstacle distance, movement speed and grid cost evaluation function to correct the robot path in real time, and optimize path planning by combining adaptive simulation time and speed constraints.
Effectively prevent robots from getting stuck in obstacle traps and ensure that robots can adapt to their surroundings and quickly reach their target location.
Smart Images

Figure CN117970917B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of path planning technology, and more specifically to a method for path planning of mobile robots in unknown environments. Background Technology
[0002] Current path planning algorithms, when given a global map, can plan a relatively short and smooth path. However, during the robot's movement along this path, uncertainties may arise (such as dynamic obstacles or a lack of timely updates to the global map, resulting in missing static obstacle information). Real-time obstacle avoidance necessitates local path planning algorithms. In such cases, the robot may fall into obstacle traps and be unable to continue moving due to deficiencies in the obstacle avoidance algorithm, or obstacles may exist near the target point, making it difficult for the robot to reach the target location due to the algorithm's limitations. Summary of the Invention
[0003] The purpose of this invention is to provide a path planning method for mobile robots in unknown environments. This method can avoid obstacles in real time and solve the problems of robots getting stuck in obstacle traps and being unable to reach their targets when moving.
[0004] A method for path planning of a mobile robot in an unknown environment includes:
[0005] Obtain the starting position and the target position;
[0006] Plan the initial path based on the starting and target positions;
[0007] Rasterize the global map and assign value to each grid cell;
[0008] An improved dynamic window method is used to correct the initial path based on the cost of each grid during the movement of the mobile robot.
[0009] Preferably, the improved dynamic window method includes: a dynamic window method for evaluating sub-functions;
[0010] The dynamic window method evaluation function includes:
[0011] The orientation evaluation function is used to evaluate the orientation of the mobile robot and the angle of the line connecting the mobile robot and the target position.
[0012] The obstacle distance evaluation function is used to evaluate the distance between the mobile robot and obstacles.
[0013] The movement speed evaluation function is used to evaluate the robot's movement speed;
[0014] The grid cost evaluation function is used to evaluate the cost of a grid. The score of the mobile robot's predicted trajectory is related to the cost of the grid in the map.
[0015] Weights are set before each evaluation function, and the weight of each evaluation function will affect the choice of the mobile robot's movement path.
[0016] Preferably, before correcting the initial path based on the cost of each grid cell using the improved dynamic window method during the mobile robot's movement, the robot's speed is further limited, specifically:
[0017] The maximum and minimum speeds of the mobile robot are preset. During movement, the speed of the mobile robot cannot exceed the maximum linear velocity and the maximum angular velocity.
[0018] The robot's own motor performance limits the robot's current linear velocity and angular velocity, as well as the maximum linear and angular acceleration of the moving robot;
[0019] The obstacle distance limits the robot's current linear and angular velocities and the maximum linear and angular accelerations of the moving robot.
[0020] Preferably, optimizing the direction evaluation function includes:
[0021] Set the influence range of the target location, optimize the weights before the direction evaluation function within the influence range, and multiply the weights by a coefficient.
[0022] Preferably, the grid cost evaluation function is used to evaluate the cost of the grid, and the score of the mobile robot's predicted trajectory is related to the cost of the grid in the map, including:
[0023] When an obstacle is detected ahead, the mobile robot adaptively corrects its initial path, adjusts its direction of travel, and changes the value of the grids it passes through to a negative value. The value of the grids it passes through gradually increases to 0 over time.
[0024] When a mobile robot detects multiple obstacles, it will prioritize moving through grids with higher cost to avoid getting trapped in obstacle traps.
[0025] Preferably, the mobile robot's adaptive correction of the predicted trajectory includes:
[0026] The fixed simulation time was changed to an adaptive simulation time, which adjusts the simulation time adaptively based on the number of nearby obstacles detected by the mobile robot.
[0027] Preferably, the influence range of the target location is set, and the weights before the direction evaluation function are optimized within the influence range. The weights are multiplied by a coefficient including:
[0028] The weight remains unchanged when the robot is more than the target location is within the influence range.
[0029] When the distance between the robot and the target position is less than the influence range, the weights are adjusted according to the control constants set in the actual situation, the influence range of the target position, and the distance between the robot and the target position.
[0030] A path planning system for a mobile robot in an unknown environment includes:
[0031] The data acquisition module is used to obtain the starting position and the target position;
[0032] The initial path planning module is used to plan the initial path based on the starting position and the target position;
[0033] The data processing module rasterizes the global map and assigns value to each raster.
[0034] The path correction module uses an improved DWA algorithm to correct the predicted trajectory based on the cost of each grid cell during the movement of the mobile robot.
[0035] An electronic device includes a chip, a processor, and a memory, wherein the memory stores computer program code, the computer program code including computer instructions, and the electronic device executes a mobile robot path planning method in an unknown environment when the chip executes the computer instructions.
[0036] A computer-readable storage medium storing a computer program, the computer program including program instructions, which, when executed by a processor of an electronic device, cause the processor to perform the aforementioned method for path planning of a mobile robot in an unknown environment.
[0037] The path planning algorithm of this invention helps the robot escape obstacle traps, avoiding situations where the robot spins in place when surrounded by obstacles, and preventing the robot from reaching the target point due to the limitations of obstacle avoidance algorithms when there are obstacles in front of it. It solves the problem of the robot being unable to reach the target location and can also adapt to the surrounding environment, reaching the target location more quickly. Attached Figure Description
[0038] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0040] Figure 1 This is a flowchart of the present invention;
[0041] Figure 2 This is a schematic diagram showing the robot navigating through a "C"-shaped obstacle using the improved algorithm of this invention.
[0042] Figure 3 This is a schematic diagram of the robot of the present invention trapped in an obstacle that is almost completely surrounded by obstacles;
[0043] Figure 4 This is a schematic diagram illustrating the situation where the target of the improved dynamic window method of the present invention is unreachable;
[0044] Figure 5 This is a schematic diagram showing how the robot successfully reaches the target position after the improved algorithm of this invention. Detailed Implementation
[0045] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.
[0046] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.
[0047] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" and "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. When the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.
[0048] Current path planning algorithms, given a known global map, can plan a short and smooth path. However, as the robot moves along this path, unknown dynamic obstacles may appear, or new static obstacle information may be missing due to outdated map updates. In such cases, the robot may fall into obstacle traps and be unable to continue moving due to deficiencies in the obstacle avoidance algorithm, or obstacles may exist near the target point, making it difficult for the robot to reach the target location due to obstacle avoidance. This invention addresses these issues by dynamically planning local routes during movement without needing to know the obstacle information of the global map, achieving real-time obstacle avoidance and solving the obstacle trap problem and target unreachability problem of traditional mobile robots.
[0049] Example 1
[0050] A method for path planning of a mobile robot in an unknown environment includes:
[0051] S100, obtain the starting position and target position;
[0052] S200, the initial predicted trajectory is obtained based on the starting position and the target position;
[0053] S300 rasterizes the global map and assigns value to each grid cell.
[0054] The S400 employs an improved dynamic window method to correct the initial path based on the cost of each grid cell during the mobile robot's movement.
[0055] Preferably, the improved dynamic window method includes: a dynamic window method evaluation function;
[0056] The dynamic window method evaluation function includes:
[0057] The orientation evaluation function is used to evaluate the orientation of the mobile robot and the angle of the line connecting the mobile robot and the target position.
[0058] The obstacle distance evaluation function is used to evaluate the distance between the mobile robot and obstacles.
[0059] The movement speed evaluation function is used to evaluate the robot's movement speed;
[0060] The grid cost evaluation function is used to evaluate the cost of a grid. The score of the mobile robot's predicted trajectory is related to the cost of the grid in the map.
[0061] Weights are set before each evaluation function, and the weight of each evaluation function will affect the choice of the mobile robot's movement path.
[0062] The orientation evaluation function, head(v,ω), is mainly used to prompt the mobile robot to move towards the target. It primarily evaluates the robot's orientation and the angle between the line connecting the robot and the target point; a smaller angle results in a higher evaluation. This invention improves this evaluation function by setting a target point influence range L. Within this range, the coefficient α before head(v,ω) is optimized by multiplying α by a coefficient ρ, as shown in the following formula:
[0063]
[0064] Where k is the proportionality coefficient, used to change the degree of control over the evaluation sub-function α·head(v,ω); j is the control constant, which is set according to the situation, generally taken as 0.2-0.3; d g This represents the distance between the robot and the target point.
[0065] The obstacle distance evaluation function, dist(v,ω), mainly evaluates the distance between the mobile robot and the obstacle. The evaluation criterion of the dynamic window method dist(x,y) is the distance between the mobile robot and the obstacle. The greater the distance, the higher the evaluation.
[0066] The velocity(v,ω) function evaluates the robot's movement speed. The higher the robot's speed, the higher the evaluation.
[0067] This invention introduces a new evaluation sub-function, the grid cost value evaluation function: the score of the robot's predicted trajectory is related to the cost value in the grid. The lower the grid cost value involved in the predicted trajectory, the lower the score of the predicted trajectory. path(v,ω) helps the robot escape semi-enclosed obstacles and prevents the robot from wandering on previously traveled paths.
[0068] As the mobile robot moves, the cost of each grid it passes through becomes negative. Over time, the cost of these grids gradually increases to zero. When the robot approaches a grid with a cost value again, it will prioritize moving to the grid with a cost value of zero because the cost is negative. This prevents the robot from spinning in place or stopping when encountering a "C"-shaped obstacle.
[0069] When robots encounter Figure 3 In the scenario shown, because the cost value of the grid the robot passes through is negative, the robot may get stuck in the obstacle trap. However, as time goes on, the cost value on the grid gradually becomes 0, and the robot can return along the same path and escape the obstacle trap.
[0070] Preferably, before S400 corrects the predicted trajectory based on the cost value of each grid using the improved dynamic window method during the mobile robot's movement, it further includes S310 limiting the robot's movement speed, specifically:
[0071] The maximum and minimum speeds of the mobile robot are preset. During movement, the speed of the mobile robot cannot exceed the maximum linear velocity and the maximum angular velocity.
[0072] The robot's own motor performance limits the robot's current linear velocity and angular velocity, as well as the maximum linear and angular acceleration of the moving robot;
[0073] The obstacle distance limits the robot's current linear and angular velocities and the maximum linear and angular accelerations of the moving robot.
[0074] The linear and angular velocities of mobile robots are limited: during movement, there is acceleration and deceleration, and the change in velocity is within a certain range, constrained by acceleration. Mobile robots are limited by their own maximum and minimum speeds.
[0075] V s ={(v,ω)|v∈[v min ,v max ]∩ω∈[ω min ,ω max ]}
[0076] During movement, the speed of the mobile robot cannot exceed its maximum linear velocity v. max and maximum angular velocity ω max
[0077] Mobile robots are affected by the performance of their own motors:
[0078]
[0079] v c ω c v represents the current linear velocity and angular velocity of the mobile robot. b ω b These are the maximum linear and angular accelerations of the mobile robot.
[0080] The mobile robot is affected by obstacles. To stop the mobile robot before it collides with the obstacles:
[0081]
[0082] dist(v,ω) represents the distance to the nearest obstacle on the trajectory corresponding to (v,ω).
[0083] The speed constraint for the mobile robot is: V = V s ∩Va ∩V b
[0084] Preferably, optimizing the direction evaluation function includes:
[0085] Set the influence range of the target location, optimize the weights before the direction evaluation function within the influence range, and multiply the weights by a coefficient.
[0086] Preferably, the grid cost evaluation function is used to evaluate the cost of the grid, and the score of the mobile robot's predicted trajectory is related to the cost of the grid in the map, including:
[0087] When an obstacle is detected ahead, the mobile robot corrects its predicted trajectory based on an improved algorithm, adjusts its direction of travel, and changes the value of the grid it passes through to a negative value. The value of the grid it passes through gradually increases to 0 over time.
[0088] When a mobile robot detects multiple obstacles, it will prioritize traversing grids with higher cost to avoid repeatedly traversing the same path.
[0089] Existing robots often have Figure 4 There are two scenarios. The first scenario is that there is an obstacle behind the target point, and the robot is near the target point but can never reach it. The second scenario is that there is an obstacle in front of the target point, and due to obstacle avoidance, the robot circles around the target point and the obstacle, and can never reach the target position.
[0090] This invention improves the calculation method of the weight coefficients in the obstacle distance evaluation function head(v,ω), thus enhancing the robot's tendency to move towards the target point as it approaches it. (See attached diagram) Figure 5 As shown, the mobile robot can successfully reach the target location.
[0091] Preferably, the mobile robot's adaptive correction of the predicted trajectory includes:
[0092] The fixed simulation time was changed to an adaptive simulation time, which adjusts the simulation time adaptively based on the number of nearby obstacles detected by the mobile robot.
[0093] The fixed simulation time is improved to an adaptive simulation time, which adjusts the simulation time according to the number of obstacles near the mobile robot. When there are many obstacles, the simulation time is shorter, the predicted trajectory is shorter, and the robot's safety in unknown environments is ensured. The number of obstacles around the robot is detected by a ranging sensor. The more obstacles detected, the shorter the robot's simulation time. If the original simulation time is T, the improved simulation time is:
[0094]
[0095] Where T' is the improved adaptive sampling period, and a is the estimated number of obstacles.
[0096] Preferably, the influence range of the target location is set, and the weights before the direction evaluation function are optimized within the influence range. The weights are multiplied by a coefficient including:
[0097] The weight remains unchanged when the robot is more than the target location is within the influence range.
[0098] When the distance between the robot and the target position is less than the influence range, the weights are adjusted according to the control constants set in the actual situation, the influence range of the target position, and the distance between the robot and the target position.
[0099] Example 2
[0100] A path planning system for a mobile robot in an unknown environment includes:
[0101] The data acquisition module is used to obtain the starting position and the target position;
[0102] The initial path planning module is used to generate an initial predicted trajectory based on the starting position and the target position;
[0103] The data processing module rasterizes the global map and assigns value to each raster.
[0104] The path correction module uses an improved dynamic window method to correct and predict the trajectory based on the cost of each grid cell during the movement of the mobile robot.
[0105] Example 3
[0106] An electronic device includes a chip, a processor, and a memory, wherein the memory stores computer program code, the computer program code including computer instructions, and the electronic device executes a path planning method for a mobile robot in an unknown environment when the chip executes the computer instructions.
[0107] Example 4
[0108] A computer-readable storage medium storing a computer program, the computer program including program instructions, which, when executed by a processor of an electronic device, cause the processor to perform a path planning method for a mobile robot in an unknown environment.
[0109] The path algorithm proposed in this invention helps the robot escape obstacle traps, preventing it from spinning in place when surrounded by obstacles and avoiding situations where the target point becomes unreachable due to the limitations of obstacle avoidance algorithms. It solves the problem of the robot being unable to reach the target location and can also adapt to the surrounding environment, reaching the target location more quickly.
[0110] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.
Claims
1. A method for path planning of a mobile robot in an unknown environment, characterized in that, include: Obtain the starting position and the target position; An initial predicted trajectory is generated based on the starting and target positions; Rasterize the global map and assign value to each grid cell; An improved dynamic window method is used to correct the predicted trajectory based on the cost of each grid during the movement of the mobile robot. The improved dynamic window method includes: a dynamic window method evaluation function; the dynamic window method evaluation function includes: a direction evaluation function, used to evaluate the orientation of the mobile robot and the direction angle of the line connecting the mobile robot and the target position; an obstacle distance evaluation function, used to evaluate the distance between the mobile robot and the obstacle; a movement speed evaluation function, used to evaluate the movement speed of the robot; and a grid cost evaluation function, used to evaluate the cost of the grid, the score of the mobile robot's predicted trajectory is related to the cost of the grid in the map; a weight is set before each evaluation function, and the weight of each evaluation function will affect the selection of the mobile robot's movement path; Optimizing the direction evaluation function includes: setting the influence range of the target location. L Within the scope of influence, the weights before the directional evaluation function are optimized by multiplying the weights by a coefficient. : ; in k This is the proportionality coefficient; This is the control constant; The distance between the robot and the target point; when the distance between the robot and the target location is greater than the influence range, the weight does not change; when the distance between the robot and the target location is less than the influence range, the weight is changed according to the control constant set in the actual situation, the influence range of the target location, and the distance between the robot and the target location. The grid cost evaluation function is used to evaluate the cost of a grid. The score of the mobile robot's predicted trajectory is related to the cost of the grid in the map, including: when an obstacle is detected ahead, the mobile robot adaptively corrects the predicted trajectory, adjusts its direction of travel, and changes the cost of the grid it passes through to a negative value. The cost of the grid passed through will gradually increase to 0 over time; when the mobile robot detects multiple obstacles, the robot will prioritize traveling through grids with higher cost values to avoid repeatedly traversing the same path. The mobile robot adaptive correction prediction trajectory includes: modifying the fixed simulation time to an adaptive simulation time, and adaptively changing the simulation time according to the number of nearby obstacles detected by the mobile robot.
2. The method for path planning of a mobile robot in an unknown environment according to claim 1, characterized in that, Before using the improved dynamic window method to correct the initial path based on the value of each grid cell during the mobile robot's movement, the method also includes limiting the robot's speed, specifically: The maximum and minimum speeds of the mobile robot are preset. During movement, the speed of the mobile robot cannot exceed the maximum linear velocity and the maximum angular velocity. The robot's own motor performance limits the robot's current linear velocity and angular velocity, as well as the maximum linear and angular acceleration of the moving robot; The obstacle distance limits the robot's current linear and angular velocities and the maximum linear and angular accelerations of the moving robot.
3. A path planning system for a mobile robot in an unknown environment, used to implement the path planning method for a mobile robot in an unknown environment as described in claim 1 or 2, characterized in that, include: The data acquisition module is used to obtain the starting position and the target position; The initial path planning module generates an initial predicted trajectory based on the starting and target positions. The data processing module rasterizes the global map and assigns value to each raster. The path correction module uses an improved dynamic window method to correct the predicted trajectory based on the cost of each grid cell during the movement of the mobile robot.
4. An electronic device, characterized in that, include: The electronic device comprises a chip, a processor, and a memory, the memory being used to store computer program code, the computer program code including computer instructions, wherein, when the chip executes the computer instructions, the electronic device performs a mobile robot path planning method in an unknown environment as described in any one of claims 1 to 2.
5. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which includes program instructions that, when executed by a processor of an electronic device, cause the processor to perform a path planning method for a mobile robot in an unknown environment as described in any one of claims 1 to 2.
Citation Information
Patent Citations
Mobile robot intelligent path planning method
CN112631294A
Path planning method based on adaptive grid and improved A*-DWA fusion algorithm
CN116360457A
