A robot path planning method, electronic device and medium

Abstract

The application relates to a robot path planning method, an electronic device and a medium, and belongs to the technical field of intelligent robots, wherein the method comprises the following steps: merging an acquired static cost map and a dynamic cost map to obtain a global cost map; performing global path planning on the global cost map to obtain a global optimal path; performing local path planning based on the global optimal path to obtain a local optimal trajectory, controlling the robot to execute the local optimal trajectory until a global target point is reached; determining the dynamic cost of the local optimal trajectory, updating the dynamic cost map, and further updating the global cost map to re-perform path planning. The dynamic cost of the robot executing the local optimal trajectory is updated into the dynamic cost map, so that the robot can actively avoid a historical difficult-to-pass area in the path planning process, and the navigation stability and long-term operation efficiency of the robot in a complex and narrow environment are improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent robot technology, and in particular to a robot path planning method, electronic device, and medium. Background Technology

[0002] Mobile robots are comprehensive systems integrating environmental perception, dynamic decision-making and planning, behavior control and execution, and are widely used in smart logistics, automated sorting and many other scenarios. Among them, path planning is one of the core technologies of mobile robots, and its quality directly affects the operational safety and efficiency of mobile robots.

[0003] Traditional path planning generally uses A-Star algorithm and Dynamic Window Approach (DWA) co-planning. The algorithm is responsible for searching a globally optimal path from the starting point to the target point on a known map to avoid static obstacles and ensure the path's rationality. The DWA algorithm is responsible for dynamically sampling feasible speed commands based on real-time sensor data during the robot's movement and selecting the optimal trajectory to avoid local dynamic obstacles.

[0004] However, the above solutions remain at the level of "single planning and execution". When the robot repeatedly travels through the same difficult areas (such as narrow passages and long-term congestion), the system lacks the ability to "memorize" and "learn" and cannot benefit from historical travel experience. This may lead to it continuously choosing roads that are statically optimal but are actually difficult to travel, resulting in low work efficiency. Summary of the Invention

[0005] In view of this, it is necessary to provide a robot path planning method, electronic device and medium to solve the technical problem of low operation efficiency in the prior art.

[0006] To address the aforementioned problems, in a first aspect, the present invention provides a robot path planning method, comprising:

[0007] S101. Convert the acquired static raster map into a static cost map, initialize the dynamic cost map, and merge the static cost map and the dynamic cost map to obtain a global cost map.

[0008] S102. Based on the preset global path planning algorithm, global path planning is performed on the global cost map to obtain the global optimal path from the current location point to the global target point;

[0009] S103. Based on the preset local path planning algorithm and the global optimal path, perform local path planning to obtain the local optimal trajectory and its corresponding trajectory planning feature parameters, and control the robot to execute the local optimal trajectory until the global target point is reached.

[0010] S104. Based on the trajectory planning feature parameters, determine the dynamic cost of the local optimal trajectory, update the dynamic cost map based on the dynamic cost of the local optimal trajectory, and then update the global cost map, returning to step S102.

[0011] In one possible implementation, the global path planning algorithm employs... The algorithm, wherein the local path planning algorithm adopts the TEB algorithm, and the local path planning algorithm performs local path planning through a multi-objective weighted optimization function, the multi-objective weighted optimization function being:

[0012] ;

[0013] In the formula, This indicates the trajectory to be optimized. This represents the cost of the trajectory to be optimized. Indicates the cost of time. Indicates the cost of obstacles. This represents the cost of speed constraints. This represents the cost of acceleration constraints. This represents the time weighting coefficient. This represents the obstacle weighting coefficient. This represents the speed constraint weighting coefficient. This represents the acceleration constraint weighting coefficient;

[0014] In one possible implementation, the time weighting coefficient, the obstacle weighting coefficient, the velocity constraint weighting coefficient, and the acceleration constraint weighting coefficient are calibrated through the following steps:

[0015] In the preset first test scenario, the time weight coefficient and the acceleration constraint weight coefficient are fixed to the corresponding initial weight coefficients. The obstacle weight coefficient and the velocity constraint weight coefficient are adjusted for path planning and navigation so that the task completion rate parameter meets the preset requirements, the minimum distance parameter between the robot and the obstacle is maximized, the velocity tracking error parameter is minimized, and the calibration values ​​of the obstacle weight coefficient and the velocity constraint weight coefficient are obtained.

[0016] In the preset first test scenario, the obstacle weight coefficient and the velocity constraint weight coefficient are fixed to their corresponding calibration values, the time weight coefficient is fixed to its corresponding initial weight coefficient, and the acceleration constraint weight coefficient is adjusted for path planning and navigation. This ensures that the task completion rate parameter, the minimum distance parameter between the robot and the obstacle, the velocity tracking error parameter, and the response speed parameter all meet the corresponding preset requirements, while minimizing the path smoothness and mechanical jitter parameters, thus obtaining the calibration value of the acceleration constraint weight coefficient.

[0017] In the preset first test scenario, the obstacle weight coefficient, the velocity constraint weight coefficient, and the acceleration constraint weight coefficient are fixed to their corresponding calibration values. The time weight coefficient is adjusted for path planning and navigation so that the task completion rate parameter, the minimum distance parameter between the robot and the obstacle, the velocity tracking error parameter, the response speed parameter, the path smoothness, and the mechanical vibration degree parameter all meet the corresponding preset requirements. The total travel time parameter is minimized to obtain the calibration value of the time weight coefficient.

[0018] In one possible implementation, determining the dynamic cost of a locally optimal trajectory based on the trajectory planning feature parameters, and updating the dynamic cost map based on the dynamic cost of the locally optimal trajectory, includes:

[0019] Based on the trajectory planning feature parameters, the difficulty score is calculated;

[0020] The dynamic cost of the local optimal trajectory is calculated based on the difficulty score, and the dynamic cost map is updated based on the dynamic cost of the local optimal trajectory.

[0021] The trajectory planning feature parameters include the cost of the local optimal trajectory, the minimum distance between the local optimal trajectory and obstacles, the number of optimization iterations for the local optimal trajectory, and the variance of all linear velocities on the local optimal trajectory. The formula for calculating the difficulty score is as follows:

[0022] ;

[0023] ;

[0024] ;

[0025] ;

[0026] ;

[0027] In the formula, Indicates the difficulty level rating. This represents the cost of a locally optimal trajectory. This represents the number of optimization iterations for a locally optimal trajectory. This represents the minimum distance between the locally optimal trajectory and the obstacle. This represents the variance of all linear velocities on the locally optimal trajectory. This represents the number of optimization iterations for the normalized local optimal trajectory. This represents the minimum distance between the normalized local optimal trajectory and the obstacle. This represents the cost of the normalized local optimal trajectory. This represents the variance of all linear velocities on the normalized local optimal trajectory. This represents the trajectory cost weighting coefficient. The weighting coefficient represents the number of trajectory iterations. This represents the obstacle spacing weighting coefficient. This represents the weighting coefficient of the variance of the trajectory linear velocity. This represents the reference value for trajectory cost. Indicates the maximum number of iterations. Indicates focus on distance. Indicates the minimum safe distance. This represents the maximum acceptable speed variance threshold.

[0028] In one possible implementation, the trajectory cost weighting coefficient, the trajectory iteration number weighting coefficient, the trajectory obstacle spacing weighting coefficient, and the trajectory linear velocity variance weighting coefficient are calibrated through the following steps:

[0029] Using the difficulty score as the objective layer, and the cost of the normalized local optimal trajectory, the number of optimization iterations of the normalized local optimal trajectory, the minimum distance between the normalized local optimal trajectory and the obstacle, and the variance of all linear velocities on the normalized local optimal trajectory as the criteria layer, a hierarchical model is constructed.

[0030] The four indicators in the criterion layer are compared pairwise. Their relative importance is determined by comparing their safety, stability, computational cost, and path economy. A judgment matrix is ​​constructed, and the largest eigenvalue of the judgment matrix and its corresponding normalized eigenvector are calculated. The priority of safety is greater than the priority of stability, the priority of stability is greater than the priority of computational cost, and the priority of computational cost is greater than the priority of path economy.

[0031] The consistency index is calculated based on the largest eigenvalue. The consistency index is used to perform a consistency test on the judgment matrix. The normalized eigenvector of the judgment matrix that passes the consistency test is used as the trajectory cost weight coefficient, trajectory iteration number weight coefficient, trajectory obstacle spacing weight coefficient, and trajectory linear velocity variance weight coefficient.

[0032] In one possible implementation, the dynamic cost map is updated according to the following formula:

[0033] ;

[0034] ;

[0035] In the formula, Represents the grid coordinates of points on the dynamic cost map. Updated dynamic cost, Represents the grid coordinates of points on the dynamic cost map. The dynamic cost before the update Represents the dynamic cost of a locally optimal trajectory. Indicates the difficulty level rating. This indicates the upper limit of the dynamic cost of a single injection. Indicates the sensitivity factor. Indicates the attenuation factor. Represents the grid coordinates of points on the static cost map. The cost.

[0036] In one possible implementation, the single-injection dynamic cost cap, the sensitivity factor, and the decay factor are calibrated using the following steps:

[0037] In the preset fifth test scenario, the sensitivity factor and the decay factor are fixed to their corresponding initial values, the upper limit of the dynamic cost of a single injection is adjusted, and robot path planning and navigation are performed so that the number of iterations in which the robot first stably avoids the first preset region in the fifth test scenario during global path planning is stable within the preset iteration range, and the calibration value of the upper limit of the dynamic cost of a single injection is obtained.

[0038] In the preset sixth test scenario, the upper limit of the single injection dynamic cost is fixed to the corresponding calibration value, the decay factor is fixed to the corresponding initial value, the sensitivity factor is adjusted, and robot path planning and navigation are performed so that the robot actively avoids the second preset area in the sixth test scenario where the difficulty score is higher than the threshold, and does not avoid the third preset area where the difficulty score is lower than the threshold, thereby obtaining the calibration value of the sensitivity factor.

[0039] The single injection dynamic cost upper limit and sensitivity factor are fixed to the corresponding calibration values. The decay factor is adjusted. Temporary obstacles are set on the robot's path in the preset seventh test scenario to perform robot path planning and navigation. The learning time for the robot to bypass the temporary obstacles is obtained. The temporary obstacles are removed in the preset seventh test scenario to perform robot path planning and navigation. The forgetting time for the robot to reselect the robot's path is obtained. The learning time and the forgetting time are within the corresponding preset time range, and the calibration value of the decay factor is obtained.

[0040] In one possible implementation, the return step S102 includes:

[0041] Obtain the initial total cost of the globally optimal path on the global cost map before the update, and the cumulative cost of the actual driving path in the globally optimal path;

[0042] Calculate the new cost of the remaining paths in the global optimal path on the updated global cost map;

[0043] If the sum of the cumulative cost and the new cost is greater than the product of the preset sensitivity coefficient and the initial total cost, then return to step S102.

[0044] In a second aspect, the present invention also provides an electronic device, including a memory and a processor;

[0045] The memory is used to store programs;

[0046] The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps of the robot path planning method described above.

[0047] Thirdly, the present invention also provides a computer-readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the robot path planning method described above.

[0048] The beneficial effects of this invention are as follows: The robot path planning method provided by this invention introduces a dynamic cost refeeding mechanism to update the dynamic cost of the robot executing the local optimal trajectory to the dynamic cost map. This is deeply integrated with global path planning and local path optimization, enabling the robot to learn from experience and optimize itself. During the path planning process, the robot can actively avoid historically difficult passage areas, thereby improving the navigation stability and long-term operating efficiency of the robot in complex and narrow environments. Attached Figure Description

[0049] Figure 1 This is a schematic flowchart of an embodiment of the robot path planning method provided by the present invention;

[0050] Figure 2 This is a schematic flowchart of an embodiment of the method for calibrating the weight coefficients of a multi-objective weighted optimization function provided by the present invention;

[0051] Figure 3 A schematic flowchart of an embodiment of the method for calibrating the weight coefficients of each item in the difficulty scoring formula provided by the present invention;

[0052] Figure 4 A schematic flowchart of an embodiment of the dynamic cost map update formula parameter calibration method provided by the present invention;

[0053] Figure 5 For the present invention Figure 1 A schematic flowchart of an embodiment of step S104;

[0054] Figure 6 A schematic diagram of an embodiment of the electronic device provided by the present invention. Detailed Implementation

[0055] 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 them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0056] This invention provides a robot path planning method, electronic device, and medium, which are described below.

[0057] Figure 1 This is a schematic flowchart of an embodiment of the robot path planning method provided by the present invention, as shown below. Figure 1 As shown, robot path planning methods include:

[0058] S101. Convert the acquired static raster map into a static cost map, initialize the dynamic cost map, merge the static cost map and the dynamic cost map to obtain the global cost map.

[0059] It should be noted that converting a static raster map into a static cost map... This process is primarily achieved through obstacle inflation technology. The specific steps include: First, cells marked as "occupied" (e.g., walls) in the static grid map are designated as "lethal obstacles" in the static cost map, with a high cost value (e.g., 254). Then, a preset expansion radius (typically set based on the robot's physical dimensions) is used to expand outwards from the "lethal obstacle." Within this radius, the cost value of cells decreases based on their distance from the nearest "lethal obstacle": the closer to the obstacle, the higher the cost value (e.g., a cost of 253 for "inner obstacle" when the robot's center is in this cell and a collision would occur); the farther away, the lower the cost value, until it reaches 0 (completely free). The resulting static cost map... It contains a potential field with decreasing value surrounding a physical obstacle.

[0060] It should also be noted that the dynamic cost map Used to store the "historical difficulty of passage" calculated in subsequent steps, when the system runs for the first time, the dynamic cost map is created as a raster map of the same size as the static cost map, and the cost value of all cells is initialized to 0. Therefore, when the global path planning module runs the global path planning algorithm for the first time, the dynamic cost value is 0. The global path planning algorithm searches on the static cost map to obtain a globally optimal path from the global starting point to the global target point.

[0061] It should also be noted that the global cost map is the combined cost function used in global path search. When using the global path planning algorithm to search for a path, it evaluates the coordinates of each grid point. Total cost of passage It is through the static cost of this point and dynamic cost The result of adding them together:

[0062] ;

[0063] Therefore, when planning, the global path planning algorithm will comprehensively consider the static cost of physical obstacles and the dynamic cost learned by the "dynamic cost feedback mechanism" of this invention in order to find an optimal path with the lowest global total cost.

[0064] S102. Based on the preset global path planning algorithm, perform global path planning on the global cost map to obtain the global optimal path from the current location point to the global target point;

[0065] In some embodiments of the present invention, the global path planning algorithm is as follows: (A-Star) algorithm. It should be noted that the choice of global path planning algorithm can be adjusted according to actual needs, and can also be... Algorithms such as Dijkstra's are not limited to... The algorithms will not be elaborated on here.

[0066] S103. Based on the preset local path planning algorithm and the global optimal path, perform local path planning to obtain the local optimal trajectory and its corresponding trajectory planning feature parameters, and control the robot to execute the local optimal trajectory until the global target point is reached.

[0067] Considering that the commonly used local path planning algorithm in the existing technology is the dynamic window algorithm, which is based on the principle of instantaneous velocity sampling, its planning is short-sighted and lacks overall optimization for the spatiotemporal consistency of the trajectory. Especially in narrow corners or areas with dense obstacles, robots are prone to trajectory oscillation, repeated forward and backward movements, or even local jamming. In addition, the dynamic window algorithm also has insufficient control over the accuracy of the destination, which is difficult to meet some scenarios with high-precision docking requirements, such as the grasping and delivery of express packages. Small errors can lead to grasping or delivery failures, which seriously restricts the overall success rate of the task. To solve the limitations of the dynamic window algorithm, in some embodiments of the present invention, the Timed Elastic Band (TEB) algorithm is introduced as a local planner, that is, the local path planning algorithm is the Timed Elastic Band algorithm. The Timed Elastic Band algorithm can generate a smooth, continuous local path that conforms to robot dynamics by jointly optimizing the pose sequence and timestamp of a trajectory within a local window, which significantly improves the robot's passability in narrow spaces and the accuracy of destination control.

[0068] It should be noted that the time-elastic band algorithm involves the robot, during its journey along the globally optimal path, extracting a local reference path and a local target point within a preset range from the globally optimal path in each planning cycle. Based on a multi-objective weighted optimization function and a G2O solver, a locally optimal trajectory is obtained. The overall difficulty includes the locally optimal path and the linear and angular velocity motion control parameters, enabling the robot to continuously move towards the local target point until it reaches the final global target point. The multi-objective weighted optimization function is as follows:

[0069] ;

[0070] In the formula, This indicates the trajectory to be optimized. This represents the cost of the trajectory to be optimized. Indicates the cost of time. Indicates the cost of obstacles. This represents the cost of speed constraints. This represents the cost of acceleration constraints. This represents the time weighting coefficient. This represents the obstacle weighting coefficient. This represents the speed constraint weighting coefficient. This represents the acceleration constraint weighting coefficient.

[0071] Furthermore, in order to achieve the optimal balance of robot navigation performance under different working conditions, in some embodiments of the present invention, such as... Figure 2 As shown, the time weighting coefficient, obstacle weighting coefficient, velocity constraint weighting coefficient, and acceleration constraint weighting coefficient are calibrated through the following steps:

[0072] S201. Under the preset first test scenario, fix the time weight coefficient and acceleration constraint weight coefficient to the corresponding initial weight coefficients, adjust the obstacle weight coefficient and velocity constraint weight coefficient for path planning and navigation, so that the minimum distance parameter between the robot and the obstacle is maximized and the velocity tracking error parameter is minimized while the task completion rate parameter meets the preset requirements, and obtain the calibration values ​​of the obstacle weight coefficient and velocity constraint weight coefficient.

[0073] It should be noted that before testing, a typical working condition library needs to be built, and a series of simulation or physical test scenarios need to be established to cover the typical application environment expected by this invention, such as: narrow passages, areas with dense dynamic obstacles, U-turns, and high-precision stopping points, i.e., the preset first test scenario; set performance evaluation indicators (KPIs): define key indicators for quantifying navigation effects, including but not limited to: task success rate, total travel time, path smoothness (e.g., variance or root mean square value of speed / acceleration), and minimum safe distance from obstacles; systematic iterative optimization is based on a set of balanced initial weight coefficients as a baseline, and iterative adjustments and verifications are performed according to priority and trade-off relationships.

[0074] It should also be noted that the obstacle weight coefficient and speed constraint weight coefficient are the highest priority. The obstacle weight coefficient is adjusted first to ensure that the robot can maintain a sufficient safe distance from obstacles in all preset first test scenarios (especially narrow passages). Increasing this weight coefficient will make the robot more inclined to move away from obstacles, but too high a weight coefficient may cause the robot to be unable to find a path in narrow spaces. The speed constraint weight coefficient is adjusted simultaneously to ensure that the robot strictly adheres to the preset global maximum speed, minimum speed, or speed limit requirements in specific areas (such as turns). Increasing this weight coefficient can enhance the robot's ability to track speed curves.

[0075] S202. Under the preset first test scenario, the obstacle weight coefficient and the velocity constraint weight coefficient are fixed to the corresponding calibration values, the time weight coefficient is fixed to the corresponding initial weight coefficient, and the acceleration constraint weight coefficient is adjusted for path planning and navigation. Under the condition that the task completion rate parameter, the minimum distance parameter between the robot and the obstacle, the velocity tracking error parameter and the response speed parameter all meet the corresponding preset requirements, the path smoothness and mechanical vibration parameters are minimized to obtain the calibration value of the acceleration constraint weight coefficient.

[0076] It should be noted that after meeting safety and speed constraints, adjusting the acceleration constraint weight coefficient will suppress the robot's rapid acceleration and deceleration, resulting in a smoother running trajectory and less mechanical vibration. This is especially important for scenarios involving high-precision docking or transporting sensitive items, but an excessively high coefficient may sacrifice response speed.

[0077] S203. Under the preset first test scenario, fix the obstacle weight coefficient, velocity constraint weight coefficient and acceleration constraint weight coefficient to the corresponding calibration values, and adjust the time weight coefficient for path planning and navigation so that the task completion rate parameter, the minimum distance parameter between the robot and the obstacle, the velocity tracking error parameter, the response speed parameter, the path smoothness and the mechanical vibration degree parameter all meet the corresponding preset requirements, and minimize the total travel time parameter to obtain the calibration value of the time weight coefficient.

[0078] It should be noted that, under the premise of ensuring safety, smoothness and compliance with speed constraints, the time weight coefficient is adjusted last. Appropriately increasing the time weight coefficient can incentivize the robot to find shorter paths, thereby shortening the task execution time. However, an excessively high time weight coefficient can lead to an overly aggressive trajectory, thus sacrificing safety threshold or smoothness.

[0079] Tests were repeatedly run in a typical operating condition library to compare the KPI performance under different weight coefficient combinations. A set of weight coefficient values ​​that achieves the best balance between safety, smoothness, efficiency and constraint compliance was selected as the final configuration parameters of the system.

[0080] S104. Based on the trajectory planning feature parameters, determine the dynamic cost of the local optimal trajectory, update the dynamic cost map based on the dynamic cost of the local optimal trajectory, and then update the global cost map. Return to step S102.

[0081] In order to calculate the dynamic cost of a higher quality local optimal trajectory, in some embodiments of the present invention, step S104, which determines the dynamic cost of the local optimal trajectory based on trajectory planning feature parameters and updates the dynamic cost map based on the dynamic cost of the local optimal trajectory, includes: calculating a difficulty score based on trajectory planning feature parameters; calculating the dynamic cost of the local optimal trajectory based on the difficulty score; and updating the dynamic cost map based on the dynamic cost of the local optimal trajectory.

[0082] The trajectory planning feature parameters include the cost of the local optimal trajectory, the minimum distance between the local optimal trajectory and obstacles, the number of optimization iterations for the local optimal trajectory, and the variance of all linear velocities on the local optimal trajectory. The formula for calculating the difficulty score is as follows:

[0083] ;

[0084] ;

[0085] ;

[0086] ;

[0087] ;

[0088] In the formula, Indicates the difficulty level rating. This represents the cost of a locally optimal trajectory. This represents the number of optimization iterations for a locally optimal trajectory. This represents the minimum distance between the locally optimal trajectory and the obstacle. This represents the variance of all linear velocities on the locally optimal trajectory. This represents the number of optimization iterations for the normalized local optimal trajectory. This represents the minimum distance between the normalized local optimal trajectory and the obstacle. This represents the cost of the normalized local optimal trajectory. This represents the variance of all linear velocities on the normalized local optimal trajectory. This represents the trajectory cost weighting coefficient. The weighting coefficient represents the number of trajectory iterations. This represents the obstacle spacing weighting coefficient. This represents the weighting coefficient of the variance of the trajectory linear velocity. This represents the reference value for trajectory cost. Indicates the maximum number of iterations. Indicates focus on distance. Indicates the minimum safe distance. This represents the maximum acceptable speed variance threshold.

[0089] Furthermore, in order to objectively reflect the contribution of different difficulty indicators to the difficulty score, in some embodiments of the present invention, such as... Figure 3 As shown, the trajectory cost weighting coefficient, trajectory iteration number weighting coefficient, trajectory obstacle spacing weighting coefficient, and trajectory linear velocity variance weighting coefficient are calibrated through the following steps:

[0090] S301. Using the difficulty score as the target layer, and the cost of the normalized local optimal trajectory, the number of optimization iterations of the normalized local optimal trajectory, the minimum distance between the normalized local optimal trajectory and the obstacle, and the variance of all linear velocities on the normalized local optimal trajectory as the criteria layer, a hierarchical model is constructed.

[0091] S302. Compare the four indicators in the criterion layer pairwise. Determine their relative importance by comparing their safety, stability, computational cost, and path economy. Construct a judgment matrix and calculate the largest eigenvalue of the judgment matrix and its corresponding normalized eigenvector. Safety has a higher priority than stability, stability has a higher priority than computational cost, and computational cost has a higher priority than path economy.

[0092] It should be noted that, according to the invention's objective—to improve the robot's navigation stability, task endpoint accuracy, and long-term operational efficiency in complex and confined environments—technical personnel conducted pairwise comparisons of the four indicators in the criterion layer to determine their relative importance, and constructed the 1-9 scale method. Judgment Matrix As an example, technicians can make judgments based on the priority principle of "security" > "stability" > "computational cost" > "path economy". For example:

[0093] "Obstacle Distance" (corresponding to) Compared to "velocity variance" (corresponding to...) If ) is "obviously important", then , .

[0094] "Obstacle Distance" (corresponding to) Compared to "number of iterations" (corresponding to) If ) is "strongly important", then , .

[0095] The rest follow the same pattern, and .

[0096] It should also be noted that, specifically, mathematical methods (such as the sum-product method or the square root method) are used to calculate the judgment matrix. The largest eigenvalue and its corresponding normalized eigenvectors .

[0097] S303. Calculate the consistency index based on the maximum eigenvalue, perform consistency verification on the judgment matrix based on the consistency index, and use the normalized eigenvector of the judgment matrix that passes the consistency verification as the trajectory cost weight coefficient, trajectory iteration number weight coefficient, trajectory obstacle spacing weight coefficient, and trajectory linear velocity variance weight coefficient.

[0098] It should be noted that consistency checks are performed to ensure the rationality of the judgment logic by calculating a consistency index. (in and consistency ratio (in (For the preset average random consistency index), when At that time, the judgment matrix is ​​considered to have satisfactory consistency. After passing the consistency test, the eigenvectors are normalized. These are the weighting coefficients for each element in the difficulty rating.

[0099] It is understandable that the weight coefficients of the difficulty score can also be iteratively optimized based on a large number of simulation experiments or actual operation data through manual trial and error or machine learning methods to adapt to the needs of specific robot models or specific application scenarios (such as high-precision docking scenarios or narrow corner areas), and all of these should be included within the scope of protection of this invention.

[0100] Furthermore, considering that the calculation of the difficulty score involves multiple normalization parameters, the calibration method is crucial to the effectiveness of the dynamic cost refeeding mechanism of this invention. These normalization parameters include: trajectory cost reference value. Maximum number of iterations Attention Distance Minimum safe distance and the maximum acceptable speed variance threshold .

[0101] Among them, minimum safe distance A minimum safe distance threshold is defined between the robot and obstacles. This threshold is set when the trajectory planned by the TEB algorithm is at the minimum distance from the nearest obstacle. Less than or equal to At that time, the minimum distance between the normalized local optimal trajectory and the obstacle. It is calibrated to a maximum value of 1.0; at the minimum safe distance During calibration, physical constraints must be considered, meaning the calibrated minimum safe distance must be greater than the robot's physical contour dimensions, such as the radius of the robot's envelope circle. Furthermore, the superposition of error redundancy must be considered. That is, based on physical constraints, system errors must be taken into account, including the measurement errors of robot sensors (such as the 2D LiDAR in this embodiment). Trajectory tracking error with the robot's underlying controller (For example, caused by servo latency or wheel slippage), therefore, in some embodiments of the present invention, a minimum safe distance is required. The final calibration value is calculated and set using the following formula:

[0102] ;

[0103] In the formula, Indicates the minimum safe distance. This represents the radius of the robot's envelope circle. This indicates the measurement error of the robot's sensors. This indicates the trajectory tracking error of the robot's underlying controller.

[0104] It should be noted that the minimum safe distance After calibration, a passage test was conducted in a real narrow passage (such as a door frame) to verify that the robot can pass stably at the safe distance and will not trigger a collision due to minor control jitter, while ensuring... The rating can sensitively reflect the danger of nearby obstacles.

[0105] Focus distance An upper bound is defined on the distance at which the robot begins to focus on the obstacle and calculate the difficulty of passage. Greater than or equal to At that time, normalized obstacle distance score It was labeled as 0.0; at the distance of interest When calibrating, the relevant local planning horizon must be taken into account, i.e., the distance of concern. The value of should match the local planning horizon of the TEB algorithm (i.e., the length of the intercepted local reference path). If the obstacle is within the scope of the TEB algorithm, it should be included in the difficulty score calculation. Empirical optimization should also be considered, i.e., if distance is the focus... If the value is too small, the robot will be "short-sighted," accumulating difficulty only when very close to obstacles, which is not conducive to avoiding narrow areas in advance. If the value is too large, the robot will be "oversensitive," accumulating unnecessary dynamic cost value even in wide areas due to distant obstacles. Therefore, in some embodiments of the present invention, the attention distance is 1.0 to 1.5 times the length of the local planning path of the Local Path Planning Algorithm (TEB algorithm), or 30% to 50% of the effective detection distance of the robot's main sensor (such as LiDAR), and the optimal value is determined through simulation and field testing.

[0106] Maximum number of iterations It is the number of optimization iterations of the TEB algorithm within a single planning cycle. The normalized reference value is used to quantify the computational difficulty of TEB solvers (such as g2o solvers); in some embodiments of the present invention, the maximum number of iterations... The maximum number of iterations that the solver of the preset local path planning algorithm can achieve within the preset planning period is 80% to 90% when performing robot local path planning and navigation in the preset second test scenario.

[0107] It should be noted that, regarding the maximum number of iterations... During calibration, the specific steps include: First, determining the planning period: First, determining the planning period of the local path planning algorithm, for example, 100ms (i.e., 10Hz); Next, conducting stress tests: Running robot navigation in multiple known complex and narrow test scenarios (e.g., sharp turns, U-turns, areas with dense obstacles, i.e., a preset second test scenario), and collecting data during the test: Recording the reference maximum number of iterations that the preset local path planning algorithm solver can achieve while ensuring no timeout (i.e., completing the calculation within the 100ms planning period); Finally, parameter tuning: Maximum number of iterations. Set to 80% to 90% of the maximum reference number of iterations observed in the stress tests described above. This calibration ensures that when Exceeding this threshold indicates that the solver is approaching its real-time limit, the planning computation complexity in this region is high, and the difficulty score is [not specified]. Consequently, it increased significantly.

[0108] Trajectory cost reference value It is the cost of the locally optimal trajectory output by the TEB algorithm. The normalized reference value, It is the TEB multi-objective weighted optimization function The calculation results comprehensively reflect the costs associated with time, obstacles, and velocity / acceleration constraints; in some embodiments of this invention, the trajectory cost reference value... This represents the average or 90th percentile cost of achieving the local optimal trajectory when performing local path planning and navigation for the robot in the preset third test scenario.

[0109] It should be noted that, regarding the reference value of trajectory cost During calibration, the specific steps include: designing baseline scenarios: designing standard test scenarios, such as "Scenario A" (straight-line driving in open terrain, a low-cost scenario) and "Scenario B" (low-speed driving in a narrow passage that is just passable, a high-cost scenario, i.e., a pre-set third test scenario); data acquisition: running the robot through "Scenario B" (high-cost scenario) several times, recording the output of the TEB algorithm during these runs. The average or 90th percentile value; final parameter tuning: set this statistic to This calibration ensures that the normalized score is only calculated when the overall cost of the trajectory reaches a preset "difficulty" level. Only then does it approach 1.0, thus accurately quantifying the difficulty of traversing the trajectory itself.

[0110] Maximum acceptable speed variance threshold It is the variance of all linear velocities on the local trajectory. The normalized reference value is used to quantify the "smoothness" of the trajectory and to identify the "trajectory oscillation and repeated advance and retreat" phenomenon mentioned in the background art. In some embodiments of the present invention, the maximum acceptable velocity variance threshold is the average or median of the linear velocity variance on the local optimal trajectory when performing robot local path planning and navigation in a preset fourth test scenario. The preset fourth scenario is a narrow doorway or facing a suddenly appearing dynamic obstacle.

[0111] It should be noted that, regarding the maximum acceptable speed variance threshold During calibration, the specific steps include: reproducing the problem scenario: constructing a specific scenario that easily causes the robot to "oscillate" or "hesitate" (e.g., in front of a narrow doorway or when facing a suddenly appearing dynamic obstacle, i.e., the preset fourth test scenario); data acquisition: in this scenario, when the robot exhibits obvious "repeated forward and backward" or "oscillating" behavior with drastic speed fluctuations, collecting the variance of the linear velocity on the locally optimal path output by the TEB algorithm. Parameter tuning: The collected data... The mean or median is set as This calibration ensures that when the robot moves smoothly ( When the robot exhibits "shock" (smaller), the score is close to 0; while when the robot exhibits "shock" (smaller), the score is close to 0. (The number of cases increased dramatically), and the score approached 1.0, thus injecting this experience of "difficulty in getting around" into the dynamic cost map through a dynamic cost-reinforcing mechanism.

[0112] In some embodiments of the present invention, the local optimal trajectory includes a local optimal path. The pose coordinates of the local optimal path are converted to grid coordinates on the global cost map to form the influence area. Then, the dynamic cost map is updated according to the following formula:

[0113] ;

[0114] ;

[0115] In the formula, Represents the grid coordinates of points on the dynamic cost map. Updated dynamic cost, Represents the grid coordinates of points on the dynamic cost map. The dynamic cost before the update Represents the dynamic cost of a locally optimal trajectory. Indicates the difficulty level rating. This indicates the upper limit of the dynamic cost of a single injection. Indicates the sensitivity factor. Indicates the attenuation factor. Represents the grid coordinates of points on the static cost map. The cost.

[0116] In some embodiments of the present invention, such as Figure 4 As shown, the upper limit of dynamic cost per injection, sensitivity factor, and decay factor are calibrated using the following steps:

[0117] S401. In the preset fifth test scenario, the sensitivity factor and attenuation factor are fixed to their corresponding initial values. The upper limit of the dynamic cost of a single injection is adjusted. Robot path planning and navigation are performed so that the number of iterations in which the robot first stably avoids the first preset area in the fifth test scenario during global path planning is stable within the preset iteration range, and the calibration value of the upper limit of the dynamic cost of a single injection is obtained.

[0118] It should be noted that there is a maximum dynamic cost limit for a single injection. This parameter controls the maximum penalty value injected into the dynamic cost map when local path planning is difficult in a single attempt. This parameter directly affects the robot's "learning speed" and "memory strength" when avoiding difficult areas; it also controls the upper limit of the dynamic cost injected in a single attempt. The calibration employs the standard difficult scenario convergence analysis method. Specific steps include: constructing standard difficult scenarios: in a simulation environment or a controlled real environment, setting one or more standardized "static difficult" scenarios (e.g., a narrow S-shaped passage, a doorway requiring repeated posture adjustments to pass through, i.e., the fifth test scenario); setting evaluation metrics, such as learning efficiency (…). The robot repeatedly performs the same navigation task (e.g., traversing a difficult scenario 50 times). The algorithm begins to stably avoid the difficult region (i.e., the first preset region) during the Nth planning iteration. The smaller N is, the faster the learning speed and the better the path stability. This is achieved by observing whether the robot exhibits any issues during the learning process. Excessive risk leading to "over-avoidance" (e.g., choosing an extremely long detour to avoid minor difficulties); controlled variable experiment: fixed (Suggested initial value: 1.0) and (Suggested initial value: 0.95), select one group Candidate values ​​(e.g., 10, 30, 50, 80, 100), using each Run repeated navigation experiments, record evaluation metrics; analysis and decision-making: Too low: This results in an excessively large N value, leading to low learning efficiency and failing to demonstrate the advantage of "actively avoiding historically difficult areas." Too high: This results in an excessively small N value (e.g., N=1), leading to overly aggressive learning. The robot might permanently "blacklist" a usable path due to a single unsuccessful TEB planning attempt (e.g., sensor noise), resulting in poor path stability. Ideal value: Choose a value that keeps N stable within a reasonable range (e.g., N=3-5 times). The goal is to achieve a balance between "learning" and "stability".

[0119] S402. In the preset sixth test scenario, the upper limit of the dynamic cost of a single injection is fixed to the corresponding calibration value, the attenuation factor is fixed to the corresponding initial value, the sensitivity factor is adjusted, and robot path planning and navigation are performed so that the robot actively avoids the second preset area in the sixth test scenario where the difficulty score is higher than the threshold, and does not avoid the third preset area where the difficulty score is lower than the threshold, thereby obtaining the calibration value of the sensitivity factor.

[0120] It should be noted that the sensitivity factor The dynamic cost calculation formula for a locally optimal trajectory The value of is used as an index to adjust the dynamic cost of local optimal trajectories. Difficulty rating The nonlinear response; the sensitivity factor calibration adopts the multi-difficulty gradient scenario comparison method, the specific steps of which include: constructing multi-difficulty scenarios: designing a test environment containing multiple different passage difficulties (i.e., the sixth test scenario), including area A (low difficulty): a slightly narrow straight passage (estimated difficulty score) Area B (High Difficulty): Extremely narrow corners with obstacles (estimated difficulty score below the threshold). (Difficulty score exceeds threshold); Set evaluation metric: Cost discrimination: After the robot passes through multiple times, the dynamic cost map In the study, the cost difference between region A and region B; path selection preference: observation. The algorithm's global planning result is either to avoid only B, or to avoid both A and B simultaneously; Controlled variable experiment: fixed (Using calibration values) and Select a group Candidate values ​​(e.g., 0.5, 1.0, 2.0); Analysis and decision-making: Improved the low The penalty weight of the value will cause the robot to be oversensitive to area A (low difficulty), which may lead to unnecessary avoidance; Linear relationship and Proportional; (Preferred) Increased the height The penalty weight of the value simultaneously suppresses low The penalty value allows the system to "tolerate" low-difficulty areas (Area A) but "severely punish" high-difficulty areas (Area B); Ideal value: To achieve the goal of "actively avoiding historically difficult areas" in the patent, especially for "complex and narrow environments", one should be selected; The value (e.g., 1.5 or 2.0) is used to enable intelligent differentiation of areas of different difficulty.

[0121] S403. Fix the upper limit of dynamic cost per injection and sensitivity factor to the corresponding calibration values, adjust the attenuation factor, set temporary obstacles on the robot's path in the preset seventh test scenario to perform robot path planning and navigation, obtain the learning time for the robot to bypass the temporary obstacles, remove the temporary obstacles in the preset seventh test scenario to perform robot path planning and navigation, obtain the forgetting time for the robot to reselect the robot's path, so that the learning time and forgetting time are within the corresponding preset time range, and obtain the calibration value of the attenuation factor.

[0122] It should be noted that the attenuation factor In the dynamic cost update rule, controlling the "forgetting rate" or "decay rate" of the dynamic cost over time determines the persistence of "historical experience." It employs a dynamic environment adaptability testing method for calibration. The specific steps include: constructing a dynamically changing scenario: Stage 1 (learning) setting a temporary but challenging obstacle in the environment (e.g., placing a box on a necessary path); the robot traverses the area multiple times and "learns" the high dynamic cost of that area, then begins to detour; Stage 2 (forgetting): removing the temporary obstacle; setting evaluation metrics: adaptation time (…). ): From Phase 2 (obstacle removal) to the time or number of navigation attempts taken for the robot to "forget" the historical difficulty and reselect the optimal path; Controlled variable experiment: fixed and (Use the value specified in the preceding specification) For coefficients close to 1, select a set of candidate values ​​(e.g., 0.90, 0.95, 0.99, 0.999); Analysis and decision: Too low (e.g., 0.90): Forgetting is too fast. In stage 1, the experience that the robot has just learned decays quickly, which may cause it to repeatedly try when the obstacle is still there, reducing avoidance efficiency. Too high (e.g., 0.999 or 1.0): The memory is almost permanent. In stage 2, the robot cannot "forget" the removed obstacles and will forever avoid the restored path, violating the system's adaptability to dynamic environmental changes; Ideal value: The value should be matched with the update frequency of the cost map and the dynamic nature of the task. It should be selected to ensure stable memory in Phase 1 and "forget" old experiences within a reasonable time in Phase 2 (e.g., several task cycles). Value (e.g., 0.995).

[0123] In some embodiments of the present invention, such as Figure 5 As shown, the return to step S102 in step S104 includes:

[0124] S1041. Obtain the initial total cost of the global optimal path on the global cost map before the update, and the cumulative cost of the actual driving path in the global optimal path;

[0125] S1042. Calculate the new cost of the remaining paths in the global optimal path on the updated global cost map;

[0126] S1043. If the sum of the cumulative cost and the new cost is greater than the product of the preset sensitivity coefficient and the initial total cost, then return to step S102.

[0127] It should be noted that the calibration steps for the sensitivity coefficient include: constructing a standard test scenario: building one or more representative simulation or physical test environments, which should include the typical features targeted by this invention, such as narrow passages, U-shaped traps, dynamic pedestrian flow, or obstacle simulation areas; and setting a candidate value range: setting a series of candidate values ​​for the sensitivity coefficient based on experience. For example, testing can be conducted within a range of [1.05, 1.5]. The closer the sensitivity coefficient is to 1.0, the higher the sensitivity to cost changes and the lower the threshold for triggering replanning; the larger the sensitivity coefficient, the higher the tolerance. Navigation testing: In a standard test scenario, for each candidate sensitivity coefficient value, the robot performs multiple standard navigation tasks (e.g., from a fixed starting point to a fixed ending point). Statistical performance metrics: Record and statistically analyze the key performance metrics of the navigation task under different sensitivity coefficients, including but not limited to total task time, number of global replanning attempts, total path cost or smoothness, and number of local planning failures or dead time. Trade-off selection: Analyze the above performance metrics data and select a candidate sensitivity coefficient value that achieves the best trade-off between path optimality (able to avoid high-cost paths in a timely manner) and planning overhead (avoiding unnecessary frequent replanning), as the final calibration value of the sensitivity coefficient.

[0128] It should also be noted that the “planning cycle” of the Local Path Planning (TEB) algorithm is defined as the preset execution frequency of the TEB algorithm for updating the local path. This frequency is a configurable parameter of the robot system. In each planning cycle of the TEB algorithm, the cumulative cost of the robot’s actual travel path and the new cost of the remaining path are calculated and judged.

[0129] Furthermore, if the Local Path Planning (TEB) algorithm fails to find the local optimal trajectory within three consecutive planning cycles, it returns to step S102, the Global Path Planning (TBP) algorithm. The algorithm then searches the global cost map again to find a globally optimal path from the current location to the target point.

[0130] Compared with existing technologies, this invention introduces a dynamic cost refeeding mechanism, which updates the dynamic cost of the robot's execution of the local optimal trajectory to the dynamic cost map. This is deeply integrated with global path planning and local path optimization, enabling the robot to learn from experience and optimize itself. During the path planning process, the robot can actively avoid historically difficult areas, thereby improving the robot's navigation stability and long-term operating efficiency in complex and narrow environments.

[0131] like Figure 6 As shown, the present invention also provides an electronic device. This electronic device includes at least a processor 601 and a memory 602.

[0132] Processor 601 may include one or more processing cores, such as a quad-core processor or an octa-core processor. Processor 601 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 601 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 601 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 601 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0133] The memory 602 may include one or more computer-readable storage media, which may be non-transitory. The memory 602 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 602 are used to store at least one instruction, which is executed by the processor 601 to implement the robot path planning method provided in the method embodiments of this application.

[0134] In some embodiments, the electronic device may also optionally include a peripheral device interface and at least one peripheral device. The processor 601, memory 602, and peripheral device interface can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface via a bus, signal line, or circuit board. Indicatively, peripheral devices include, but are not limited to, radio frequency circuits, touch displays, audio circuits, and power supplies.

[0135] Of course, electronic devices may also include fewer or more components, and this embodiment does not limit this.

[0136] Accordingly, embodiments of the present invention also provide a computer-readable storage medium for storing computer-readable programs or instructions. When the programs or instructions are executed by a processor, they can implement the steps or functions of the robot path planning methods provided in the above-described method embodiments.

[0137] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0138] The robot path planning method provided by the present invention has been described in detail above. Specific examples have been used to illustrate the principle and implementation of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation and application scope based on the idea of ​​the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

[0139] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method of robot path planning, characterized by , comprising: S101, converting the acquired static grid map into a static cost map, initializing a dynamic cost map, merging the static cost map and the dynamic cost map to obtain a global cost map; S102, performing global path planning on the global cost map based on a preset global path planning algorithm to obtain a global optimal path from a current position point to a global target point; S103, performing local path planning based on a preset local path planning algorithm and the global optimal path to obtain a local optimal trajectory and its corresponding trajectory planning characteristic parameters, controlling the robot to execute the local optimal trajectory until the global target point is reached; S104, determining the dynamic cost of the local optimal trajectory based on the trajectory planning characteristic parameters, updating the dynamic cost map based on the dynamic cost of the local optimal trajectory, and further updating the global cost map, returning to step S102; The determination of the dynamic cost of the local optimal trajectory based on the trajectory planning characteristic parameters and the updating of the dynamic cost map based on the dynamic cost of the local optimal trajectory comprise: Calculating a difficulty score based on the trajectory planning characteristic parameters; Calculating the dynamic cost of the local optimal trajectory based on the difficulty score and updating the dynamic cost map based on the dynamic cost of the local optimal trajectory; Wherein, the trajectory planning characteristic parameters include the cost of the local optimal trajectory, the minimum distance between the local optimal trajectory and the obstacle, the number of optimization iterations of the local optimal trajectory, and the variance of all linear velocities on the local optimal trajectory, and the calculation formula of the difficulty score is: ; ; ; ; ; wherein, denotes the difficulty score, denotes the cost of the locally optimal trajectory, denotes the number of optimization iterations of the locally optimal trajectory, denotes the minimum distance of the locally optimal trajectory to the obstacles, denotes the variance of all linear velocities on the locally optimal trajectory, denotes the number of optimization iterations of the normalized locally optimal trajectory, denotes the minimum distance of the normalized locally optimal trajectory to the obstacles, denotes the cost of the normalized locally optimal trajectory, denotes the variance of all linear velocities on the normalized locally optimal trajectory, denotes the trajectory cost weight coefficient, denotes the trajectory iteration number weight coefficient, denotes the trajectory obstacle distance weight coefficient, denotes the trajectory linear velocity variance weight coefficient, denotes the trajectory cost reference value, denotes the maximum number of iterations, denotes the attention distance, denotes the minimum safety distance, denotes the maximum acceptable velocity variance threshold value; The dynamic cost map is updated according to the following formula: ; ; wherein, represents a dynamic cost of a local optimal trajectory, represents a difficulty score, represents an upper bound of a single injection dynamic cost, represents a sensitivity factor, represents a grid coordinate point on a dynamic cost map an updated dynamic cost, represents a grid coordinate point on a dynamic cost map a dynamic cost before update, represents a decay factor, represents a grid coordinate point on a static cost map a cost of. 2.The robot path planning method of claim 1, wherein The global path planning algorithm adopts A* algorithm, the local path planning algorithm adopts TEB algorithm, the local path planning algorithm performs local path planning through a multi-objective weighted optimization function, and the multi-objective weighted optimization function is: ; wherein denotes the trajectory to be optimized, denotes the cost of the trajectory to be optimized, denotes the time cost, denotes the obstacle cost, denotes the speed constraint cost, denotes the acceleration constraint cost, denotes the time weight coefficient, denotes the obstacle weight coefficient, denotes the speed constraint weight coefficient, denotes the acceleration constraint weight coefficient.

3. The robot path planning method of claim 2, wherein The time weight coefficient, the obstacle weight coefficient, the speed constraint weight coefficient and the acceleration constraint weight coefficient are calibrated by the following steps: In a preset first test scene, the time weight coefficient and the acceleration constraint weight coefficient are fixed as the corresponding initial weight coefficients, the obstacle weight coefficient and the speed constraint weight coefficient are adjusted for path planning and navigation, so that the task completion rate parameter meets the preset requirements, the minimum distance between the robot and the obstacle is maximized, and the speed tracking error parameter is minimized, to obtain the calibration values of the obstacle weight coefficient and the speed constraint weight coefficient; In a preset first test scene, the obstacle weight coefficient and the speed constraint weight coefficient are fixed as the corresponding calibration values, the time weight coefficient is fixed as the corresponding initial weight coefficient, and the acceleration constraint weight coefficient is adjusted for path planning and navigation, so that the task completion rate parameter, the minimum distance between the robot and the obstacle, the speed tracking error parameter and the response speed parameter all meet the corresponding preset requirements, and the path smoothness and mechanical jitter degree parameters are minimized to obtain the calibration value of the acceleration constraint weight coefficient. In a preset first test scene, the obstacle weight coefficient, the speed constraint weight coefficient and the acceleration constraint weight coefficient are fixed as corresponding calibration values, the time weight coefficient is adjusted for path planning and navigation, so that the task completion rate parameter, the minimum distance between the robot and the obstacle parameter, the speed tracking error parameter, the response speed parameter, the path smoothness and the mechanical jitter degree parameter meet the corresponding preset requirements, and the total travel time parameter is minimized to obtain the calibration value of the time weight coefficient. 4.The robot path planning method of claim 1, wherein The trajectory cost weight coefficient, the trajectory iteration number weight coefficient, the trajectory obstacle distance weight coefficient and the trajectory linear velocity variance weight coefficient are calibrated by the following steps: Taking the difficulty score as a target layer, taking the cost of the normalized local optimal trajectory, the optimization iteration number of the normalized local optimal trajectory, the minimum distance between the normalized local optimal trajectory and the obstacle, and the variance of all linear velocities on the normalized local optimal trajectory as a criterion layer, a hierarchical structure model is constructed; The four indexes in the criterion layer are compared with each other, the relative importance is determined by comparing the safety, stability, calculation overhead and path economy, a judgment matrix is constructed, the maximum eigenvalue of the judgment matrix and the corresponding normalized eigenvector are calculated, the priority of the safety is higher than that of the stability, the priority of the stability is higher than that of the calculation overhead, the priority of the calculation overhead is higher than that of the path economy; Based on the maximum eigenvalue, a consistency index is calculated, the judgment matrix is tested for consistency based on the consistency index, and the normalized eigenvector of the judgment matrix that passes the consistency test is taken as the trajectory cost weight coefficient, the trajectory iteration number weight coefficient, the trajectory obstacle distance weight coefficient and the trajectory linear velocity variance weight coefficient.

5. The robotic path planning method of claim 1, wherein The single injection dynamic cost upper limit, the sensitivity factor and the attenuation factor are calibrated by the following steps: In a preset fifth test scene, the sensitivity factor and the attenuation factor are fixed as corresponding initial values, the single injection dynamic cost upper limit is adjusted, the robot path planning and navigation are performed, so that the iteration number of the robot for the first time to start to stably avoid the first preset area in the fifth test scene is stabilized within a preset iteration range, and the calibration value of the single injection dynamic cost upper limit is obtained; In a preset sixth test scene, the single injection dynamic cost upper limit is fixed as a corresponding calibration value, the attenuation factor is fixed as a corresponding initial value, the sensitivity factor is adjusted, the robot path planning and navigation are performed, so that the robot actively avoids the second preset area in the sixth test scene whose difficulty score is higher than a threshold value, and does not avoid the third preset area whose difficulty score is lower than the threshold value, and the calibration value of the sensitivity factor is obtained. The single-injection dynamic cost upper limit and the sensitivity factor are fixed as corresponding calibration values, the attenuation factor is adjusted, temporary obstacles are set on a robot passing path in a preset seventh test scene to perform robot path planning and navigation, learning time of the robot to bypass the temporary obstacles is obtained, the temporary obstacles are removed in the preset seventh test scene to perform robot path planning and navigation, forgetting time of the robot to select the robot passing path again is obtained, so that the learning time and the forgetting time are within corresponding preset time ranges, and a calibration value of the attenuation factor is obtained.

6. The robotic path planning method of claim 1, wherein Returning to step S102 includes: obtaining an initial total cost of the global optimal path on a global cost map before updating, and a cumulative cost of an actually traveled path in the global optimal path; calculating a new cost of a remaining path in the global optimal path on the global cost map after updating; if a sum of the cumulative cost and the new cost is greater than a product of a preset sensitivity coefficient and the initial total cost, returning to step S102.

7. An electronic device, comprising comprising a memory and a processor; the memory is configured to store a program; the processor is coupled to the memory and is configured to execute the program stored in the memory to implement steps of the robot path planning method in any one of claims 1 to 6.

8. A computer readable storage medium, characterized in that The readable storage medium has a program or instruction stored thereon, and the program or instruction is executed by the processor to implement steps of the robot path planning method in any one of claims 1 to 6.

Images