Intelligent path planning method for four-direction shuttle robot

Abstract

The invention belongs to the technical field of path planning, and particularly relates to an intelligent path planning method for a four-way shuttling robot, which comprises the following steps of: generating an initial path by adopting a JPS (JavaScript Pattern Scheduling) algorithm and extracting key anchor points; the system responds through an innovative hierarchical decision-making mechanism: firstly, the stability of anchor points behind conflict points is evaluated, and if the stability is high, a minimum repair window is adopted; and if the stability is uncertain or low, topological influence depth verification is started to dynamically define an optimal local repair window, finally, local path replanning is performed in the window, and a generated new path section is seamlessly spliced with an original path. According to the method, efficient and low-overhead path updating in a dynamic environment is realized through a self-adaptive local repair strategy, and the stability and efficiency of robot operation are ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of path planning. More particularly, the present application relates to a four-way shuttle robot intelligent path planning method. BACKGROUND

[0002] The four-way shuttle robot is the core execution unit of the modern intensive warehouse system, and its running efficiency is directly related to the throughput capacity and response speed of the entire logistics system. Path planning, as the brain of the robot, its core task is to quickly and accurately calculate an optimal or suboptimal path from the starting position to the target position in a complex warehouse grid environment.

[0003] In actual warehouse operation scenarios, the environment is not constant. In addition to static layouts such as shelves and pillars, there are also temporary parked equipment, malfunctioning other robots, or temporarily stacked goods and other dynamic obstacles. These sudden situations can make the previously planned global optimal path infeasible, at which point the robot must be able to intelligently adjust its route to bypass the obstacles. This puts a very high requirement on the dynamic adaptability of the path planning algorithm.

[0004] Currently, the common technical means to solve such problems is to use path planning algorithms based on graph search, such as the classic A-Star algorithm or its efficient improved version on the grid map, i.e., the JPS (Jump Point Search) algorithm. This kind of algorithm can efficiently calculate a global optimal path after a static map is given.

[0005] However, when the path encounters a dynamic obstacle during execution, the most direct response of the existing technology is to trigger a complete path re-planning, i.e., to recalculate a brand new path from the current position of the robot to the end point. This complete re-planning strategy has significant defects: first, the global search calculation overhead is huge, which can cause the robot to stop waiting for a long time, seriously affecting the operation efficiency; second, the newly generated path may differ greatly in structure from the original path, even if it is only to avoid a small local obstacle, it may cause the path to shake violently, which destroys the stability and predictability of the path, and adversely affects the collaborative scheduling and smooth operation of the entire multi-robot system. SUMMARY

[0006] To solve the technical problems in the prior art that when a robot encounters a dynamic obstacle, either global path re-planning leads to large amount of calculation and long robot pause time, or a fixed repair region leads to low repair success rate or insufficient efficiency, the present application provides a four-way shuttle robot intelligent path planning method, comprising: obtaining a rasterized map containing a static environment layout; based on the map, using a JPS algorithm to calculate an initial optimal path from a starting position to a target position, and extracting a plurality of jump points, the starting position and the target position in the initial optimal path as an ordered path anchor point sequence; during robot travel along the initial optimal path, in response to detecting a dynamic obstacle, determining whether the obstacle conflicts with the initial optimal path; if there is a conflict, performing stability evaluation on a first anchor point after the conflict point to obtain a stability evaluation index, the stability evaluation index being proportional to the distance from the first anchor point to the obstacle, inversely proportional to the distance from the first anchor point to the current position of the robot, and increasing with the position of the first anchor point in the remaining path; making a hierarchical decision based on the comparison result of the stability evaluation index and a preset threshold to define a repair window containing the conflict point, the boundary of the repair window being determined by two anchor points in the path anchor point sequence; performing local path search in the repair window to generate an optimal local repair path that bypasses the obstacle; and splicing the optimal local repair path with the unaffected path segment in the initial optimal path to form a complete new path.

[0007] The present application reduces the calculation complexity and time consumption of the algorithm by pre-extracting path anchor points and performing multi-dimensional stability evaluation on the first anchor point after the conflict, dynamically adjusting the repair window, and reducing the path re-planning range from the entire map to the local area affected by the obstacle, thereby avoiding complete recalculation of the entire path, especially avoiding repeated search of a large number of still valid path segments in the path, and enabling faster response to dynamic changes in the environment.

[0008] Further, the anchor point stability evaluation index designed by the present application can dynamically determine the influence range of the obstacle, define the repair region, so that path repair is only performed locally, the newly generated path maintains maximum consistency with the original path, effectively avoids the problem of path dramatic fluctuation caused by global recalculation, makes the robot running trajectory smoother and more predictable, reduces the chain interference caused by single path dramatic change on other robots in a high-density multi-robot collaborative work scenario, and improves the running stability and overall work efficiency of the entire warehouse system; at the same time, the inherent fast advantage of the JPS algorithm is combined with the idea of incremental repair, so that the path planning system can quickly respond and make high-quality and low-impact decisions when facing sudden failures or obstacles, significantly enhancing the robustness and fault tolerance of the entire automated warehouse system.

[0009] Preferably, determining that the obstacle conflicts with the initial optimal path includes: assuming the robot's current position coordinates are... The paths that have not been traversed are those from the initial optimal path. Sub-path to target location; check obstacle coordinates Is it located on the untraveled sub-path? If If the conflict exists on the sub-path, a path conflict is determined, and the distance on the path is recorded. The system identifies the nearest conflict point and locates the anchor point interval containing the conflict point within the path anchor point sequence. .

[0010] Preferably, a stability assessment is performed on the first anchor point after the conflict point to obtain its stability assessment index, including: As the first anchor point after the conflict point, its stability assessment index The formula for calculation is: In the formula, The Manhattan distance between the two points; The coordinates of the dynamic obstacle; These are the robot's current position coordinates; It is the last effective anchor point before the conflict occurs; From the anchor point From the initial optimal path to the anchor point Path length; From the anchor point From the initial optimal path to the destination The total remaining path length.

[0011] This invention comprehensively considers three dimensions—the distance between the anchor point and the obstacle, the distance to the robot's current position, and the relative position in the remaining path—to calculate the anchor point stability evaluation index. This makes the judgment of anchor point stability more accurate and comprehensive, providing a data foundation for the reliability of subsequent hierarchical decision-making and avoiding repair failures or inefficiencies caused by misjudgments based on a single dimension.

[0012] Preferably, the preset threshold includes a high stability threshold. and low stability threshold ,and .

[0013] Preferably, a hierarchical decision is made based on the comparison result between the stability evaluation index and the preset threshold, defining a repair window that includes the conflict point, including: if the anchor point Stability assessment indicators Then repair the starting anchor point of the window. End point anchor If , the system initiates a topological influence depth verification to determine the repair window.

[0014] Based on the set double threshold, the invention constructs a hierarchical decision-making process: for anchor points with extremely high stability, the smallest repair window is adopted to pursue the highest efficiency; for uncertain stability, more in-depth verification is initiated; this hierarchical processing mechanism avoids the one-size-fits-all approach for all conflicts, significantly improving the comprehensive efficiency and intelligent level of the system in dealing with dynamic obstacles of different complexities.

[0015] Preferably, the initiation of topological influence depth verification to determine the repair window includes: Starting from , a bounded breadth-first search is performed: if a path to the exploration endpoint can be found in the bounded breadth-first search, the start anchor point of the repair window and the end anchor point ; if the path to cannot be found within the limited range, the window range needs to be expanded: keep the start anchor point of the repair window unchanged, and sequentially extend the exploration endpoint to the next anchor point , repeat the stability evaluation, and make hierarchical decisions based on the comparison results of the stability evaluation indicators and the preset threshold until the first anchor point that can be connected by is found , then the end anchor point of the repair window is .

[0016] The invention initiates a topological influence depth verification mechanism when the stability of the anchor point is uncertain: when simple geometric evaluation is not enough to judge, this method detects the actual path connectivity through bounded breadth-first search, and can dynamically expand the repair window when necessary, solving the problem that the existing technology may fall into a topological trap where the seemingly remote but actually necessary path is blocked, greatly improving the success rate and robustness of path repair in complex blocking scenarios.

[0017] Preferably, when performing the bounded breadth-first search, the search range is limited to a circular area with a Manhattan distance between and as the radius.

[0018] The invention limits the range of breadth-first search, by limiting the search area to a circular area with Manhattan distance as the radius, effectively controlling the computational complexity of the topological verification process. This ensures the effectiveness of the verification while avoiding the explosive increase in computational complexity caused by unlimited expansion of the search range, achieving a balance between higher success rate and computational efficiency.

[0019] Preferably, the local path search performed within the repair window comprises: taking the start point of the local search as the end point of the local search, and calculating an optimal local repair path from to that can bypass the dynamic obstacle . .

[0020] Preferably, the new path is composed of three parts: a sub-path segment from the start point of the original path to the start point of the repair , the newly generated optimal local repair path , and a sub-path segment from the end point of the repair to the end point of the original path .

[0021] Preferably, the jump points include corner points and / or obstacle-adjacent points in the initial optimal path.

[0022] The present application has the following advantages: The present application extracts path anchor points in advance and performs multi-dimensional stability evaluation on the first anchor point after the conflict, dynamically adjusts the repair window, and reduces the range of path re-planning from the entire map to the local area affected by the obstacle, thereby avoiding complete recalculation of the entire path and repeated search of a large number of still valid path segments in the path, thereby greatly reducing the computational complexity and time consumption of the algorithm and enabling faster response to dynamic changes in the environment.

[0023] Further, the anchor point stability evaluation index designed by the present application can dynamically determine the influence range of the obstacle, define the repair area, so that the path repair is only performed locally, the newly generated path maintains the maximum consistency with the original path, effectively avoids the problem of path dramatic fluctuation caused by global recalculation, makes the running trajectory of the robot smoother and more predictable, reduces the chain interference caused by the dramatic change of the single path to other robots in the high-density multi-robot collaborative work scene, and improves the running stability and overall work efficiency of the entire warehouse system; at the same time, the inherent fast advantage of the JPS algorithm is combined with the idea of incremental repair, so that the path planning system can quickly respond and make high-quality and low-impact decisions when facing sudden failures or obstacles, thereby significantly enhancing the robustness and fault tolerance of the entire automated warehouse system. BRIEF DESCRIPTION OF DRAWINGS

[0024] ​​​Figure 1 This is a flowchart illustrating an intelligent path planning method for a four-way shuttle robot according to the present invention; Figure 2 This is a flowchart illustrating step S3; Figure 3 It is a schematic map showing the warehouse information; Figure 4 It is a schematic diagram showing the initial optimal path; Figure 5 This is a schematic diagram illustrating the planning of a new path for local path repair using the method of the present invention; Figure 6 It is a schematic diagram showing the planning of a completely new path recalculated using existing technology. Detailed Implementation

[0025] 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 some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0027] This invention discloses an intelligent path planning method for a four-way shuttle robot, referring to... Figure 1 This includes steps S1 to S4: S1: Generate the initial path and extract the path anchors.

[0028] It should be noted that in order to perform local and incremental repairs when path conflicts occur, rather than recalculating globally, the initially generated complete path first needs to be structured to extract the key nodes that can represent the path skeleton, i.e., path anchor points.

[0029] Specifically, the system acquires the gridded map information of the warehouse and the starting position coordinates of the four-way shuttle robot. and the coordinates of the mission target The map information includes static environmental layouts such as shelves and aisles.

[0030] Furthermore, the system executes the standard JPS algorithm once to calculate a route from... arrive Initial optimal path The path consists of a series of continuous grid coordinate points.

[0031] Furthermore, to facilitate subsequent local repairs, starting from the initial optimal path... The algorithm identifies all jump points, which are key decision points identified by the JPS algorithm during the search process, including but not limited to path corners and obstacle proximity points.

[0032] Finally, list all jump points and the starting points of the paths. and the end point Combined, they form an ordered sequence of path anchor points. ,in and .

[0033] S2: Perform dynamic obstacle conflict detection.

[0034] It should be noted that during the robot's movement, environmental changes must be monitored in real time. Once a dynamic obstacle appears, it should be immediately determined whether it poses a threat to the current planned path. This is a prerequisite for activating the path repair mechanism.

[0035] Specifically, as the robot follows the initial optimal path During the journey, the system monitors the warehouse environment in real time: when it receives information about dynamic obstacles, such as a malfunctioning robot reporting its location coordinates... When an obstacle appears, the system immediately determines whether it conflicts with the currently planned path, including: Let the robot's current position coordinates be... The path that has not been traversed is the initial optimal path. Zhong Cong arrive Sub-paths; check obstacle coordinates Is it located on the untraveled sub-path? If If the conflict exists on the sub-path, a path conflict is determined, and the distance on the path is recorded. Recent points of conflict Meanwhile, the system in the path anchor point sequence Locating the point of conflict The anchor point range .

[0036] S3: In response to the detection of a dynamic obstacle that conflicts with the initial optimal path, a stability assessment is performed on the first anchor point after the conflict point. Based on the comparison results of the stability assessment index and the preset threshold, a graded decision is made to define the repair window.

[0037] It should be noted that in order to guarantee the success rate of repair while minimizing the computational overhead, a fixed size of the repair window cannot be used, and the window range should be adaptively determined according to the actual degree of influence of the obstacle, therefore, this step achieves this goal through a hierarchical process combining low-overhead geometric evaluation and high-precision topological verification.

[0038] The flowchart of step S3 refers to Figure 2 , including steps S301 to S303, specifically: S301: Stability evaluation is performed on the first anchor point after the conflict point.

[0039] It should be noted that when determining the boundary of the repair window, a key problem is to determine which anchor point after the conflict point is stable and not affected by the obstacle, which can be used as a reliable repair endpoint. The stability of an anchor point is related not only to its physical distance from the obstacle, but also to its importance and position in future path planning; therefore, constructing a comprehensive evaluation index is a prerequisite for scientifically defining the window.

[0040] Specifically, the system performs stability evaluation on the first anchor point after the conflict point , and the stability evaluation index of the anchor point is calculated by the following formula:

[0041] In the formula, is the stability evaluation index of the anchor point; is the Manhattan distance between two points, which reflects the actual travel distance in the grid map; is the position coordinate of the dynamic obstacle; is the current position coordinate of the robot; is the last valid anchor point before the conflict occurs; is the path length from the anchor point to the anchor point along the initial optimal path; is the total remaining path length from the anchor point to the end point along the initial optimal path.

[0042] Wherein, the first term of the calculation formula measures the relative influence of the obstacle on the anchor point relative to the current position of the robot; the second term of the calculation formula is a weighting factor, which makes the later anchor point have a higher stability weight; therefore, the calculation formula combines the two dimensions of distance and path position: when the anchor point is far away from the obstacle​ the farther, or the distance from the current robot position the closer, the ratio of the first term increases, while the second term the later the position in the remaining path, the larger the logarithm value of the second term; the two together make the value of the larger, the more stable the anchor point is, and the less likely it is to be affected by this dynamic obstacle.

[0043] It should be noted that this index can quickly evaluate the degree of influence of the anchor point, providing data basis for subsequent grading decisions, avoiding the one-sidedness of judging only by a single distance.

[0044] S302: Make a grading decision according to the stability evaluation result.

[0045] It should be noted that in order to balance the decision efficiency and accuracy, different processing strategies are adopted for anchor points with different stabilities. For the case of extreme stability, the smallest window is directly used to pursue the highest efficiency; for the uncertain case, it is transferred to a more accurate but higher overhead verification process.

[0046] Specifically, a high stability threshold and a low stability threshold are preset, and the high stability threshold and the low stability threshold serve to divide the decision area, so in this embodiment, is set to 0.8, and is set to 0.3. Such a setting makes the system tend to classify it as a high stability area when the relative distance between the obstacle and the anchor point is more than 4 to 5 times the relative distance between the robot and the anchor point; and when the distance between the two is close or smaller, it tends to classify it as an unstable area, thereby starting a more in-depth topological verification, achieving a balance between efficiency and decision reliability; in other embodiments, the implementer can adjust these two thresholds according to the complexity of the warehouse layout, the density of the robot, and other actual situations.

[0047] Further, according to the size relationship between the stability evaluation index of the anchor point and the threshold, the grading decision is made in three cases: Case 1: If the stability evaluation index of the anchor point , the system determines that the anchor point is hardly affected by the obstacle, and its geometric position is very safe, without the need to start a more complex topological analysis, the system directly determines the repair window to be the smallest range, then the start anchor point of the repair window is the anchor point The method constructs a fast channel and can handle most simple local obstacles with the highest efficiency.

[0048] Case two: if , it indicates that the stability evaluation result of the anchor point is in the gray zone, and the anchor point has uncertainty in stability; at this time, the simple geometric distance is not enough to make a reliable judgment, and there may be a topological trap that seems remote but must be passed through, so the system must start the topological impact depth verification to determine the repair window.

[0049] Case three: if , it indicates that the anchor point is very unstable from a geometric point of view; at this time, the system also needs to start the topological impact depth verification to determine the repair window to find the truly stable boundary.

[0050] S303: In response to uncertainty or low stability, start topological impact depth verification to define the repair window.

[0051] It should be noted that when geometric evaluation cannot give a definite conclusion, the actual connectivity of the map, i.e., the topological structure, must be considered to judge the real impact range caused by the obstacle. This verification can avoid being misled by the appearance of geometric distance, such as the case of a narrow channel that seems remote but must be passed through being blocked.

[0052] Specifically, when entering case two or case three, take as the starting point and as the first exploration endpoint, perform a bounded breadth-first search to try to find a path to the current exploration endpoint anchor point, and the search range is limited to a small area, i.e., a circular area with a Manhattan distance between and as the radius, to strictly limit the amount of calculation.

[0053] Optionally, if a path to the exploration endpoint can be quickly found in the bounded breadth-first search, it indicates that the obstacle only causes local detours and does not damage the key topological structure; at this time, the system sets the repair window to the minimum range, and the starting point anchor point and the endpoint anchor point of the repair window.

[0054] Optionally, if a path to cannot be found within the limited range in the bounded breadth-first search, it indicates that the obstacle blocks and The necessary passage between them creates a local topological bottleneck; at this point, the system determines that the obstacle has a significant impact, requiring an expansion of the window range: maintaining the starting anchor point of the repair window. for The exploration endpoint will remain unchanged, and will be moved forward to the next anchor point. The stability assessment is repeated, and a tiered decision is made based on the comparison between the stability assessment index and the preset threshold, until the first one that can be [performed / resolved] is found. Connected anchor points The anchor point It is then ultimately determined as the endpoint anchor point of the repair window. This ensures that the endpoint of the repair window is located in an open area outside the actual topological influence range of the obstacle, thereby guaranteeing the success rate and path quality of the local JPS search.

[0055] It should be noted that, in this way, the size of the repair window no longer depends on a potentially inaccurate distance calculation formula, but is dynamically determined by the degree to which obstacles disrupt the actual connectivity of the map, ensuring that the boundaries of the repair window are reliable in complex situations.

[0056] S4: Perform a local path search within the repair window to generate the optimal local repair path, and then merge it with the unaffected path segments in the initial optimal path to form a complete new path.

[0057] It should be noted that once a reliable repair boundary is determined, efficient path searching can be performed within the restricted area, and the conflicting parts of the original path can be replaced with the newly generated local path, thereby completing the entire repair process.

[0058] First, within the defined repair window, the system performs a local JPS path search: As the starting point for local search, with As the endpoint of the local search, after updating the dynamic obstacles... On the map copy, calculate a route from arrive And it can bypass obstacles Optimal local repair path .

[0059] Then, the newly generated optimal local repair path Seamlessly splice it with the stable path segments preserved in the original path to form a complete and restored new path. New Path It consists of three parts: the original path from the starting point To the starting point of repair sub-path segments The newly generated optimal local repair path , and the sub-path segment from the repair end point to the end point in the original path . .

[0060] Finally, the system issues the new path to the four-way shuttle robot for execution.

[0061] It should be noted that since the new path only changes in the local area, it maintains high consistency with the main structure of the original path, thereby avoiding drastic shaking of the path and ensuring the stability and predictability of the robot operation.

[0062] Exemplarily, the map information of the warehouse is as shown in Figure 3 , which includes the starting position and the task target position; for the map information of the warehouse in Figure 3 , the system performs a standard JPS algorithm once to calculate an initial optimal path from the starting position to the task target position, and the planning graph of the initial optimal path is as shown in Figure 4 ; in the process of the robot traveling along the initial optimal path, the system monitors the warehouse environment in real time, and when the robot travels to the current position in Figure 4 , it receives a report of a malfunctioning robot and its position coordinates, and determines that the obstacle conflicts with the currently planned path; further, the method of the present application is used to repair the local path, and the planning graph of the repaired new path is as shown in Figure 5 ; and the prior art is to recalculate a brand new path from the current position of the robot to the task target position, and the planning graph of the brand new path is as shown in Figure 6 ; compared with the brand new path in Figure 6 , the repaired new path in Figure 5 only changes in the local area, and maintains high consistency with the main structure of the original path, thereby avoiding drastic shaking of the path and ensuring the stability and predictability of the robot operation.​​

Claims

1. A method for intelligent path planning of a four-way shuttle robot, characterized in that, include: Obtain a rasterized map containing the static environment layout; Based on the map, the JPS algorithm is used to calculate the initial optimal path from the starting position to the target position, and multiple jump points, starting positions and target positions in the initial optimal path are extracted into an ordered sequence of path anchor points; During the robot's journey along the initial optimal path, in response to the detection of a dynamic obstacle, it is determined that the obstacle conflicts with the initial optimal path. If a conflict exists, a stability assessment is performed on the first anchor point after the conflict point to obtain its stability assessment index. The stability assessment index is directly proportional to the distance from the first anchor point to the obstacle and inversely proportional to the distance from the first anchor point to the robot's current position, and increases as its position in the remaining path progresses. A hierarchical decision is made based on the comparison results between the stability evaluation index and the preset threshold, and a repair window containing the conflict point is defined. The boundary of the repair window is determined by two anchor points in the path anchor point sequence. Perform a local path search within the repair window to generate an optimal local repair path that bypasses the obstacle; then merge the optimal local repair path with the unaffected path segments of the initial optimal path to form a complete new path.

2. The intelligent path planning method for a four-way shuttle robot according to claim 1, characterized in that, The determination that the obstacle conflicts with the initial optimal path includes: Let the robot's current position coordinates be... The paths that have not been traversed are those from the initial optimal path. Subpath to the target location; Check obstacle coordinates Is it located on the untraveled sub-path? If If the conflict exists on the sub-path, a path conflict is determined, and the distance on the path is recorded. The system identifies the nearest conflict point and locates the anchor point interval containing the conflict point within the path anchor point sequence. .

3. The intelligent path planning method for a four-way shuttle robot according to claim 2, characterized in that, A stability assessment is performed on the first anchor point after the conflict point to obtain its stability assessment index, including: As the first anchor point after the conflict point, its stability assessment index The formula for calculation is: ； In the formula, The Manhattan distance between the two points; The coordinates of the dynamic obstacle; These are the robot's current position coordinates; It is the last effective anchor point before the conflict occurs; From the anchor point From the initial optimal path to the anchor point Path length; From the anchor point From the initial optimal path to the destination The total remaining path length.

4. The intelligent path planning method for a four-way shuttle robot according to claim 1, characterized in that, The preset threshold includes a high stability threshold. and low stability threshold ,and .

5. The intelligent path planning method for a four-way shuttle robot according to claim 4, characterized in that, Based on the comparison results between the stability assessment index and the preset threshold, a hierarchical decision is made to define a repair window that includes the conflict points, including: If anchor point Stability assessment indicators Then repair the starting anchor point of the window. End point anchor ; if The system initiates topology impact depth verification to determine the repair window.

6. The intelligent path planning method for a four-way shuttle robot according to claim 5, characterized in that, The initiation topology impact depth verification to determine the repair window includes: by Starting from, with For the first exploration endpoint, perform a bounded breadth-first search: If, in a bounded breadth-first search, a path leading to the exploration endpoint can be found... The path then repairs the starting anchor point of the window. End point anchor ; If, in a bounded breadth-first search, a path cannot be found within the specified range... The path needs to be expanded to include a wider window: maintain the starting anchor point of the repair window. The exploration endpoint will remain unchanged, and will be moved forward to the next anchor point. The stability assessment is repeated, and a tiered decision is made based on the comparison between the stability assessment index and the preset threshold, until the first one that can be [performed / resolved] is found. Connected anchor points Then repair the end anchor point of the window. .

7. The intelligent path planning method for a four-way shuttle robot according to claim 6, characterized in that, When performing a bounded breadth-first search, the search scope is limited to a range of [number of elements]. and Within a circular region with a radius equal to the Manhattan distance between them.

8. The intelligent path planning method for a four-way shuttle robot according to claim 1, characterized in that, The process of performing a local path search within the repair window includes: by As the starting point for local search, with As the endpoint of the local search, after updating the dynamic obstacles... On the map copy, a route from... is calculated using the JPS algorithm. arrive And it can bypass obstacles Optimal local repair path .

9. The intelligent path planning method for a four-way shuttle robot according to claim 1, characterized in that, The new path consists of three parts: the original path from the starting point To the starting point of repair sub-path segments The newly generated optimal local repair path And the original path from the repair endpoint To the finish line sub-path segments .

10. The intelligent path planning method for a four-way shuttle robot according to claim 1, characterized in that, The jump points include corner points and / or points near obstacles in the initial optimal path.

Images