ROS2-based workshop robot path planning method and system

Abstract

The invention provides a workshop robot path planning method and system based on ROS2, and is applied to the technical field of robots, potential problems can be identified before conflicts actually occur by obtaining current task information and short-term planning path information and performing prediction in a future time window, and the path planning method and system based on the ROS2 can be used for solving the problems of the conflicts by obtaining and utilizing the current task information. The system can identify the robot executing the high-priority task, so that the passing right of the robot is guaranteed preferentially when the conflict is solved; after the task priorities of the two conflicting parties are determined, path adjustment is carried out according to the task priorities, and disordered or low-efficiency avoidance behaviors are avoided. Therefore, the method has the advantages that potential space conflicts among the multiple robots can be effectively predicted, cooperative path adjustment is performed according to the task priority, the response efficiency of high-priority tasks is improved, invalid avoidance and congestion among the robots are reduced, and the overall operation process is optimized.

Description

Technical Field

[0001] The present application relates to the field of robotics technology, and in particular to a workshop robot path planning method and system based on ROS2. Background Art

[0002] Floor cleaning in manufacturing workshops is a repetitive and critical task, and its efficiency directly impacts the production environment and product quality. Traditional cleaning methods rely on manual labor, which is inefficient and difficult to cover large areas. With the advancement of automation technology, the use of multiple autonomous mobile cleaning robots for collaborative operations has become a trend. In a typical manufacturing workshop environment, floor cleaning is performed by a system consisting of multiple autonomous mobile cleaning robots. This robotic system typically utilizes advanced software architectures, such as ROS2 (Robot Operating System 2), to enable communication between individual robots, environmental perception, task decision-making, and motion control.

[0003] Robots are typically equipped with various sensory devices to acquire environmental information, such as mapping, positioning, and real-time obstacle detection. A central control system manages the entire robot fleet, including assigning cleaning tasks to the robots. Each task typically specifies the area to be cleaned, cleaning requirements, and task priority. After receiving the task information, the robot, combined with its current state information, such as energy levels and remaining consumables, plans a path to reach the task area and perform the cleaning operation.

[0004] In the early stages of system deployment, workshops were often simply divided into cleaning zones based on their geometry or pre-set grids, with these zones rigidly assigned to specific robots or groups of robots. To address the diverse cleaning needs of different areas, the system introduced a more flexible task dispatching mechanism. This mechanism dynamically prioritizes tasks for different areas based on real-time dirt sensing data or pre-set cleaning plans.

[0005] When there are multiple robots and multiple priority tasks simultaneously, a central system needs to coordinate task dispatch. However, in this multi-robot, multi-task, and multi-priority environment, when multiple high-priority tasks are concentrated in a certain area or require robots to pass through the same necessary passage, multiple robots independently planning paths to the high-priority areas may result in excessive density of moving objects in these areas or on the paths to them, or severe overlap of paths. This task switching and path change, performed without effective coordination with other robots, can easily interrupt existing work processes. More importantly, if a robot updates a new priority task mid-process and plans a new path to execute the new priority task, the robot may conflict with the paths currently being executed or planned by other robots in the workshop. This may not only delay its arrival at the spill location, but also reduce the efficiency of emergency response.

[0006] Therefore, in a multi-robot collaborative cleaning scenario in a workshop where there are dynamically emerging high-priority tasks and the current operation needs to be interrupted for path replanning, how to optimize the collective movement of the entire robot team when priority interruptions occur, while trying to maintain the progress of other low-priority tasks, avoid bottlenecks in key areas, and reduce ineffective movement or repetitive cleaning work, has become a technical challenge that needs to be solved urgently.

[0007] In view of the above problems, the existing technology is in urgent need of improvement. Summary of the Invention

[0008] In view of the above-mentioned shortcomings of the existing technology, the present application provides a workshop robot path planning method and system based on ROS2, which has the advantages of being able to effectively predict potential spatial conflicts between multiple robots and adjust collaborative paths according to task priorities, thereby improving the response efficiency of high-priority tasks, reducing ineffective avoidance and congestion between robots, and optimizing the overall operation process.

[0009] In a first aspect, a workshop robot path planning method based on ROS2 is provided, the method comprising the steps of:

[0010] S1: Obtain the current task information and short-term planning path information of multiple robots;

[0011] S2: predicting whether there is a spatial conflict between multiple robots in a future time window based on the current task information and the short-term planning path information;

[0012] S3: When a spatial conflict is predicted, determining the task priorities of the robots involved in the conflict based on the current task information;

[0013] S4: According to the task priorities, adjust the short-term planned paths of the robots involved in the conflict so that the low-priority robot avoids the high-priority robot.

[0014] The present application proposes a workshop robot path planning method based on ROS2, which provides the necessary data support for subsequent conflict prediction and resolution by obtaining current task information and short-term planning path information; by making predictions within the "future time window", potential problems can be identified before the conflict actually occurs, which buys time for subsequent intervention and adjustment, avoids temporary and passive obstacle avoidance behaviors, and improves response efficiency; by obtaining and utilizing current task information, the system can identify robots performing high-priority tasks, thereby giving priority to their right of way when resolving conflicts; after determining the task priorities of the conflicting parties, the path is adjusted "according to the task priority", and the principle of adjustment is clarified as "low-priority robots avoid high-priority robots", avoiding disordered or inefficient avoidance behaviors. Therefore, the present application has the advantages of being able to effectively predict potential spatial conflicts between multiple robots and make collaborative path adjustments according to task priorities, thereby improving the response efficiency of high-priority tasks, reducing ineffective avoidance and congestion between robots, and optimizing the overall operation process.

[0015] Furthermore, step S1 includes:

[0016] S11: receiving current task information published by multiple robots;

[0017] S12: receiving messages published by multiple robots, each of which includes short-term planned path information, timestamp information associated with the short-term planned path information, and a format identifier representing the short-term planned path information;

[0018] S13: performing format conversion on the short-term planned path information according to the format identifier to obtain short-term planned path information in a unified format;

[0019] S14: Determine the short-term planned path information for subsequent conflict prediction from the short-term planned path information in a unified format according to the timestamp information.

[0020] This application proposes a ROS2-based workshop robot path planning method, which specifies in detail the specific implementation methods for obtaining the current task information and short-term planning path information of multiple robots. It solves the problem of how to reliably, accurately and timely obtain the heterogeneous and distributed task information and short-term planning path information required for conflict prediction in a multi-robot system.

[0021] Furthermore, step S2 includes:

[0022] S21: Obtaining restricted area information of the manufacturing workshop and access rules associated with the restricted area information;

[0023] S22: Determine movement characteristic parameters of each of the multiple robots according to the current task information;

[0024] S23: predicting the space occupancy information of the plurality of robots in a future time window based on the short-term planned path information, the restricted area information, the traffic rules, and the movement characteristic parameters;

[0025] S24: Determine whether there is a spatial conflict between multiple robots in a future time window based on the space occupancy information.

[0026] This application proposes a path planning method for workshop robots based on ROS2, which improves the accuracy of spatial conflict prediction by more comprehensively considering the workshop environment constraints and the robot's own characteristics.

[0027] Furthermore, step S23 includes:

[0028] S231: Acquire dynamic environmental information of the manufacturing workshop and real-time status information of multiple robots;

[0029] S232: Determine execution deviation ranges of the plurality of robots within a future time window based on the short-term planned path information, the restricted area information, the traffic rules, the movement characteristic parameters, the environmental dynamic information, and the real-time state information;

[0030] S233: Predicting the space occupancy information of the respective robots in the future time window based on the short-term planning path information, the restricted area information, the traffic rules, the movement characteristic parameters and the execution deviation range.

[0031] This application proposes a workshop robot path planning method based on ROS2. By introducing environmental dynamic information and real-time robot status information, and calculating the robot's execution deviation range based on this information, it can more accurately predict the robot's actual space occupancy and improve the accuracy of spatial conflict prediction.

[0032] Furthermore, step S232 includes:

[0033] S2321: Obtaining real-time status information of multiple robots;

[0034] S2322: Determine, based on the short-term planned path information, the restricted area information, the traffic rules, the movement characteristic parameters, and the environmental dynamic information, the expected spatial occupancy areas of the multiple robots along the short-term planned paths in a future time window;

[0035] S2323: Determine, based on the real-time state information, additional space occupied by each of the multiple robots due to positioning uncertainty in a future time window;

[0036] S2324: Combine the expected space occupation area and the additional space occupation area to obtain the execution deviation ranges of the multiple robots in the future time window.

[0037] Furthermore, step S233 includes:

[0038] S2331: Determine, along the short-term planned path, a sequence of expected trajectory points of multiple robots along the short-term planned path within a future time window according to the movement characteristic parameters, wherein the movement characteristic parameters include robot size information;

[0039] S2332: For each trajectory point in the expected trajectory point sequence, determine an initial spatial occupation area of ​​the robot at the trajectory point based on the position of the trajectory point, the robot size information, and the execution deviation range corresponding to the trajectory point;

[0040] S2333: Modify the initial space occupied area according to the restricted area information and the passage rule to obtain the space occupied area of ​​the robot at the trajectory point;

[0041] S2334: Combining the corrected space occupation areas at the multiple trajectory points to obtain the space occupation information of the multiple robots in the future time window.

[0042] Furthermore, step S3 includes:

[0043] Obtaining current task information of each of the robots involved in the conflict, wherein the current task information includes task type information and task timeliness information;

[0044] S31: Acquire the area information of each robot involved in the conflict and the overall status information of the workshop;

[0045] S32: Acquire real-time status information of each robot involved in the conflict, wherein the real-time status information includes at least robot power information;

[0046] S33: Comprehensively determine the task priorities of the robots involved in the conflict based on the task type information, the task timeliness information, the area information, the overall workshop status information, and the robot power information.

[0047] Furthermore, step S33 includes:

[0048] S331: Determine the basic task priorities of the robots involved in the conflict according to the task type information;

[0049] S332: Calculating the task urgency of each of the robots involved in the conflict based on the task timeliness information;

[0050] S333: Determining the environmental impact factors of the robots involved in the conflict based on the area information and the overall state information of the workshop;

[0051] S334: Determine the power impact factor of each of the robots involved in the conflict based on the robot power information;

[0052] S335: Comprehensively determine the task priorities of the respective robots involved in the conflict based on the basic task priority, the task urgency, the environmental impact factor, and the power impact factor.

[0053] Furthermore, it is characterized in that step S4 includes:

[0054] S41: acquiring, according to the task priorities, first current task information and first short-term planned path information of the low-priority robot involved in the conflict, and second short-term planned path information of the high-priority robot involved in the conflict;

[0055] S42: Obtaining restricted area information and access rules of the manufacturing workshop;

[0056] S43: Determine, based on the first short-term planned path information, the second short-term planned path information, the restricted area information, and the traffic rules, a feasible avoidance area or path segment for the low-priority robot within a future time window;

[0057] S44: Planning an adjustment path for the low-priority robot based on the first current task information, the feasible avoidance area or path segment, and the second short-term planned path information, wherein the adjustment path is used to avoid the high-priority robot.

[0058] In a second aspect, a workshop robot path planning system based on ROS2 is applied to the steps of any of the above methods, the system comprising:

[0059] Acquisition module: obtains the current task information and short-term planning path information of multiple robots;

[0060] Prediction module: predicts whether there is spatial conflict between multiple robots in a future time window based on the current task information and the short-term planning path information;

[0061] Priority determination module: when a spatial conflict is predicted, determining the task priority of the robots involved in the conflict based on the current task information;

[0062] Planning module: According to the task priorities, adjust the short-term planning paths of the robots involved in the conflict so that the low-priority robots avoid the high-priority robots.

[0063] Beneficial effects: The present application proposes a ROS2-based workshop robot path planning method and system, which provides the necessary data support for subsequent conflict prediction and resolution by acquiring current task information and short-term planning path information; by making predictions within the "future time window", potential problems can be identified before the conflict actually occurs, which buys time for subsequent intervention and adjustment, avoids temporary and passive obstacle avoidance behaviors, and improves response efficiency; by acquiring and utilizing current task information, the system can identify robots that perform high-priority tasks, thereby giving priority to their right of way when resolving conflicts; after determining the task priorities of the conflicting parties, the path is adjusted "according to the task priority", and the principle of adjustment is clarified as "low-priority robots avoid high-priority robots", avoiding disordered or inefficient avoidance behaviors. Therefore, the present application has the advantages of being able to effectively predict potential spatial conflicts between multiple robots and make collaborative path adjustments according to task priorities, thereby improving the response efficiency of high-priority tasks, reducing ineffective avoidance and congestion between robots, and optimizing the overall operation process. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 This is a flowchart of a ROS2-based workshop robot path planning method proposed in this application.

[0065] Figure 2 This is a structural diagram of a workshop robot path planning system based on ROS2 proposed in this application.

[0066] Figure 3 This is an architecture diagram of a ROS2-based workshop robot path planning system proposed in this application.

[0067] Description of reference numerals: 201, acquisition module; 202, prediction module; 203, priority determination module; 204, planning module. DETAILED DESCRIPTION

[0068] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and marked in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of this application.

[0069] It should be noted that similar reference numerals and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined or explained in subsequent figures. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0070] Please refer to Figure 1 , a workshop robot path planning method based on ROS2, the method comprising the steps of:

[0071] S1: Obtain the current task information and short-term planning path information of multiple robots;

[0072] S2: Based on the current task information and short-term planning path information, predict whether there will be spatial conflicts among multiple robots in the future time window;

[0073] S3: When a spatial conflict is predicted, the task priorities of the robots involved in the conflict are determined based on the current task information;

[0074] S4: Based on the task priorities, adjust the short-term planned paths of the robots involved in the conflict so that the low-priority robots avoid the high-priority robots.

[0075] Among them, the current task information includes the type, target, priority, etc. of the task currently assigned to the robot. It can be implemented in a structured data format, for example, including fields such as task identifier, task type, target location or area, task priority value, etc., which is mainly for understanding the current work content and importance of the robot.

[0076] Short-term planning path information refers to the movement trajectory data that the robot plans to follow in the future. It can be represented by a series of ordered pose points and associated timestamps to describe the robot's expected movement trajectory in the future. Its main purpose is to predict the robot's space occupancy in the future.

[0077] Spatial conflict refers to the overlap of the predicted spatial occupation areas of multiple robots in time and space within a future time window, mainly to detect potential collision or congestion risks in advance.

[0078] The future time window refers to the time range for conflict prediction, which can be dynamically determined based on factors such as robot speed and communication delay. It is mainly used to limit the scope of prediction and balance computing resources and prediction accuracy.

[0079] Task priority refers to the order in which tasks are executed or the level of access rights determined based on factors such as task type, timeliness, and importance. It primarily determines the order in which resources are allocated during resource competition. Adjusting the short-term planned path involves modifying the robot's original short-term planned path based on conflict prediction results and task priority, generating a new feasible path and achieving orderly avoidance between robots.

[0080] As a preferred embodiment, the solution of this application is specifically implemented as follows:

[0081] In a manufacturing workshop environment, multiple autonomous mobile robots are deployed alongside a central coordination system (hereafter referred to as the system). The system periodically receives messages from each robot through a communication mechanism. These messages contain the robot's current task identifier, task type, and the short-term planned path for the next few seconds generated by the robot's local planner.

[0082] After receiving this information, the system analyzes the short-term planned paths of all robots. It models each robot as a geometric object of a certain size and, based on the path information and the robot's movement characteristics, predicts the sequence of spatial areas that each robot will occupy within a future time window.

[0083] The system predicts whether there is a spatial conflict by checking whether the spatial occupancy sequences of different robots overlap in time. If a conflict is detected, the system queries the task information of the robots involved and determines the priority of the conflicting parties based on pre-set task priority rules.

[0084] Suppose robot A is performing a low-priority task and robot B is performing a high-priority task, and they are predicted to collide in a certain area. The system calculates feasible avoidance paths or areas for robot A during the conflict period, such as temporary parking spots or detours. The system then generates a new short-term planned path for robot A, guiding it to perform avoidance maneuvers to avoid the collision with robot B. This new path is sent to robot A via a message for execution. Robot B then continues executing its high-priority task.

[0085] Through the above solution, this application solves the problem of path conflicts and interference with low-priority tasks caused by high-priority tasks in a multi-robot collaborative operation environment. This method avoids the inefficiency and uncertainty caused by temporary obstacle avoidance by proactively predicting spatial conflicts between robots. The conflict resolution mechanism based on task priority ensures the rapid response and execution of high-priority tasks and reduces the interference they receive. At the same time, by guiding low-priority robots to avoid, the negative impact of high-priority tasks on other ongoing low-priority task processes is minimized, thereby improving the collaborative efficiency and operational fluency of the entire robot system.

[0086] Furthermore, step S1 includes:

[0087] S11: receiving current task information published by multiple robots;

[0088] S12: receiving messages published by multiple robots, each containing short-term planned path information, timestamp information associated with the short-term planned path information, and a format identifier representing the short-term planned path information;

[0089] S13: Converting the format of the short-term planning path information according to the format identifier to obtain the short-term planning path information in a unified format;

[0090] S14: Determine short-term planning path information for subsequent conflict prediction from the short-term planning path information in a unified format according to the timestamp information.

[0091] In a specific embodiment, the message mechanism of ROS2 may be used to implement the reception and release of information.

[0092] Each robot can publish its current task information (for example, a custom TaskStatus message containing fields such as task ID, type, priority, and target location) and short-term planned path information (for example, a Path message containing a series of PoseStamped points and an additional Header field containing a timestamp and frame_id, which can be used as a format identifier) ​​through ROS2's Publisher. The system can subscribe to these messages as a Subscriber.

[0093] For short-term planning path information, since different robots or different path planning algorithms may generate different types of Path messages (for example, containing speed information or not), the system can call the corresponding format conversion function according to the message type (i.e., format identifier).

[0094] Specifically, the implementation of calling the corresponding format conversion function based on the message type (i.e., format identifier) ​​involves the following: When the system receives a path message published by a robot, it first identifies the message format by parsing the message's type field or topic name, such as PathWithVelocity, a standard Path type, or a custom path format. For PathWithVelocity messages, the conversion function extracts the poses array, ignores the velocity field, retains the position coordinates (x, y, z) and orientation quaternion, and then repackages it into the standard nav_msgs::Path message format. For custom path messages that include additional time information, the conversion function extracts the waypoint sequence and the corresponding timestamp sequence, reorganizing the data structure according to the standard format. During the conversion process, the frame_id is uniformly set to the "map" coordinate system to ensure that all path information is processed in the same reference coordinate system.

[0095] For example, if a custom PathWithVelocity message containing velocity information is received, the conversion function can extract the location and timestamp and convert it to the standard nav_msgs / Path message format. These converted, unified-format Path messages are stored in a buffer and managed based on the timestamp in their headers. Before performing conflict prediction, the system can query this buffer and select Path messages with timestamps within a recent threshold as valid short-term planning path information for processing.

[0096] Specifically, the timestamp-based management mechanism is as follows: the system maintains a hash table with the robot ID as the key value, and each key value corresponds to a path message queue sorted in descending order by timestamp. When a new path message is received, the system first checks the stamp field in the message header to obtain the timestamp, and then compares it with the current system time, setting the time validity threshold to 5 seconds, that is, only messages whose publishing time is no more than 5 seconds from the current time are retained. For messages that meet the time requirements, they are inserted into the message queue of the corresponding robot in timestamp order, and historical messages in the queue that exceed the time threshold are removed. When performing conflict prediction, the system selects the path information with the latest timestamp from the message queue of each robot as the valid short-term planning path. The queue length is limited to save a maximum of 10 messages. When the limit is exceeded, the oldest message is automatically deleted to ensure the rationality of memory usage and the real-time nature of data.

[0097] Through the above method, the system can reliably obtain and preprocess the current task information and short-term planning path information released by multiple robots.

[0098] Furthermore, step S2 includes:

[0099] S21: Obtaining restricted area information of the manufacturing workshop and access rules associated with the restricted area;

[0100] S22: Determine the movement characteristic parameters of each of the multiple robots according to the current task information;

[0101] S23: Predicting the spatial occupancy information of multiple robots in a future time window based on the short-term planning path information, restricted area information, traffic rules, and movement characteristic parameters;

[0102] S24: Based on the space occupancy information, determine whether there is a space conflict between multiple robots in the future time window.

[0103] Specifically, the robot acquires information about restricted areas within the manufacturing workshop and the associated traffic rules. This information can include prohibited areas, one-way traffic areas, and speed-limited areas marked on the workshop map, as well as the movement regulations that the robot must comply with within these areas. This information provides important environmental constraints for subsequent space occupancy prediction.

[0104] Determine the motion parameters of multiple robots. These parameters reflect the robot's physical size, maximum speed, acceleration, turning radius, positioning accuracy, and other factors. These parameters can be adjusted based on the type of mission the robot is currently performing (e.g., emergency or routine) or the payload status. These parameters are the basis for predicting the robot's spatial requirements and dynamic behavior during actual movement.

[0105] The spatial occupancy of multiple robots within future time windows is predicted based on short-term planned paths, acquired information about the workshop environment's constraints, and the robots' own characteristics. By comprehensively considering these factors, a more precise prediction of the spatial extents that the robots are likely to occupy at different moments in the future can be made. For example, this prediction takes into account the robots' actual dimensions, the additional space required for turning, and speed and position constraints within narrow or restricted areas. This multi-dimensional prediction significantly improves the sophistication and accuracy of spatial occupancy predictions.

[0106] Finally, based on the predicted spatial occupancy information of multiple robots in the future time window, it is determined whether there is any spatial conflict between them. Because the spatial occupancy predictions are more accurate and more realistic, the conflict judgment based on this prediction is more reliable and can more effectively identify potential collisions, congestion, or other forms of spatial conflict.

[0107] Furthermore, step S23 includes:

[0108] S231: Acquire dynamic environmental information of the manufacturing workshop and real-time status information of multiple robots;

[0109] S232: Determine the execution deviation ranges of the multiple robots within a future time window based on the short-term planned path information, restricted area information, traffic rules, movement characteristic parameters, environmental dynamic information, and real-time status information;

[0110] S233: Predict the space occupancy information of multiple robots in the future time window based on the short-term planning path information, restricted area information, traffic rules, movement characteristic parameters, and execution deviation range.

[0111] In a specific embodiment, the environmental dynamic information may include: receiving real-time obstacle position and speed information released from a sensor network deployed in the workshop, for example, position data of temporary piles or mobile forklifts detected by lidar scanning.

[0112] The real-time status information of each of the multiple robots may include receiving from each robot a positioning accuracy estimate reported by its current positioning system and a tracking error reported by its motion controller.

[0113] When determining the execution deviation range of multiple robots in the future time window, a basic expected space occupation area can be calculated based on the expected position points on the short-term planning path and combined with the movement characteristic parameters.

[0114] The calculation process specifically involves: first, determining the robot's geometric shape based on its motion parameters. Typically, the robot is modeled as a circular area centered at the robot's center and with its maximum outer dimensions as its radius, or as a rectangular area based on its length and width. Second, at each trajectory point along the short-term planned path, the robot's geometric shape is placed at that point, forming the initial occupied area at that moment. Then, based on the maximum velocity and acceleration information in the robot's motion parameters, the maximum distance the robot can deviate from the path when moving between adjacent trajectory points is calculated. This deviation distance is used as a safety margin to expand the initial occupied area.

[0115] Based on the acquired dynamic information of the environment, such as the presence of dynamic obstacles near the path and their movement trends, an additional potential space occupation area caused by uncertainty is calculated.

[0116] This calculation method can be as follows: First, sensors acquire the position coordinates and velocity vector information of dynamic obstacles within a certain range (for example, a radius of 3 meters) around the robot's expected path. Then, based on the dynamic obstacle's current position and motion trend, the robot predicts the possible location area it may reach within a future time window. The calculation formula is: Future obstacle location area = Current position + Velocity vector × Time range. If the predicted obstacle movement area intersects the robot's expected path, the intersection area and the surrounding safety distance (typically set at 1.5 times the robot's size) are considered as potential occupied space for the robot to ensure that the robot can adjust its trajectory in a timely manner to avoid dynamic obstacles.

[0117] For example, for a robot with lower localization accuracy, the additional spatial footprint may be a larger circular or elliptical area. The final execution deviation range can be determined by combining the base expected spatial footprint with the additional potential spatial footprint (e.g., performing a set union operation or envelope calculation).

[0118] To predict the spatial occupancy of multiple robots within a future time window, a series of expected trajectory points can be determined along the short-term planned path based on the robot's mobility parameters (including robot size) and expected velocity. For each expected trajectory point, the robot's size and shape are placed at that point and combined with the corresponding execution deviation range at that point (for example, the robot shape and the deviation range are dilated or convolved) to obtain an initial spatial occupancy region. This initial region is then modified based on restricted area information and traffic rules. For example, if a portion of the region falls within a prohibited area, it is removed from the spatial occupancy region or marked. The spatial occupancy regions of all modified trajectory points are combined (for example, by calculating the union of all regions) to obtain the predicted spatial occupancy information of the robot within the future time window.

[0119] By acquiring dynamic information about the manufacturing floor's environment and the real-time status of multiple robots, and using this information to determine the execution deviation ranges of each robot within a future time window, this solution can more accurately predict the space robots are likely to occupy in dynamic and uncertain environments. Incorporating execution deviation ranges into space occupancy predictions makes the predictions more accurate, thereby improving the accuracy of subsequent spatial conflict determinations. This helps reduce missed or falsely reported conflicts caused by inaccurate predictions, thereby enhancing the reliability and efficiency of multi-robot collaborative operations.

[0120] Furthermore, step S232 includes:

[0121] S2321: Obtaining real-time status information of multiple robots;

[0122] S2322: Determine the expected spatial occupancy areas of the multiple robots along their respective short-term planned paths within a future time window based on the short-term planned path information, restricted area information, traffic rules, movement characteristic parameters, and environmental dynamic information;

[0123] S2323: Determine, based on the real-time state information, additional space occupied by each of the multiple robots due to positioning uncertainty within a future time window;

[0124] S2324: Combine the expected space occupation area and the additional space occupation area to obtain the execution deviation ranges of the multiple robots in the future time window.

[0125] Among them, real-time status information refers to data reflecting the current operating status of the robot, which may include the robot's current position, posture, speed, acceleration, and information related to positioning accuracy.

[0126] The expected space occupation area refers to the space range that the robot is expected to occupy based on its size and movement characteristics and environmental constraints under ideal circumstances, that is, when the robot moves strictly according to the planned path and does not consider positioning errors.

[0127] Excessive space refers to the amount of space beyond the expected space occupied by a robot due to uncertainty in its actual positioning, which can cause its true position to deviate from its expected position. Positioning uncertainty refers to the error in the robot's estimated position, caused by sensor noise, environmental changes, map accuracy, or algorithm limitations.

[0128] In a specific embodiment, determining the execution deviation ranges of the multiple robots in the future time window can be achieved as follows:

[0129] In step S2321, by subscribing to ROS2 topics such as ` / odom` or ` / amcl_pose`, the real-time status information of multiple robots is obtained. This information includes the current position (position and attitude) of the robot and the related covariance matrix, which can be used to characterize positioning uncertainty.

[0130] In step S2322, the robot's expected spatial footprint is calculated along the short-term planned path based on the robot's published short-term planned path information, combined with the static restricted area information of the manufacturing workshop, pre-set traffic rules, the robot's mobility parameters such as size and maximum speed, and dynamic environmental information acquired by sensors (e.g., the position and speed of dynamic obstacles). This can be achieved by discretizing the planned path into a series of trajectory points. At each trajectory point, a region representing the robot (e.g., a circle or rectangle) is generated based on the robot's size information, corrected to account for environmental constraints, and then these regions are combined along the path.

[0131] In step S2323, the extra space occupied by the robot due to positioning uncertainty is calculated at each expected trajectory point in the future time window based on the covariance matrix in the real-time state information. This can be done by calculating a confidence ellipse or ellipsoid from the covariance matrix, which represents the range within which the robot's true position falls with a certain probability. This range constitutes the extra space occupied.

[0132] In step S2324, the expected space occupied area calculated along the short-term planning path is combined with the additional space occupied area calculated by the positioning uncertainty, for example, the union of the two is taken to obtain the execution deviation range of each robot in the future time window.

[0133] Furthermore, step S233 includes:

[0134] S2331: Determine, along the short-term planned path, a sequence of expected trajectory points of the multiple robots within a future time window based on movement characteristic parameters, wherein the movement characteristic parameters include robot size information;

[0135] S2332: For each trajectory point in the expected trajectory point sequence, determine the initial spatial occupation area of ​​the robot at the trajectory point based on the position of the trajectory point, the robot size information, and the execution deviation range corresponding to the trajectory point;

[0136] S2333: Modify the initial space occupied area based on the restricted area information and traffic rules to obtain the space occupied area of ​​the robot at the trajectory point;

[0137] S2334: Combining the corrected space occupation areas at the multiple trajectory points to obtain the space occupation information of the multiple robots in the future time window.

[0138] Among them, the mobility characteristic parameters refer to a set of parameters that describe the robot's motion and physical properties, which can be represented by a set of parameters including the robot's maximum speed, maximum acceleration, turning radius, and robot size information.

[0139] The execution deviation range refers to the maximum possible deviation area of ​​the robot's actual position relative to its planned position after taking into account the environmental dynamics and the robot's real-time status (such as positioning accuracy). It can be represented by an area with a specific shape and size (such as a circle, ellipse or polygon) centered on the planned position.

[0140] This application uses a series of steps to systematically predict the spatial regions that multiple robots may occupy within a future time window. Specifically:

[0141] Step S2331 generates a series of discrete expected trajectory points along each robot's short-term planned path based on its motion characteristic parameters. This process converts the continuous path into a series of expected positions at different time points, providing a discretized basis for subsequent spatial occupancy calculations. It is precisely because of this discretization that refined spatial occupancy analysis can be performed at each specific expected position.

[0142] Step S2332 not only considers the robot's physical size but, more importantly, incorporates the deviation range caused by potential positioning or control errors during actual execution. This combination of robot size and execution deviation range ensures that the predicted area more accurately reflects the maximum space the robot could actually occupy near the expected position, thereby improving the reliability of the prediction.

[0143] In step S2333, the initial region may extend into areas that the robot is not actually allowed to enter or remain in, such as walls, fixed obstacles, or no-go zones, due to consideration of deviations. This modification of the initial region based on environmental constraints ensures that the resulting spatial occupancy area conforms to the actual environmental constraints, preventing the predicted region from exceeding the physically or legally feasible range, thereby improving the accuracy and practicality of the prediction.

[0144] In step S2334, it is precisely because the prediction results at discrete time points are integrated into a whole that the information can comprehensively represent the robot's spatial requirements in the future, providing a comprehensive and reliable basis for subsequent judgment of whether there is spatial conflict between multiple robots.

[0145] Through the synergistic effect of the above steps, the present application can more accurately predict the spatial occupancy of robots, especially in complex workshop environments with execution deviations and environmental constraints, thereby providing a solid foundation for conflict detection and avoidance in multi-robot collaborative path planning.

[0146] Furthermore, step S3 includes:

[0147] Obtain the current task information of each robot involved in the conflict, including task type information and task timeliness information;

[0148] S31: Acquire the area information of each robot involved in the conflict and the overall status information of the workshop;

[0149] S32: Acquire real-time status information of each robot involved in the conflict, where the real-time status information includes at least robot power information;

[0150] S33: Based on the task type information, task timeliness information, area information, overall workshop status information, and robot power information, comprehensively determine the task priorities of the robots involved in the conflict.

[0151] Based on the above technical features, the task priority determination process of this application is as follows.

[0152] In step S31, the system further obtains information about the robot's location and the overall workshop status. Incorporating these environmental factors allows priority determination to move beyond the task itself and take into account the robot's specific environment and its impact on the overall workshop process. For example, a robot in a critical production area or performing a task during periods of high overall workshop load may have its task assigned a higher priority.

[0153] In step S32, the system obtains real-time status information for each robot involved in the conflict, with particular attention paid to the robot's battery level. Considering the robot's real-time status, especially its battery level, is crucial because it directly impacts its ability and flexibility to perform tasks. For example, a robot with low battery may need to prioritize recharging, or its ability to perform complex evasive maneuvers may be limited.

[0154] In step S33, the system comprehensively considers the task type, timeliness, region, overall workshop status, and robot battery status information obtained above to determine the task priority of each conflicting robot. This comprehensive assessment, which organically combines task attributes, environmental factors, and the robot's own status, enables a more accurate and comprehensive assessment of the relative importance and urgency of each conflicting robot. This more refined and context-aware priority determination provides a more rational and effective basis for subsequent path adjustments.

[0155] For example, even if a robot has a higher priority for a task type, if its battery is extremely low, the system may take this factor into account when determining its priority; or if a robot has a lower priority for a task type, if it is in a critical area that must pass quickly, its priority may be appropriately increased.

[0156] In this way, the improvements of this application enable the entire path planning method to better balance the needs of different tasks when resolving robot conflicts, more effectively utilize robot resources, thereby improving the efficiency and rationality of conflict resolution and optimizing overall system performance.

[0157] Furthermore, step S33 includes:

[0158] S331: Determine the basic task priorities of the robots involved in the conflict based on the task type information;

[0159] S332: Calculating the task urgency of each robot involved in the conflict based on the task timeliness information;

[0160] S333: Determine the environmental impact factors of the robots involved in the conflict based on the regional information and the overall workshop status information;

[0161] S334: Determine the power impact factor of each robot involved in the conflict based on the robot power information;

[0162] S335: Comprehensively determine the task priorities of the robots involved in the conflict based on the basic task priority, task urgency, environmental impact factors, and power impact factors.

[0163] The basic task priority refers to the initial priority assigned according to the inherent importance of the task itself or the preset level, which can be implemented by using a predefined task type and priority mapping table.

[0164] Task urgency refers to the urgency of task completion, which can be achieved by using a function calculation based on the task deadline or remaining time.

[0165] The environmental impact factor refers to the impact of the robot's regional environment or the overall operating status of the workshop on the importance of the task. It can be achieved by evaluating or looking up information based on the area type (such as key area, ordinary area) or the degree of congestion in the workshop, the operating status of the equipment, and other information.

[0166] The power impact factor refers to the impact of the robot's current power level on its task execution capability. It can be achieved by calculating or grading based on the robot's current power percentage or remaining battery life.

[0167] Comprehensive judgment refers to integrating multiple influencing factors to obtain the final task priority, which can be achieved by weighted summation.

[0168] In a specific embodiment, the above priority determination process can be implemented in this way.

[0169] In step S331, a task type priority table can be preset. For example, emergency spill cleanup tasks are assigned a base priority of 5 (highest), daily cleaning tasks in high-traffic areas are assigned a priority of 4, periodic cleaning tasks in general areas are assigned a priority of 3, maintenance cleaning tasks in low-traffic areas are assigned a priority of 2, and charging tasks are assigned a priority of 1 (lowest). When a conflict occurs, the conflicting robots are queried for their respective task types and their corresponding base priorities.

[0170] In step S332, the task urgency can be calculated based on the remaining time of the task. For example, the closer to the task deadline, the higher the urgency. An inverse proportional function or a piecewise function can be used to calculate the urgency score. For example, if the remaining time is less than 5 minutes, the urgency is 5; 5-15 minutes, the urgency is 4; 15-30 minutes, the urgency is 3; and more than 30 minutes, the urgency is 2.

[0171] In step S333, an environmental impact factor can be determined based on the type of area the robot is in and the overall state of the workshop. For example, in critical production areas or main transportation corridors, the environmental impact factor is set to high (e.g., a factor of 1.2); in general areas, it is set to medium (e.g., a factor of 1.0); and in non-critical areas, it is set to low (e.g., a factor of 0.8). If the overall congestion level in the workshop is high, the environmental impact factor of all tasks can be appropriately increased.

[0172] In step S334, the power impact factor can be determined based on the robot's current power level. For example, the factor value is 1.0 when the power level is above 80%, 0.9 when it is between 60% and 80%, 0.8 when it is between 40% and 60%, and 0.7 when it is below 40% (assuming that low power will reduce execution efficiency or require priority charging). In step S335, the basic task priority, task urgency score, environmental impact factor, and power impact factor can be comprehensively calculated. For example, a weighted summation method is used: final priority = weight 1 * basic task priority + weight 2 * task urgency + weight 3 * environmental impact factor + weight 4 * power impact factor, where the weights can be adjusted according to actual needs. The higher the calculated final priority value, the higher the task priority.

[0173] Through this specific calculation method, a quantified task priority can be obtained for subsequent path adjustment decisions.

[0174] Furthermore, it is characterized in that step S4 includes:

[0175] S41: acquiring, according to the task priorities, first current task information and first short-term planned path information of the low-priority robot involved in the conflict, and second short-term planned path information of the high-priority robot involved in the conflict;

[0176] S42: Obtaining restricted area information and access rules of the manufacturing workshop;

[0177] S43: Determine, based on the first short-term planned path information, the second short-term planned path information, the restricted area information, and the traffic rules, a feasible avoidance area or path segment for the low-priority robot within the future time window;

[0178] S44: Planning an adjusted path for the low-priority robot based on the first current task information, the feasible avoidance area or path segment, and the second short-term planned path information, where the adjusted path is used to avoid the high-priority robot.

[0179] This solution details how to implement a path adjustment process where a low-priority robot avoids a high-priority robot after spatial conflicts between robots are predicted and task priorities have been determined.

[0180] The core of this method is to intelligently determine the feasible avoidance options for the low-priority robot by comprehensively considering the path information of the conflicting parties, the task information of the low-priority robot, and the environmental constraints of the workshop, and plan an effective adjustment path based on these options.

[0181] Specifically: First, basic information for avoidance planning is obtained. By obtaining the first current task information and the original first short-term planned path information of the low-priority robot involved in the conflict based on the determined task priority, the status, target and original planned movement trajectory of the low-priority robot before avoidance can be understood.

[0182] At the same time, obtaining the second short-term planning path information of the high-priority robot involved in the conflict clarifies the spatial area or path segment that the low-priority robot needs to avoid, providing target information for subsequent avoidance analysis.

[0183] Next, the system obtains information about restricted areas and traffic rules within the manufacturing workshop, providing crucial environmental constraints for avoidance planning. This information defines the legal range of movement and behavioral norms within the workshop. These constraints must be adhered to when subsequently determining avoidance areas or path segments and planning path adjustments to ensure the safety and feasibility of avoidance maneuvers, preventing low-priority robots from entering dangerous areas or violating workshop regulations. The system then determines avoidance options for the low-priority robot. By combining the original path information of the low-priority robot, the path information of the high-priority robot, and information about restricted areas and traffic rules, the system calculates and determines which areas the low-priority robot can safely enter or which path segments it can move along within a future time window, successfully avoiding the high-priority robot while maintaining environmental constraints. The key concept here is "feasibility," which filters out infeasible or unsafe avoidance options, providing a valid candidate space for the final path planning. Finally, an avoidance path is generated. Based on the first current task information of the low-priority robot, combined with the determined feasible avoidance area or path segment (as the planning constraint or target space), and the second short-term planned path information of the high-priority robot (to ensure that the planned path can effectively avoid the high-priority robot), the system plans an adjusted path for the low-priority robot, thereby achieving orderly avoidance of the high-priority robot by the low-priority robot and reducing conflicts and congestion.

[0184] Please refer to Figure 2 、 Figure 3 A workshop robot path planning system based on ROS2 is applied to the steps of any of the above methods, and the system includes:

[0185] Acquisition module 201: Acquisition of current task information and short-term planning path information of multiple robots;

[0186] Prediction module 202: predicts whether there will be spatial conflicts among multiple robots in a future time window based on current task information and short-term planning path information;

[0187] Priority determination module 203: when a spatial conflict is predicted, determines the task priorities of the robots involved in the conflict based on the current task information;

[0188] Planning module 204: adjusts the short-term planned paths of robots involved in the conflict according to the task priorities so that the low-priority robots avoid the high-priority robots.

[0189] Among them, a module refers to a relatively independent software or hardware unit with specific functions in the system, which can be implemented by software processes, threads, function libraries, hardware circuits or their combinations.

[0190] Specifically, the acquisition module 201 refers to a unit responsible for receiving or reading data from an external source.

[0191] The prediction module 202 is a unit that analyzes and infers future states or events based on input data.

[0192] The priority determination module 203 is a unit that ranks objects by importance according to preset rules or input information.

[0193] The planning module 204 is a unit that generates an action plan or path based on the goal and constraints.

[0194] This system is implemented by decomposing the above method steps into different functional modules.

[0195] The acquisition module 201 is responsible for collecting real-time status information for all robots in the system, including details of their currently executing tasks and their respective planned short-term movement paths. This information forms the basis for the system's subsequent decision-making. The prediction module 202 receives the data provided by the acquisition module and uses it to analyze the robots' expected spatial occupancy over the next period of time, thereby determining whether there are potential spatial conflicts, such as path intersections or overlaps. When the prediction module detects a conflict, the priority determination module 203 is triggered. This module determines the relative importance of the tasks involved based on information about the robots' respective tasks, such as task type and timeliness, to determine their priority order. Finally, the planning module 204 adjusts the short-term planned paths of low-priority robots based on the results provided by the priority determination module. This adjustment aims to guide low-priority robots to avoid the expected paths of high-priority robots, thereby resolving spatial conflicts without affecting the execution of high-priority tasks.

[0196] The entire process forms a closed loop, with the system continuously acquiring information, making predictions, determining decisions, and adjusting, ensuring efficient and coordinated multi-robot operation in dynamic environments. This modular design allows the system to clearly implement each step of the method, effectively executing conflict prediction, priority determination, and path adjustment, thereby transforming the method into an operational system function.

[0197] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any actual relationship or order between these entities or operations.

[0198] The foregoing is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. Persons skilled in the art will readily appreciate that the present application may be modified and altered in various ways. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A workshop robot path planning method based on ROS2, characterized in that: The method comprises the steps of: S1: Obtain the current task information and short-term planning path information of multiple robots; S2: predicting whether there is a spatial conflict between multiple robots in a future time window based on the current task information and the short-term planning path information; S3: When a spatial conflict is predicted, determining the task priorities of the robots involved in the conflict based on the current task information; S4: According to the task priorities, adjust the short-term planned paths of the robots involved in the conflict so that the low-priority robot avoids the high-priority robot.

2. A workshop robot path planning method based on ROS2 according to claim 1, characterized in that: Step S1 includes: S11: receiving current task information published by multiple robots; S12: receiving messages published by multiple robots, each of which includes short-term planned path information, timestamp information associated with the short-term planned path information, and a format identifier representing the short-term planned path information; S13: performing format conversion on the short-term planned path information according to the format identifier to obtain short-term planned path information in a unified format; S14: Determine the short-term planned path information for subsequent conflict prediction from the short-term planned path information in a unified format according to the timestamp information.

3. A workshop robot path planning method based on ROS2 according to claim 1, characterized in that: Step S2 includes: S21: Obtaining restricted area information of the manufacturing workshop and access rules associated with the restricted area information; S22: Determine movement characteristic parameters of each of the multiple robots according to the current task information; S23: predicting the space occupancy information of the plurality of robots in a future time window based on the short-term planned path information, the restricted area information, the traffic rules, and the movement characteristic parameters; S24: Determine whether there is a spatial conflict between multiple robots in a future time window based on the space occupancy information.

4. A workshop robot path planning method based on ROS2 according to claim 3, characterized in that: Step S23 includes: S231: Acquire dynamic environmental information of the manufacturing workshop and real-time status information of multiple robots; S232: Determine execution deviation ranges of the plurality of robots within a future time window based on the short-term planned path information, the restricted area information, the traffic rules, the movement characteristic parameters, the environmental dynamic information, and the real-time state information; S233: Predicting the space occupancy information of the respective robots in the future time window based on the short-term planning path information, the restricted area information, the traffic rules, the movement characteristic parameters and the execution deviation range.

5. A workshop robot path planning method based on ROS2 according to claim 4, characterized in that: Step S232 includes: S2321: Obtaining real-time status information of multiple robots; S2322: Determine, based on the short-term planned path information, the restricted area information, the traffic rules, the movement characteristic parameters, and the environmental dynamic information, the expected spatial occupancy areas of the multiple robots along the short-term planned paths in a future time window; S2323: Determine, based on the real-time state information, additional space occupied by each of the multiple robots due to positioning uncertainty in a future time window; S2324: Combine the expected space occupation area and the additional space occupation area to obtain the execution deviation ranges of the multiple robots in the future time window.

6. A workshop robot path planning method based on ROS2 according to claim 4, characterized in that: Step S233 includes: S2331: Determine, along the short-term planned path, a sequence of expected trajectory points of multiple robots along the short-term planned path within a future time window according to the movement characteristic parameters, wherein the movement characteristic parameters include robot size information; S2332: For each trajectory point in the expected trajectory point sequence, determine an initial spatial occupation area of ​​the robot at the trajectory point based on the position of the trajectory point, the robot size information, and the execution deviation range corresponding to the trajectory point; S2333: Modify the initial space occupied area according to the restricted area information and the passage rule to obtain the space occupied area of ​​the robot at the trajectory point; S2334: Combining the corrected space occupation areas at the multiple trajectory points to obtain the space occupation information of the multiple robots in the future time window.

7. A workshop robot path planning method based on ROS2 according to claim 1, characterized in that: Step S3 includes: Obtaining current task information of each of the robots involved in the conflict, wherein the current task information includes task type information and task timeliness information; S31: Acquire the area information of each robot involved in the conflict and the overall status information of the workshop; S32: Acquire real-time status information of each robot involved in the conflict, wherein the real-time status information includes at least robot power information; S33: Comprehensively determine the task priorities of the robots involved in the conflict based on the task type information, the task timeliness information, the area information, the overall workshop status information, and the robot power information.

8. A workshop robot path planning method based on ROS2 according to claim 7, characterized in that: Step S33 includes: S331: Determine the basic task priorities of the robots involved in the conflict according to the task type information; S332: Calculating the task urgency of each of the robots involved in the conflict based on the task timeliness information; S333: Determining the environmental impact factors of the robots involved in the conflict based on the area information and the overall state information of the workshop; S334: Determine the power impact factor of each of the robots involved in the conflict based on the robot power information; S335: Comprehensively determine the task priorities of the respective robots involved in the conflict based on the basic task priority, the task urgency, the environmental impact factor, and the power impact factor.

9. A workshop robot path planning method based on ROS2 according to claim 1, characterized in that: Step S4 includes: S41: acquiring, according to the task priorities, first current task information and first short-term planned path information of the low-priority robot involved in the conflict, and second short-term planned path information of the high-priority robot involved in the conflict; S42: Obtaining restricted area information and access rules of the manufacturing workshop; S43: Determine, based on the first short-term planned path information, the second short-term planned path information, the restricted area information, and the traffic rules, a feasible avoidance area or path segment for the low-priority robot within a future time window; S44: Planning an adjustment path for the low-priority robot based on the first current task information, the feasible avoidance area or path segment, and the second short-term planned path information, wherein the adjustment path is used to avoid the high-priority robot.

10. A workshop robot path planning system based on ROS2, characterized in that: In the steps of the method according to any one of claims 1 to 9, the system comprises: Acquisition module: obtains the current task information and short-term planning path information of multiple robots; Prediction module: predicts whether there is spatial conflict between multiple robots in a future time window based on the current task information and the short-term planning path information; Priority determination module: when a spatial conflict is predicted, determining the task priority of the robots involved in the conflict based on the current task information; Planning module: According to the task priorities, adjust the short-term planning paths of the robots involved in the conflict so that the low-priority robots avoid the high-priority robots.

Images