A method for a mobile robot to pass through a narrow passage and a mobile robot

Abstract

The application discloses a kind of mobile robot narrow passage passing method and its mobile robot, it includes the following steps: whether the target point of executing task is in narrow passage area;If, according to the target point of executing task, global path planning is carried out, and narrow passage area trajectory is obtained;According to narrow passage area trajectory, enter narrow passage area, reach target point and complete task;When mobile robot leaves narrow passage area, adopt the strategy of cheating local planner, the orientation of mobile robot is rotated 180 degrees by local planner, and control quantity linear velocity, angular velocity are all taken reverse;Mobile robot uses narrow passage area trajectory to leave narrow passage area, above technical scheme makes mobile robot to tail end advance way through narrow passage area trajectory and leave narrow passage area, improve the efficiency and flexibility of mobile robot out of narrow passage area.

Description

Technical Field

[0001] This invention relates to the field of mobile robot technology, and in particular to a method for a mobile robot to pass through narrow passages and the mobile robot thereof. Background Technology

[0002] Mobile robots typically plan their mission paths autonomously according to pre-defined instructions. If they detect obstacles or narrow passages during their journey, they usually employ obstacle avoidance techniques to circumvent them. When a mobile robot enters a narrow passageway (such as a hotel room corridor or kitchen aisle where the width of the path is limited), if it finds itself unable to proceed further and cannot turn around due to the narrowness, it will attempt to reverse to exit the passage. However, due to the complex environment of narrow passages—such as winding paths or obstacles blocking the robot's path—it is easy for the robot to become trapped while trying to exit. Therefore, improving the success rate of robots exiting narrow passages has become a pressing technical problem that needs to be solved.

[0003] Patent CN 114355887 B discloses a method, apparatus, robot, and storage medium for robot passage through narrow passages. The method includes: if the robot does not slip, indicating no obstacle behind it, it will exit the narrow passage based on a first detection collected by the robot, thus ensuring normal exit without being trapped and improving the success rate of exiting the narrow passage; conversely, if the robot slips, indicating an obstacle behind it, a reference path is planned, and the robot exits the narrow passage according to the reference path, thus avoiding the phenomenon of being unable to exit the narrow passage due to an obstacle behind it, further improving the success rate of exiting the narrow passage. While the above technical solution solves the problem of the robot's success rate in exiting narrow passages, this method involves the robot reversing out of the narrow passage, which is inefficient and lacks flexibility. Summary of the Invention

[0004] Therefore, it is necessary to provide a method for mobile robots to pass through narrow passages, so as to solve the problem of low efficiency and flexibility of mobile robots reversing out of narrow passages in reversing mode.

[0005] To achieve the above objectives, the present invention provides a method for a mobile robot to pass through narrow passages, comprising the following steps:

[0006] Determine whether the goal point of the mobile robot's task is within the narrow passage area;

[0007] If present, then based on the goalpoint of the mobile robot's task, global path planning is performed to obtain the trajectory pointssets for the narrow passage area;

[0008] The mobile robot enters the narrow passage area by following the trajectory pointsets and reaches the goalpoint to complete the task.

[0009] When the mobile robot leaves the narrow passage area, a strategy of deceiving the local planner is adopted. The local planner rotates the orientation of the mobile robot by 180 degrees and reverses the linear velocity and angular velocity of the control quantities.

[0010] The mobile robot uses pointsets to leave the narrow area.

[0011] Furthermore, before determining whether the target point for the mobile robot to perform the task is within the narrow passage area, the process also includes creating a scene map and marking the narrow passage area in the scene map.

[0012] Furthermore, the mobile robot determines whether the target point of the task is within the narrow passage area using the ray method. Starting from the target point, a ray is drawn parallel to one side of the narrow passage area. The number of intersections between the ray and the narrow passage area is calculated. If the number of intersections is odd, it proves that the target point is within the narrow passage area; otherwise, it proves that the target point is not within the narrow passage area.

[0013] Furthermore, the narrow passage area trajectory pointssets are the trajectory from the last trajectory point pointn before the mobile robot enters the narrow passage area to the target point goalpoint.

[0014] Furthermore, when the mobile robot enters the narrow passage area according to the narrow passage area trajectory pointsets, if the scene changes within the narrow passage area before reaching the goal point to complete the task, the path within the narrow passage area is replanned and the narrow passage area trajectory pointsets are updated.

[0015] Furthermore, after the mobile robot enters the narrow passage area according to the narrow passage area trajectory pointsets, before reaching the target point to complete the task, it also includes determining whether the mobile robot has reached the target point.

[0016] If the target is reached, the mobile robot will perform the task; otherwise, it will continue to travel along the narrow path.

[0017] Furthermore, after the mobile robot reaches the target point, the system further includes determining whether the orientation of the mobile robot matches the orientation of the target point. If they match, the mobile robot executes the task; otherwise, the orientation of the mobile robot is adjusted.

[0018] Furthermore, the determination of whether the mobile robot has reached the target point uses the Euclidean distance method to determine whether the robot's coordinates are within the allowable tolerance range of the target point. If the robot is within the allowable tolerance range of the target point, it means that the mobile robot has reached the target point.

[0019] Furthermore, adjusting the orientation of the mobile robot includes the following steps:

[0020] If the deviation between the orientation of the mobile robot and the orientation of the target point is within 90 degrees, then the mobile robot rotates to the target point.

[0021] Otherwise, rotate the orientation of the goalpoint by 180 degrees, and the mobile robot will rotate to the correct position according to the orientation of the goalpoint.

[0022] A mobile robot that applies the above-described method for navigating narrow passages.

[0023] Unlike existing technologies, the above technical solution first obtains the narrow-area trajectory pointssets for the mobile robot to perform its tasks. The mobile robot then moves forward through the narrow-area trajectory pointssets to reach the target point. After completing the task at the target point, a strategy of deceiving the local planner is adopted. The local planner modifies the mobile robot's orientation, linear velocity, and angular velocity by rotating the orientation by 180 degrees and inverting the control quantities linear velocity and angular velocity. This makes the local planner believe that the mobile robot is still moving forward, causing the mobile robot to leave the narrow-area area by moving forward through the narrow-area trajectory pointssets, thus improving the efficiency and flexibility of the mobile robot in leaving the narrow-area area. Attached Figure Description

[0024] Figure 1 This is a flowchart of the mobile robot narrow passage method according to the present invention;

[0025] Figure 2 This is a flowchart of the mobile robot narrow passage method according to the present invention. Detailed Implementation

[0026] To explain in detail the technical content, structural features, objectives, and effects of the technical solution, the following description is provided in conjunction with specific embodiments and accompanying drawings.

[0027] In this document, the term "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The term "embodiment" appearing in various places throughout the specification does not necessarily refer to the same embodiment, nor does it specifically limit its independence or connection with other embodiments. In principle, in this application, as long as there are no technical contradictions or conflicts, the technical features mentioned in each embodiment can be combined in any way to form corresponding implementable technical solutions.

[0028] Unless otherwise defined, the technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the use of related terms herein is merely for the purpose of describing particular embodiments and is not intended to limit this application.

[0029] In the description of this application, the term "and / or" is used to describe the logical relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A exists, B exists, and A and B exist simultaneously. Additionally, the character " / " in this document generally indicates that the preceding and following objects have an "or" logical relationship.

[0030] In this application, terms such as “first” and “second” are used only to distinguish one entity or operation from another, and do not necessarily require or imply any actual quantity, hierarchy or order relationship between these entities or operations.

[0031] Unless otherwise specified, the use of terms such as “comprising,” “including,” “having,” or other similar expressions in this application is intended to cover non-exclusive inclusion, which does not exclude the presence of additional elements in a process, method, or product that includes the stated elements, such that a process, method, or product that includes a list of elements may include not only those defined elements but also other elements not expressly listed, or elements inherent to such a process, method, or product.

[0032] Similar to the interpretation in the Patent Examination Guidelines, in this application, expressions such as "greater than," "less than," and "exceeding" are understood to exclude the stated number; expressions such as "above," "below," and "within" are understood to include the stated number. Furthermore, in the description of the embodiments in this application, "multiple" means two or more (including two), and similar expressions related to "multiple" are also interpreted in this way, such as "multiple groups" and "multiple times," unless otherwise explicitly specified.

[0033] In the description of the embodiments of this application, the space-related expressions used, such as "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "vertical," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential," indicate the orientation or positional relationship based on the orientation or positional relationship shown in the specific embodiments or drawings. They are only for the purpose of describing the specific embodiments of this application or for the reader's understanding, and do not indicate or imply that the device or component referred to must have a specific position, a specific orientation, or be constructed or operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of this application.

[0034] Unless otherwise expressly specified or limited, the terms "installation," "connection," "linking," "fixing," and "setting," as used in the description of the embodiments of this application, should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral setting; it can be a mechanical connection, an electrical connection, or a communication connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be the internal connection of two components or the interaction between two components. For those skilled in the art to which this application pertains, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0035] See Figure 1 and Figure 2 As shown, the present invention provides a method for a mobile robot to pass through narrow passages, which includes the following steps:

[0036] Determine whether the goal point of the mobile robot's task is within the narrow passage area;

[0037] If present, then based on the goalpoint of the mobile robot's task, global path planning is performed to obtain the trajectory pointssets for the narrow passage area;

[0038] The mobile robot enters the narrow passage area by following the trajectory pointsets and reaches the goalpoint to complete the task.

[0039] When the mobile robot leaves the narrow passage area, a strategy of deceiving the local planner is adopted. The local planner rotates the orientation of the mobile robot by 180 degrees, and the linear velocity and angular velocity of the control quantities are reversed. The robot then leaves the narrow passage area using the narrow passage area trajectory pointsets.

[0040] The above technical solution first obtains the narrow-area trajectory pointssets for the mobile robot to perform the task. The mobile robot moves forward through the narrow-area trajectory pointssets to reach the target point. After completing the task at the target point, a strategy of deceiving the local planner is adopted. The local planner modifies the orientation, linear velocity, and angular velocity of the mobile robot, rotates the orientation by 180 degrees, and reverses the control quantities linear velocity and angular velocity. This makes the local planner think that the mobile robot is still moving forward, so that the mobile robot leaves the narrow-area area by moving forward through the narrow-area trajectory pointssets, thereby improving the efficiency and flexibility of the mobile robot leaving the narrow-area area. The aforementioned scene map is a scene map pre-built by the mobile robot; the aforementioned narrow passage area can be semantically annotated on the scene map, that is, semantically annotated on the scene map through a scene feature model set (obtained by deep learning training on obvious non-dynamic features of the scene); the aforementioned global path planning is the path planning performed by the mobile robot to perform the task, obtaining all the trajectories traversed by the mobile robot to perform the task, and the trajectory is composed of several trajectory points connected together; the aforementioned narrow passage area trajectory pointsets is the trajectory passing through the narrow passage area, that is, the trajectory from the last trajectory point pointn before the mobile robot enters the narrow passage area to the target point goalpoint.

[0041] The above-mentioned annotation of the narrow passage area in the scene map involves semantic annotation of the narrow passage area by drawing closed regions. That is, the narrow passage area is divided into relatively regular closed shapes (such as rectangles) in the scene map, and semantic annotation is performed on these closed shapes. Semantic annotation of the narrow passage area by drawing closed regions is helpful in determining whether the target point of the mobile robot is within the narrow passage area. For example, it can be determined by whether the coordinates of the target point are within the narrow passage area. Preferably, the target point is determined by the ray method. That is, starting from the target point, a ray is drawn parallel to one edge of the narrow passage area, and the number of intersections between the ray and the narrow passage area is calculated. If the number of intersections is odd, it proves that the target point is within the narrow passage area; otherwise, it proves that the target point is not within the narrow passage area. The ray method is relatively simple to implement and has a fast calculation speed.

[0042] If the scene changes significantly during the mobile robot's task execution, and an updated map cannot be used for navigation, localization anomalies can easily occur. This can lead to the robot losing its ability to recognize scene changes and getting stuck in a loop of optimal localization matching. To address this, after the mobile robot enters a narrow passage area according to its trajectory pointssets, if the scene changes within the narrow passage area before reaching the goal point to complete the task, the path within the narrow passage area is replanned, and the narrow passage trajectory pointssets are updated. This solves the problem of mobile robot localization anomalies and getting stuck in a loop of optimal localization matching when the scene changes during execution and the map cannot be updated in time. It ensures the mobile robot's environmental awareness during task execution, increases safety and reliability, enables effective pose estimation and route planning in dynamic environments, and meets the real-time obstacle avoidance requirements of the mobile robot.

[0043] After the mobile robot enters the narrow passage area according to the narrow passage trajectory (pointsets), before reaching the goal point to complete the task, to prevent the mobile robot from executing the task before reaching the goal point, thus causing the task to fail, some implementations also include determining whether the mobile robot has reached the goal point; if it has, the mobile robot executes the task; otherwise, it continues to travel along the narrow passage trajectory until it reaches the goal point; this ensures that the mobile robot reaches the goal point and that the task is successfully executed. In some embodiments, in addition to determining whether the mobile robot has reached the goal point, it is also necessary to determine whether the orientation of the mobile robot matches the orientation of the goal point. This is to prevent the orientation of the goal point from being inconsistent with the orientation of the mobile robot, which could lead to the inability to perform the task normally. That is, after the mobile robot reaches the goal point, it is also necessary to determine whether the orientation of the mobile robot matches the orientation of the goal point. If they match, the mobile robot performs the task; otherwise, the orientation of the mobile robot is adjusted so that the orientation of the mobile robot is the same as the orientation of the goal point, ensuring that the mobile robot can successfully complete the task when it reaches the goal point.

[0044] In the above, the Euclidean distance method can be used to determine whether the robot's coordinates are within the allowable tolerance range of the target point. If the robot is within the allowable tolerance range of the target point, it means that the mobile robot has reached the target point.

[0045] The aforementioned adjustment of the mobile robot's orientation can be achieved by rotating the robot by the same angle as the deviation between its current orientation and the target point's orientation. To improve the efficiency of adjusting the mobile robot's orientation, some embodiments include the following steps:

[0046] If the deviation between the orientation of the mobile robot and the orientation of the target point is within 90 degrees, then the mobile robot rotates to the target point.

[0047] Otherwise, rotate the orientation of the goalpoint by 180 degrees, and the mobile robot will rotate to the correct position according to the orientation of the goalpoint.

[0048] Reducing the rotation angle of the mobile robot makes its rotation more flexible in narrow areas, thereby improving the efficiency of the mobile robot in performing tasks.

[0049] A mobile robot employs the aforementioned method for navigating narrow passages. The mobile robot exits the narrow passage area by moving its tail forward along a trajectory of pointsets, and then reverses direction to exit the narrow passage, thereby improving the efficiency and flexibility of the mobile robot exiting the narrow passage area.

[0050] It should be noted that although the above embodiments have been described herein, this does not limit the scope of patent protection of the present invention. Therefore, any changes and modifications made to the embodiments described herein based on the innovative concept of the present invention, or equivalent structural or procedural transformations made using the content of the present invention's specification and drawings, directly or indirectly applying the above technical solutions to other related technical fields, are all included within the scope of patent protection of the present invention.

Claims

1. A method for a mobile robot to pass through narrow passages, characterized in that, Includes the following steps: Determine whether the goal point of the mobile robot's task is within the narrow passage area; If present, then based on the goalpoint of the mobile robot's task, global path planning is performed to obtain the trajectory pointssets for the narrow passage area; The mobile robot enters the narrow passage area by following the trajectory pointsets and reaches the goalpoint to complete the task. When the mobile robot leaves the narrow passage area, a strategy of deceiving the local planner is adopted. The local planner modifies the orientation, linear velocity, and angular velocity of the mobile robot, rotates the orientation by 180 degrees, and reverses the control quantities linear velocity and angular velocity. This makes the local planner think that the mobile robot is still moving forward, so that the mobile robot leaves the narrow passage area by passing through the trajectory pointssets of the narrow passage area in a tail-forward manner.

2. The method for mobile robots to pass through narrow passages according to claim 1, characterized in that, Before determining whether the goal point for the mobile robot to perform the task is within the narrow passage area, the process also includes creating a scene map and marking the narrow passage area in the scene map.

3. The method for mobile robots to pass through narrow passages according to claim 1, characterized in that, The mobile robot determines whether the target point of the task is within the narrow passage area using the ray method. Starting from the target point, a ray is drawn parallel to one side of the narrow passage area. The number of intersections between the ray and the narrow passage area is calculated. If the number of intersections is odd, it proves that the target point is within the narrow passage area; otherwise, it proves that the target point is not within the narrow passage area.

4. The method for mobile robots to pass through narrow passages according to claim 1, characterized in that, The narrow passage area trajectory pointssets refers to the trajectory from the last trajectory point pointn before the mobile robot enters the narrow passage area to the target point goalpoint.

5. The method for mobile robots to pass through narrow passages according to claim 1, characterized in that, Once the mobile robot enters the narrow passage area according to the narrow passage area trajectory pointsets, if the scene changes within the narrow passage area before reaching the goal point to complete the task, the path within the narrow passage area will be replanned and the narrow passage area trajectory pointsets will be updated.

6. The method for mobile robots to pass through narrow passages according to claim 1, characterized in that, After the mobile robot enters the narrow passage area according to the narrow passage area trajectory pointsets, before reaching the target point to complete the task, it also includes determining whether the mobile robot has reached the target point. If the target is reached, the mobile robot will perform the task; otherwise, it will continue to travel along the narrow path.

7. The method for mobile robots to pass through narrow passages according to claim 6, characterized in that, After the mobile robot reaches the target point, the system further determines whether the orientation of the mobile robot matches the orientation of the target point. If they match, the mobile robot executes the task; otherwise, the orientation of the mobile robot is adjusted.

8. The method for mobile robots to pass through narrow passages according to claim 6, characterized in that, The determination of whether the mobile robot has reached the target point is made using the Euclidean distance method. If the robot's coordinates are within the allowable tolerance range of the target point, then the mobile robot has reached the target point.

9. The method for a mobile robot to pass through a narrow passage according to claim 7, characterized in that, Adjusting the position of the mobile robot includes the following steps: If the deviation between the orientation of the mobile robot and the orientation of the target point is within 90 degrees, then the mobile robot rotates to the target point. Otherwise, rotate the orientation of the goalpoint by 180 degrees, and the mobile robot will rotate to the correct position according to the orientation of the goalpoint.

10. A mobile robot, characterized in that: The method for mobile robots to pass through narrow passages according to any one of claims 1 to 9 is applied.

Images