Quadruped robot path planning method and system under multi-signal vision assistance

Abstract

The invention relates to a quadruped robot path planning method and system under multi-signal vision aide.The quadruped robot path planning method under multi-signal vision aide.The quadruped robot path planning method under multi-signal vision aide.The quadruped robot path planning method comprises the steps that when it is detected that an attitude sensor detects that head movement of a robot meets a preset track, a camera and a GPS are controlled to be initialized; in response to the first control signal, controlling the quadruped robot to move; in response to the second control signal, acquiring GPS positioning of the robot at the first position and acquiring a first environment image; storing the GPS positioning, the environment image and a first motion direction in response to a second control signal as a first target position; and in response to a third control signal, moving to the vicinity of the first position based on the GPS positioning, and based on the first environment image and a first motion direction in response to the second control signal, moving to a first position and facing the first motion direction. According to the invention, the robot can accurately move to the destination in an unfamiliar environment.

Description

Technical Field

[0001] This invention relates to the field of robot control, specifically to a method and system for path planning of quadruped robots with multi-signal vision assistance. Background Technology

[0002] Legged robots are equipped with multiple legs. By controlling the lifting or lowering of the legs through the joints on the legs, the legged robot can move and thus simulate the walking of animals or people.

[0003] Currently, in order to control legged robots to move accurately to the target position, it is necessary to store high-precision environmental maps. This is difficult to achieve for robots that often work in unfamiliar environments, because high-precision maps need to be collected in advance. Summary of the Invention

[0004] This invention addresses the problem of how to control a legged robot to move accurately to a target position.

[0005] In a first aspect, this application provides a path planning method for a quadruped robot under multi-signal vision assistance, characterized in that it is applied to a quadruped robot equipped with a camera, GPS, and an attitude sensor, and the method includes: When the posture sensor detects that the robot's head movement meets a preset trajectory, the camera and GPS are initialized. In response to the first control signal, the movement of the quadruped robot is controlled; In response to the second control signal, the robot's GPS location at the first position and the first environmental image are acquired; The GPS positioning, the environmental image, and the first direction of motion in response to the second control signal are stored as the first target location; and... In response to the third control signal, the device moves to the vicinity of the first position based on the GPS positioning. Based on the first environmental image and the first direction of motion when responding to the second control signal, the object moves to the first position and faces the first direction of motion.

[0006] In some embodiments, the first control signal is a control signal automatically generated by the robot based on an environmental map; The second and third control signals are control signals generated based on user input.

[0007] In some embodiments, moving to a first position and toward the first direction of motion based on the first environmental image and a first direction of motion in response to a second control signal includes: Acquire second environmental images around the first location; The first location is determined based on the matching degree between the first environmental image and the second environmental image; Move to the first position and face the first direction of movement.

[0008] In some embodiments, determining the first location based on the matching degree between the first environmental image and the second environmental image includes: Multiple first point cloud points are determined based on the first environmental image; Multiple second point cloud points were determined based on the second environmental image; The first position is determined by matching the first point cloud point and the second point cloud point.

[0009] In some embodiments, the number of the first point cloud points is less than or equal to 200.

[0010] In some embodiments, the number of the second point cloud points is less than or equal to 200.

[0011] In some embodiments, moving to the vicinity of the first location based on the GPS positioning in response to a third control signal includes: If the robot cannot obtain its current GPS location, it will move to the target location based on the environmental images captured by the camera. When the current GPS position is acquired at the target location, the relative position of the robot and the GPS position of the first location is determined, and the robot is controlled to move to the GPS position of the first location.

[0012] In some embodiments, the quadruped robot path planning method under multi-signal vision assistance further includes: In response to the first control signal, while controlling the movement of the quadruped robot, the GPS location information of the robot at each position within a preset time before moving to the current position is updated; If the robot cannot collect the current GPS location, the target location is the location with the highest number of satellites searched among the GPS location information of various locations within a preset time period.

[0013] In some embodiments, the target location is an open area.

[0014] Secondly, this application provides a quadruped robot path planning system under multi-signal vision assistance, characterized in that it includes: a memory storing a quadruped robot path planning program; and one or more processors configured to implement the above-described method when executing the quadruped robot path planning program.

[0015] This application records information about a first position during the robot's movement, either autonomously or manually, after initialization. This information includes GPS positioning, the environmental image, and the first direction of movement when responding to a second control signal. This allows the robot to first move to the vicinity of the first position, and then, based on the first environmental image and the real-time acquired second environmental map, control the robot to move precisely to the first position, with the robot in a first orientation at the first position. Attached Figure Description

[0016] Figure 1 This is a flowchart of an embodiment of the path planning method for a quadruped robot under multi-signal vision assistance according to this application; Figure 2 This is a flowchart of another embodiment of the path planning method for quadruped robots under multi-signal vision assistance of this application; Figure 3 This is a flowchart of another embodiment of the path planning method for quadruped robots under multi-signal vision assistance of this application. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0019] In the description of this invention, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.

[0020] Example 1 In a first aspect, this application provides a path planning method for a quadruped robot under multi-signal vision assistance, characterized in that it is applied to a quadruped robot equipped with a camera, GPS, and an attitude sensor, and the method includes: S100: When the posture sensor detects that the robot's head movement meets a preset trajectory, control the camera and GPS to initialize; For example, an IMU is installed in the head of the robot, which controls the robot to initialize when the user rotates the robot's head in a preset manner.

[0021] The preset methods can be: three circles to the left + three circles to the right, one circle to the left + one circle to the right, or other predetermined trigger methods, as long as they are easy to use and not prone to accidental touches.

[0022] S200, In response to the first control signal, control the movement of the quadruped robot; The first control signal can be triggered by the user via a remote control, which controls the robot to move forward, backward, left, right, etc.; the first control signal can also be the robot's autonomous movement based on the environment, such as automatically moving to the destination.

[0023] S300, in response to the second control signal, acquires the robot's GPS positioning at the first location and acquires the first environmental image; The second control signal can be a task point triggered by the user, after which the robot needs to move to the first position and perform the task in the first orientation.

[0024] S400, store the GPS positioning, the environmental image, and the first direction of motion in response to the second control signal as a first target position; and... In this step, a first position sequence, i.e., multiple first positions, can be recorded, and the robot moves to each first position to perform the task. The information of each first position can be stored in a structured manner, i.e., it includes GPS positioning, the environmental image, and the first direction of movement in response to the second control signal.

[0025] S500, in response to the third control signal, moves to the vicinity of the first position based on the GPS positioning; It should be noted that GPS positioning has a certain margin of error, such as 0.5 meters, making it difficult to accurately move to the first position; while relying entirely on vision to move to the first position requires the robot to construct a complete environmental map.

[0026] Therefore, this application first moves the robot to the vicinity of the first position, and then controls the robot to move precisely to the first position based on the first environmental image and the real-time acquired second environmental map.

[0027] S600: Based on the first environmental image and the first direction of motion when responding to the second control signal, move to the first position and face the first direction of motion.

[0028] This application records information about a first position during the robot's movement, either autonomously or manually, after initialization. This information includes GPS positioning, the environmental image, and the first direction of movement when responding to a second control signal. This allows the robot to first move to the vicinity of the first position, and then, based on the first environmental image and the real-time acquired second environmental map, control the robot to move precisely to the first position, with the robot in a first orientation at the first position.

[0029] In some embodiments, the first control signal is a control signal automatically generated by the robot based on an environmental map; the second and third control signals are control signals generated based on user input.

[0030] In some embodiments, S600, based on the first environmental image and the first direction of motion in response to the second control signal, moves to a first position with the orientation being the first direction of motion, including: S601. Acquire a second environmental image around the first location; The second environmental image was captured in real time during the robot's movement; the first environmental image was pre-stored in the memory.

[0031] S602. Determine the first location based on the matching degree between the first environmental image and the second environmental image; The pixels of the first and second environmental images can be directly matched, and then the robot S603 can be controlled to move to the first position and face the first direction of movement.

[0032] In other embodiments, point clouds can also be used for matching, and then the robot S603 can be controlled to move to a first position and face a first direction of movement. Exemplarily, S602, determining the first position based on the matching degree of the first environmental image and the second environmental image includes: S6021. Determine multiple first point cloud points based on the first environmental image; S6022. Determine multiple second point cloud points based on the second environmental image; S6023. Match the first point cloud point and the second point cloud point to determine the first position.

[0033] This application converts environmental images into point clouds, which effectively reduces data processing compared to pixel-based matching. In this case, the stored data for the first environmental image is the first point cloud data, instead of storing the first image itself. In some embodiments, the number of the first point cloud data is less than or equal to 200. In some embodiments, the number of the second point cloud data is less than or equal to 200. The number of the first point cloud data and the number of the second point cloud data are the same.

[0034] In some embodiments, S500, in response to a third control signal, moving to the vicinity of the first location based on the GPS positioning includes: S501. If the robot cannot obtain the current GPS location, it will move to the target location based on the environmental images collected by the camera. The target location can be a location with a good GPS signal. To determine the location with a good signal, in this application, while controlling the movement of the quadruped robot in response to the first control signal, the GPS location information of each position of the robot within a preset time period before moving to the current position can be updated; if the robot cannot collect the current GPS positioning, the target location is: the position with the highest number of satellites searched among the GPS location information of each position within the preset time period.

[0035] In order to determine a location with good signal, this application can also be based on the environmental images collected by the robot, and move to a location without building obstruction, where the GPS signal is good, that is, the target location is an open area.

[0036] S502. When the current GPS positioning is collected at the target location, determine the relative position of the robot and the GPS positioning of the first location, and control the robot to move to the GPS positioning of the first location.

[0037] This application is mainly applied to movement in unfamiliar environments. In this case, the robot can build a map in real time based on the images captured by the camera, i.e., SLAM, and then move. During the movement, GPS failure is likely to occur, and the robot's position cannot be known. You can use the historical location with GPS signal, or you can use the solution proposed in this application: move to the location with the best GPS signal. Actual tests show that compared with using the historical location with GPS signal, moving to the location with the best GPS signal can obtain GPS signal faster.

[0038] Example 2 This application provides a quadruped robot path planning system under multi-signal vision assistance, characterized in that it includes: a memory storing a quadruped robot path planning program; and one or more processors configured to execute the quadruped robot path planning program in the following manner: The method includes: S100: When the posture sensor detects that the robot's head movement meets a preset trajectory, control the camera and GPS to initialize; S200, In response to the first control signal, control the movement of the quadruped robot; S300, in response to the second control signal, acquires the robot's GPS positioning at the first location and acquires the first environmental image; S400, store the GPS positioning, the environmental image, and the first direction of motion in response to the second control signal as a first target position; and... S500, in response to the third control signal, moves to the vicinity of the first position based on the GPS positioning; S600: Based on the first environmental image and the first direction of motion when responding to the second control signal, move to the first position and face the first direction of motion.

[0039] In some embodiments, the first control signal is a control signal automatically generated by the robot based on an environmental map; the second and third control signals are control signals generated based on user input.

[0040] In some embodiments, S600, based on the first environmental image and the first direction of motion in response to the second control signal, moves to a first position with the orientation being the first direction of motion, including: S601. Acquire a second environmental image around the first location; S602. Determine the first location based on the matching degree between the first environmental image and the second environmental image; S603, Move to the first position and face the first direction of movement.

[0041] In some embodiments, S602, determining the first location based on the matching degree of the first environmental image and the second environmental image includes: S6021. Determine multiple first point cloud points based on the first environmental image; S6022. Determine multiple second point cloud points based on the second environmental image; S6023. Match the first point cloud point and the second point cloud point to determine the first position.

[0042] In some embodiments, the number of the first point cloud points is less than or equal to 200.

[0043] In some embodiments, the number of the second point cloud points is less than or equal to 200.

[0044] In some embodiments, S500, in response to a third control signal, moving to the vicinity of the first location based on the GPS positioning includes: S501. If the robot cannot obtain the current GPS location, it will move to the target location based on the environmental images collected by the camera. S502. When the current GPS positioning is collected at the target location, determine the relative position of the robot and the GPS positioning of the first location, and control the robot to move to the GPS positioning of the first location.

[0045] In some embodiments, the quadruped robot path planning method under multi-signal vision assistance further includes: In response to the first control signal, while controlling the movement of the quadruped robot, the GPS location information of the robot at each position within a preset time before moving to the current position is updated; If the robot cannot collect the current GPS location, the target location is the location with the highest number of satellites searched among the GPS location information of various locations within a preset time period.

[0046] In some embodiments, the target location is an open area.

[0047] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0048] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0049] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0050] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0051] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0052] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0053] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A path planning method for a quadruped robot under multi-signal vision assistance, characterized in that, The method, applied to a quadruped robot equipped with a camera, GPS, and an attitude sensor, includes: When the posture sensor detects that the robot's head movement meets a preset trajectory, the camera and GPS are initialized. In response to the first control signal, the movement of the quadruped robot is controlled; In response to the second control signal, the robot's GPS location at the first position and the first environmental image are acquired; The GPS positioning, the environmental image, and the first direction of motion in response to the second control signal are stored as the first target location; and... In response to the third control signal, the device moves to the vicinity of the first position based on the GPS positioning. Based on the first environmental image and the first direction of motion when responding to the second control signal, the object moves to the first position and faces the first direction of motion.

2. The path planning method for a quadruped robot under multi-signal vision assistance as described in claim 1, characterized in that, The first control signal is a control signal automatically generated by the robot based on the environmental map; The second and third control signals are control signals generated based on user input.

3. The path planning method for a quadruped robot under multi-signal vision assistance as described in claim 1, characterized in that, Based on the first environmental image and the first direction of motion in response to the second control signal, the object moves to a first position, with its orientation being the first direction of motion, including: Acquire second environmental images around the first location; The first location is determined based on the matching degree between the first environmental image and the second environmental image; Move to the first position and face the first direction of movement.

4. The path planning method for a quadruped robot under multi-signal vision assistance as described in claim 3, characterized in that, Determining the first location based on the matching degree between the first environmental image and the second environmental image includes: Multiple first point cloud points are determined based on the first environmental image; Multiple second point cloud points were determined based on the second environmental image; The first position is determined by matching the first point cloud point and the second point cloud point.

5. The path planning method for a quadruped robot under multi-signal vision assistance as described in claim 4, characterized in that, The number of the first point cloud points is less than or equal to 200.

6. The path planning method for a quadruped robot under multi-signal vision assistance as described in claim 1, characterized in that, The number of the second point cloud points is less than or equal to 200.

7. The path planning method for a quadruped robot under multi-signal vision assistance as described in claim 1, characterized in that, In response to a third control signal, moving to the vicinity of the first location based on the GPS positioning includes: If the robot cannot obtain its current GPS location, it will move to the target location based on the environmental images captured by the camera. When the current GPS position is acquired at the target location, the relative position of the robot and the GPS position of the first location is determined, and the robot is controlled to move to the GPS position of the first location.

8. The path planning method for a quadruped robot under multi-signal vision assistance as described in claim 7, characterized in that, Also includes: In response to the first control signal, while controlling the movement of the quadruped robot, the GPS location information of the robot at each position within a preset time before moving to the current position is updated; If the robot cannot collect the current GPS location, the target location is the location with the highest number of satellites searched among the GPS location information of various locations within a preset time period.

9. The path planning method for a quadruped robot under multi-signal vision assistance as described in claim 7, characterized in that, The target location is an open area.

10. A path planning system for a quadruped robot under multi-signal vision assistance, characterized in that, include: The memory stores the path planning program for the quadruped robot. One or more processors, when configured to execute the quadruped robot path planning program, implement the method as described in any one of claims 1-9.

Images