Mechanical arm motion track planning method and device and storage medium

Abstract

The invention discloses a mechanical arm motion track planning method and device and a storage medium. The method comprises the steps that the target position of a moving object at the target moment is obtained, and the current pose of a mechanical arm at the current moment is obtained; based on the target position and the current pose, a single-point planning mode is adopted, and a first track of the mechanical arm clamping jaw reaching the target position and a target pose of the mechanical arm clamping jaw located at the target position in the first track are obtained through planning; based on the current pose and the target pose, a multi-point planning mode is adopted, and a second track is obtained through planning; and determining a target trajectory based on the first trajectory and the second trajectory. According to the method, the grabbing path of the moving object can be reasonably and accurately planned.

Description

Technical Field

[0001] The present invention relates to the technical field of trajectory planning, and in particular to a method, device and storage medium for planning the motion trajectory of a robot arm. Background Art

[0002] With the emergence of embodied intelligence technology, the application scenarios of robotic arms are increasing. The grasping of robotic arms is not only limited to the grasping of static objects, but also the demand for grasping dynamic objects is increasing.

[0003] Therefore, there is an urgent need for a robot arm motion trajectory planning method to solve the problem that the existing technology cannot reasonably and accurately plan the grasping path of the moving object. Summary of the invention

[0004] In view of this, the present invention provides a robot arm motion trajectory planning method, device and storage medium, the main purpose of which is to solve the current problem that the grasping path of a moving object cannot be planned reasonably and accurately.

[0005] To solve the above problems, the present application provides a robot arm motion trajectory planning method, comprising: Get the target position of the moving object at the target time, and get the current position and posture of the robot arm at the current time; Based on the target position and the current posture, a single-point planning method is used to plan and obtain a first trajectory of the manipulator gripper to reach the target position and a target posture of the manipulator gripper at the target position in the first trajectory; Based on the current position and the target position, a second trajectory is obtained by planning using a multi-point planning method; A target trajectory is determined based on the first trajectory and the second trajectory.

[0006] Optionally, the target position includes the highest point position of the object and the landing point position of the object; Based on the target position and the current posture, a single-point planning method is used to plan and obtain a first trajectory of the manipulator gripper to reach the target position and a target posture of the manipulator gripper at the target position in the first trajectory, specifically including: Based on the landing point position and the highest point position, determining a plurality of initial postures; Determining a number of candidate poses that the robot arm can reach from each of the initial poses; Based on each of the candidate postures and the current posture, a single-point trajectory planning method is adopted to plan and obtain candidate trajectories corresponding to each candidate posture; The candidate trajectories are screened to obtain the first trajectory, and the candidate posture corresponding to the first trajectory is used as the target posture.

[0007] Optionally, determining a number of candidate poses that the robot arm can reach from each of the candidate initial poses specifically includes: Based on each of the initial postures, inverse calculation of the joint angles is performed respectively; An initial pose for which an inverse solution of a joint angle exists is determined as a candidate pose to obtain the plurality of candidate poses.

[0008] Optionally, before screening the candidate trajectories, the method further includes: The candidate trajectories are verified and adjusted by using a camera imaging verification method to obtain a number of candidate trajectories that pass the verification and are used for screening.

[0009] Optionally, the method of verifying and adjusting each of the candidate trajectories by using a camera imaging verification method to obtain a number of candidate trajectories that pass the verification and are used for screening specifically includes: For each trajectory point in the same candidate trajectory, determine the position of the object when the robot arm reaches the target trajectory point; Determine the position and posture of a camera disposed at the end of the robotic arm based on the position and posture of the robotic arm when the robotic arm is located at the target trajectory point; Based on the camera posture and the position of the object corresponding to the target trajectory point, determining whether the object is within the imaging range of the camera; When the object positions corresponding to the trajectory points in the same candidate trajectory are all within the imaging range of the camera, it is determined that the candidate trajectory passes the verification; When the object position corresponding to any trajectory point is not within the imaging range of the camera, the position and posture of the trajectory point is adjusted until the object position is within the imaging range of the camera corresponding to the adjusted trajectory point, thereby obtaining several candidate trajectories that have passed the verification and are used for screening.

[0010] Optionally, the planning to obtain the second trajectory by adopting a multi-point planning method based on the current posture and the target posture specifically includes: Based on the current posture and the target posture, position interpolation and posture interpolation processing are performed respectively to obtain a plurality of interpolated postures; Based on the current posture, each of the interpolated postures and the target posture, a multi-point planning method is adopted to plan and obtain the second trajectory.

[0011] Optionally, after obtaining the second trajectory, the method further includes: The second trajectory is verified and adjusted by using a camera imaging verification method to obtain a verified second trajectory.

[0012] Optionally, determining a target trajectory based on the first trajectory and the second trajectory specifically includes: performing collision detection and over-limit detection on the second trajectory; When it is determined that the second trajectory passes the collision detection and the overrun detection, determining the second trajectory as the target trajectory; When it is determined that the second trajectory fails the collision detection or fails the overrun detection, the first trajectory is determined to be the target trajectory. In order to solve the above problems, the present application provides a robot arm motion trajectory planning device, comprising: An acquisition module is used to acquire the target position of the moving object at the target time and acquire the current position and posture of the robot arm at the current time; A first planning module is used to plan, based on the target position and the current posture, a first trajectory of the manipulator gripper to reach the target position and a target posture of the manipulator gripper at the target position in the first trajectory by adopting a single-point planning method; A second planning module is used to plan and obtain a second trajectory based on the current posture and the target posture by adopting a multi-point planning method; The trajectory determination module is used to determine a target trajectory based on the first trajectory and the second trajectory.

[0013] To solve the above problems, the present application provides a storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of any of the above-mentioned methods for planning the motion trajectory of a robotic arm are implemented.

[0014] To solve the above problems, the present application provides an electronic device, comprising at least a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above-mentioned methods for planning the motion trajectory of the robot arm when executing the computer program on the memory.

[0015] The robot arm motion trajectory planning method, device and storage medium in the present application can determine the target position of the object at the future target moment, and then use a single-point trajectory planning method for the target position and the current posture to reasonably and accurately plan to obtain a first trajectory. Subsequently, a multi-point trajectory planning method can be further used based on the target posture in the first trajectory and the current posture to reasonably and accurately plan to obtain a second trajectory. Furthermore, the target trajectory can be reasonably and accurately determined based on the first trajectory and the second trajectory, thereby realizing accurate planning of the grasping trajectory for the moving object.

[0016] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings: Figure 1 This is a flow chart of a method for planning the motion trajectory of a robotic arm according to an embodiment of the present application; Figure 2 This is a flow chart of a method for planning the motion trajectory of a robot arm according to another embodiment of the present application; Figure 3 This is a planning flow chart of the first trajectory in another embodiment of the present application; Figure 4 This is a structural block diagram of a robot arm motion trajectory planning device according to another embodiment of the present application; Figure 5 This is a structural block diagram of an electronic device according to another embodiment of the present application. DETAILED DESCRIPTION

[0018] Various aspects and features of the present application are described herein with reference to the accompanying drawings.

[0019] It should be understood that various modifications may be made to the embodiments of the present application. Therefore, the above description should not be considered as limiting, but only as an example of an embodiment. Other modifications within the scope and spirit of the present application will occur to those skilled in the art.

[0020] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.

[0021] These and other characteristics of the present application will become apparent from the following description of a preferred form of embodiment given as a non-limiting example with reference to the accompanying drawings.

[0022] It should also be understood that although the present application has been described with reference to some specific examples, those skilled in the art will be able to readily implement many other equivalent forms of the present application.

[0023] The above and other aspects, features and advantages of the present application will become more apparent in view of the following detailed description when taken in conjunction with the accompanying drawings.

[0024] Specific embodiments of the present application are described hereinafter with reference to the accompanying drawings; however, it should be understood that the embodiments applied for are merely examples of the present application, which may be implemented in a variety of ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that obscure the present application. Therefore, the specific structural and functional details applied for herein are not intended to be limiting, but merely serve as a basis and representative basis for the claims to teach those skilled in the art to use the present application in a variety of ways with substantially any suitable detailed structure.

[0025] This specification may use the phrases "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," all of which may refer to one or more of the same or different embodiments according to the present application.

[0026] The present application embodiment provides a method for planning the motion trajectory of a robot arm, which can be specifically applied to electronic devices such as terminals and servers, such as Figure 1 As shown, the method in this implementation includes the following steps: Step S101, obtaining the target position of the moving object at the target time, and obtaining the current position and posture of the robot arm at the current time; In the specific implementation of this step, the target time specifically refers to the future grasping time. Specifically, the target position to which the object moves at the target time can be predicted / determined based on the moving speed and moving direction of the object. In this step, the current joint angle of the robot arm can be obtained, thereby obtaining the current posture of the robot arm.

[0027] Step S102, based on the target position and the current posture, a single-point planning method is used to plan and obtain a first trajectory of the manipulator gripper to reach the target position and a target posture of the manipulator gripper at the target position in the first trajectory; In this step, the target position specifically includes the landing point position of the object and the highest point position of the object. Therefore, several grasping postures of the robot gripper can be determined based on the landing point position and the highest point position, and then several candidate postures can be determined in combination with the landing point position. Subsequently, single-point trajectory planning can be performed based on each candidate posture and the current posture, thereby obtaining several candidate trajectories, and then the first trajectory can be determined from each candidate trajectory.

[0028] Step S103, based on the current posture and the target posture, a multi-point planning method is adopted to plan and obtain a second trajectory; In this step, after determining the target posture corresponding to the first trajectory, posture interpolation processing can be performed based on the current posture and the target posture to obtain several interpolated postures. Then, based on the target posture, the current posture and each interpolated posture, a multi-point planning method can be used to plan and obtain the second trajectory.

[0029] Step S104: determining a target trajectory based on the first trajectory and the second trajectory.

[0030] In the specific implementation process of this step, the second trajectory can be subjected to collision detection and over-limit detection; when it is determined that the second trajectory passes the collision detection and the over-limit detection, the second trajectory is determined to be the target trajectory; when it is determined that the second trajectory fails the collision detection or the over-limit detection, the first trajectory is determined to be the target trajectory. That is, when the robot arm postures corresponding to the trajectory points in the second trajectory do not collide and do not exceed the robot arm movement limit, the second trajectory is determined to be the target trajectory; otherwise, the first trajectory is determined to be the target trajectory.

[0031] The robot arm motion trajectory planning method in the present application, by determining the target position of the object at the future target moment, can use a single-point trajectory planning method for the target position and in combination with the current posture to reasonably and accurately plan to obtain the first trajectory. Subsequently, a multi-point trajectory planning method can be further used based on the target posture in the first trajectory and the current posture to reasonably and accurately plan to obtain the second trajectory. Furthermore, the target trajectory can be reasonably and accurately determined based on the first trajectory and the second trajectory, thereby achieving accurate planning of the grasping path for the moving object.

[0032] Based on the above embodiments, another embodiment of the present application provides a method for planning a motion trajectory of a robot arm, such as Figure 2 As shown, the method in this embodiment includes the following steps: Step S201, obtaining the landing point position of the moving object at the target time and the highest point position of the object, and obtaining the current position and posture of the robot arm at the current time; Step S202, based on the landing point position, the highest point position and the current posture, a single-point planning method is adopted to plan and obtain a first trajectory of the robotic arm gripper reaching the target position and a target posture of the robotic arm gripper at the target position in the first trajectory.

[0033] In this step, based on the landing point position and the highest point position, several grasping postures that can grasp the object can be determined, and then several candidate postures can be determined based on each grasping posture and the landing point position, so that based on the candidate postures and the current posture, a single-point planning method can be used to plan and obtain several candidate trajectories, and then a trajectory with the shortest path can be determined from each candidate trajectory as the first trajectory, and the candidate posture corresponding to the first trajectory can be used as the target posture.

[0034] Step S203, performing position interpolation and posture interpolation processing based on the current posture and the target posture, respectively, to obtain a plurality of interpolated postures; In this step, the current joint angle of the robot arm in the current position can be obtained, and the target joint angle of the robot arm in the target position can be determined. Then, according to the current joint angle and the target joint angle, interpolation processing is performed in Cartesian space, where the position is linear interpolation and the posture is quaternion interpolation. The number of interpolation points can be adjusted according to the actual situation, thereby obtaining a number of interpolation positions, that is, a number of interpolation points / path interpolation points.

[0035] Step S204, based on the current posture, each of the interpolated postures and the target posture, a multi-point planning method is adopted to plan and obtain the second trajectory; In this step, after obtaining the interpolated poses / path differences, a second trajectory can be planned using a multi-point planning method based on the target pose, the current pose, and the interpolated poses.

[0036] Step S205, verifying and adjusting the second trajectory by using a camera imaging verification method to obtain a verified second trajectory; After obtaining the second trajectory in this step, imaging verification can be performed on the object based on the camera imaging area when the robotic arm is located at the target trajectory point in the second trajectory, and the position to which the object moves when the robotic arm reaches the target trajectory point, so as to determine whether the object is within the imaging area of ​​the camera, thereby determining whether the angle of the camera is reasonable, and then determining whether the posture of the robotic arm is reasonable. This facilitates timely adjustment of the trajectory points in the second trajectory when it is determined that the object is not within the imaging range of the camera, thereby obtaining an adjusted second trajectory that meets the camera imaging verification.

[0037] In the specific implementation process of this step, the camera imaging verification process is as follows: Step S2051, for each track point in the second track, determining the position of the object when the robot arm reaches the target track point; Step S2052, determining the posture of a camera disposed at the end of the robotic arm based on the posture of the robotic arm when the robotic arm is located at the target trajectory point; In this step, the posture of the camera can be converted using the hand-eye matrix based on the posture of the robot arm when it is located at the target trajectory point.

[0038] Step S2053, determining whether the object is within the imaging range of the camera based on the camera posture and the position of the object corresponding to the target trajectory point; In this step, the projection of the position vector of the moving object and the camera on the camera imaging plane can be calculated, and the first angle between the projection and the x-axis (the horizontal direction corresponding to the imaging plane) and the second angle between the projection and the y-axis (the vertical direction corresponding to the imaging plane) can be calculated. Finally, it is determined whether the first angle and the second angle are within the given camera imaging angle range, so as to determine whether the object is within the imaging range of the camera.

[0039] Step S2054, when the object positions corresponding to the trajectory points in the second trajectory are all within the imaging range of the camera, it is determined that the second trajectory passes the camera imaging verification; when the object positions corresponding to any target trajectory point are not within the imaging range of the camera, the path interpolation point pose / interpolation point posture closest to the target trajectory point is adjusted to obtain an adjusted interpolation pose, and the target pose, the current position and the adjusted interpolation pose are re-planned to obtain the second trajectory using a multi-point planning method, until each trajectory point in the re-planned second trajectory passes the camera imaging verification, that is, a second trajectory that passes the verification is obtained; In this step, when the second trajectory that passes the verification is obtained, step S206 can be executed; if the re-planned second trajectory still fails to pass the camera imaging verification, the first trajectory can be directly used as the target trajectory, or the trajectory planning can be ended.

[0040] In this embodiment, when the posture of the path interpolation point / interpolation point is adjusted, the normal vector of the interpolation point posture can be adjusted to the position vector of the current object and the camera.

[0041] Step S206, performing collision detection and over-limit detection on the second trajectory; when it is determined that the second trajectory passes the collision detection and the over-limit detection, determining the second trajectory as the target trajectory; when it is determined that the second trajectory fails the collision detection or the over-limit detection, determining the first trajectory as the target trajectory.

[0042] In this step, after obtaining the verified second trajectory, the second trajectory may be further subjected to collision detection and over-limit detection to determine that the first trajectory is the target trajectory, or to determine that the second trajectory is the target trajectory.

[0043] In this embodiment, by adopting a single-point trajectory planning method to plan and obtain the first trajectory and determine the target posture, the multi-point trajectory planning method can be used to plan and obtain the second trajectory based on the target posture and the current posture, which lays the foundation for the subsequent reasonable and accurate determination of the target trajectory based on the first trajectory and the second trajectory. At the same time, by adopting a camera imaging verification method to verify and adjust the second trajectory, the verified and adjusted second trajectory can be made more reasonable and accurate, which further provides a guarantee for the reasonable and accurate determination of the target trajectory.

[0044] On the basis of the above embodiments, another embodiment of the present application provides a method for planning a robot arm motion trajectory. In this embodiment, based on the landing point position, the highest point position and the current posture, a single-point planning method is adopted to plan and obtain a first trajectory of the robot arm gripper reaching the target position and a target posture of the robot arm gripper at the target position in the first trajectory, that is, when executing step S202, it can be combined with Figure 3 As shown, the specific steps include: Step S2021, determining a plurality of initial postures based on the landing point position and the highest point position; In this step, multiple possible grasping postures can be generated based on the highest point position and the landing point position of the moving object in the robot arm coordinate system according to the normal vector and the rotation angle, and then several initial postures can be generated in combination with the landing point position. That is, the line connecting the landing point position and the highest point position can be used as the normal vector, and the gripper coordinate system can be generated, and then rotated around the Z axis at a predetermined angle (for example, 60 degrees) to generate multiple grasping postures, that is, to obtain the posture part in each initial posture. Then, the landing point position is further used as the position part in the initial posture, thereby determining / generating several initial postures.

[0045] Step S2022, determining a number of candidate poses that the robot arm can reach from each of the initial poses; In the specific implementation process of this step, the inverse solution of the joint angle can be calculated based on each of the initial postures; the initial posture for which the inverse solution of the joint angle exists is determined as the candidate posture to obtain the several candidate postures.

[0046] Step S2023, based on each of the candidate postures and the current posture, a single-point trajectory planning method is adopted to plan and obtain candidate trajectories corresponding to each of the candidate postures; In this step, after obtaining each candidate posture, single-point trajectory planning can be performed separately in combination with the current posture, so as to obtain candidate trajectories corresponding to each candidate posture that do not collide or exceed the limit.

[0047] Step S2024, screening each of the candidate trajectories to obtain the first trajectory, and taking the candidate posture corresponding to the first trajectory as the target posture; In this step, before screening the candidate trajectories, the candidate trajectories can be firstly verified and adjusted by using a camera imaging verification method to obtain a number of candidate trajectories that have passed the verification and are used for screening. Then, the candidate trajectory with the shortest path is determined from the candidate trajectories that have passed the verification to obtain the first trajectory.

[0048] In this embodiment, when the camera imaging verification method is used to verify and adjust each candidate trajectory, the specific process is as follows: Step 1: for each trajectory point in the same candidate trajectory, determine the position of the object when the robot arm reaches the target trajectory point; Step 2: determining the posture of a camera disposed at the end of the robotic arm based on the posture of the robotic arm when the robotic arm is located at the target trajectory point; In this step, the posture of the camera can be converted using the hand-eye matrix based on the posture of the robot arm when it is located at the target trajectory point.

[0049] Step 3: Based on the camera posture and the position of the object corresponding to the target trajectory point, determine whether the object is within the imaging range of the camera; In this step, the projection of the position vector of the moving object and the camera on the camera imaging plane can be calculated, and the first angle between the projection and the x-axis (the horizontal direction corresponding to the imaging plane) and the second angle between the projection and the y-axis (the vertical direction corresponding to the imaging plane) can be calculated. Finally, it is determined whether the first angle and the second angle are within the given camera imaging angle range, so as to determine whether the object is within the imaging range of the camera.

[0050] Step 4: When the object positions corresponding to the trajectory points in the same candidate trajectory are all within the imaging range of the camera, it is determined that the candidate trajectory passes the verification; Step 5: When the object position corresponding to any trajectory point is not within the imaging range of the camera, the position of the trajectory point is adjusted until the object position is within the imaging range of the camera corresponding to the adjusted trajectory point, thereby obtaining several candidate trajectories that have passed the verification and are used for screening.

[0051] In this step, when adjusting the posture of the track point in this embodiment, the normal vector of the track point posture can be adjusted to the position vector of the current object and the camera. That is, the normal vector of the track point capture posture is adjusted to the position vector of the current moving object and the camera.

[0052] In this embodiment, after obtaining several candidate trajectories that have passed the verification, the trajectory with the shortest path can be screened from these candidate trajectories. The specific screening method is: based on the candidate postures corresponding to each candidate trajectory, determine the candidate joint angles corresponding to each candidate posture; at the same time, determine the current joint angle corresponding to the current posture; based on each candidate joint angle and the current joint angle, perform a norm solution to obtain the candidate joint angle with the smallest change, and determine the candidate trajectory corresponding to the candidate joint angle as the first trajectory, and at the same time, the posture / candidate posture corresponding to the joint angle with the smallest change can be determined as the target posture.

[0053] In this embodiment, a single-point trajectory planning method is first used to plan and obtain several candidate paths, and then a camera imaging verification method is used to verify and adjust each candidate trajectory, so that the verified and adjusted candidate trajectory can be made more reasonable and accurate, laying a foundation for the reasonable and accurate determination of the first trajectory of the candidate.

[0054] Another embodiment of the present application provides a robot arm motion trajectory planning device, such as Figure 4 As shown, including: The acquisition module 11 is used to acquire the target position of the moving object at the target time and acquire the current position and posture of the robot arm at the current time; A first planning module 12 is used to plan, based on the target position and the current posture, a first trajectory of the manipulator gripper to reach the target position and a target posture of the manipulator gripper at the target position in the first trajectory by adopting a single-point planning method; A second planning module 13 is used to plan and obtain a second trajectory based on the current posture and the target posture by adopting a multi-point planning method; The trajectory determination module 14 is configured to determine a target trajectory based on the first trajectory and the second trajectory.

[0055] In the specific implementation process of this embodiment, the target position includes the highest point position of the object and the landing point position of the object; The first planning module includes a first determining unit, a second determining unit, a planning unit and a screening unit, and specifically includes: A first determining unit, configured to determine a plurality of initial postures based on the landing point position and the highest point position; A second determination unit, used to determine a number of candidate poses that the robot arm can reach from each of the initial poses; A planning unit, configured to plan and obtain candidate trajectories corresponding to each candidate posture based on each candidate posture and the current posture by adopting a single-point trajectory planning method; A screening unit is used to screen and obtain the first trajectory based on the candidate trajectories, and use the candidate posture corresponding to the first trajectory as the target posture.

[0056] In the specific implementation process of this embodiment, the second determination unit is specifically used to: perform inverse solution calculation of joint angles based on each of the initial postures; determine the initial posture for which the joint angle inverse solution exists as a candidate posture to obtain the several candidate postures.

[0057] In the specific implementation process of this embodiment, the robot arm motion trajectory planning device also includes a verification module, which is used to: use a camera imaging verification method to verify and adjust each of the candidate trajectories to obtain a number of candidate trajectories that have passed the verification and are used for screening.

[0058] In the specific implementation process of this embodiment, the verification module is specifically used to: determine the position of the object when the robot arm reaches the target trajectory point for each trajectory point in the same candidate trajectory; determine the posture of the camera set at the end of the robot arm based on the posture of the robot arm when it is located at the target trajectory point; determine whether the object is within the imaging range of the camera based on the camera posture and the position of the object corresponding to the target trajectory point; when the object positions corresponding to each trajectory point in the same candidate trajectory are all within the imaging range of the camera, determine that the candidate trajectory has passed the verification; when the object position corresponding to any trajectory point is not within the imaging range of the camera, adjust the posture of the trajectory point until the object position is within the imaging range of the camera corresponding to the adjusted trajectory point, and obtain a number of candidate trajectories that have passed the verification and are used for screening.

[0059] In the specific implementation process of this embodiment, the second planning module is used to: based on the current posture and the target posture, perform position interpolation and posture interpolation processing respectively to obtain a plurality of interpolated postures; based on the current posture, each of the interpolated postures and the target posture, adopt a multi-point planning method to plan and obtain the second trajectory.

[0060] In the specific implementation process of this embodiment, the verification module is further used to: after obtaining the second trajectory, use a camera imaging verification method to verify and adjust the second trajectory to obtain a verified second trajectory.

[0061] In the specific implementation process of this embodiment, the trajectory determination module is specifically used to: perform collision detection and over-limit detection on the second trajectory; when it is determined that the second trajectory passes the collision detection and the over-limit detection, determine that the second trajectory is the target trajectory; when it is determined that the second trajectory fails the collision detection or the over-limit detection, determine that the first trajectory is the target trajectory.

[0062] A robotic arm motion trajectory planning device in the present embodiment, by determining the target position of an object at a target moment in the future, can adopt a single-point trajectory planning method for the target position in combination with the current posture, and reasonably and accurately plan to obtain a first trajectory. Subsequently, a multi-point trajectory planning method can be further adopted based on the target posture in the first trajectory and the current posture, and reasonably and accurately plan to obtain a second trajectory. Furthermore, the target trajectory can be reasonably and accurately determined based on the first trajectory and the second trajectory, thereby realizing accurate planning of the grasping trajectory for the moving object.

[0063] Another embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the following method steps are implemented: Step 1: Obtain the target position of the moving object at the target time, and obtain the current position and posture of the robot arm at the current time; Step 2: Based on the target position and the current posture, a single-point planning method is used to plan and obtain a first trajectory of the manipulator gripper to reach the target position and a target posture of the manipulator gripper at the target position in the first trajectory; Step 3: Based on the current position and the target position, a multi-point planning method is used to plan and obtain a second trajectory; Step 4: Determine a target trajectory based on the first trajectory and the second trajectory.

[0064] The specific implementation process of the above method steps can be found in the above-mentioned embodiments of any robot arm motion trajectory planning method, and this embodiment will not be repeated here.

[0065] The storage medium in this embodiment can determine the target position of the object at the future target moment, and then use a single-point trajectory planning method for the target position and the current posture to reasonably and accurately plan to obtain a first trajectory. Subsequently, a multi-point trajectory planning method can be further used based on the target posture in the first trajectory and the current posture to reasonably and accurately plan to obtain a second trajectory. Furthermore, the target trajectory can be reasonably and accurately determined based on the first trajectory and the second trajectory, thereby realizing accurate planning of the grasping trajectory for the moving object.

[0066] Another embodiment of the present application provides an electronic device, such as Figure 5 As shown, at least a memory 1 and a processor 2 are included, the memory 1 stores a computer program, and the processor 2 implements the following method steps when executing the computer program on the memory 1: Step 1: Obtain the target position of the moving object at the target time, and obtain the current position and posture of the robot arm at the current time; Step 2: Based on the target position and the current posture, a single-point planning method is used to plan and obtain a first trajectory of the manipulator gripper to reach the target position and a target posture of the manipulator gripper at the target position in the first trajectory; Step 3: Based on the current position and the target position, a multi-point planning method is used to plan and obtain a second trajectory; Step 4: Determine a target trajectory based on the first trajectory and the second trajectory.

[0067] The specific implementation process of the above method steps can be found in the above-mentioned embodiments of any robot arm motion trajectory planning method, and this embodiment will not be repeated here.

[0068] The electronic device in this embodiment, by determining the target position of the object at the future target moment, can use a single-point trajectory planning method for the target position and in combination with the current posture to reasonably and accurately plan to obtain a first trajectory. Subsequently, it can further use a multi-point trajectory planning method based on the target posture in the first trajectory and the current posture to reasonably and accurately plan to obtain a second trajectory. Furthermore, the target trajectory can be reasonably and accurately determined based on the first trajectory and the second trajectory, thereby achieving precise planning of the grasping trajectory for the moving object.

[0069] The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application. The protection scope of the present application is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present application within the essence and protection scope of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present application.

Claims

1. A method for planning a robot arm motion trajectory, characterized in that: include: Get the target position of the moving object at the target time, and get the current position and posture of the robot arm at the current time; Based on the target position and the current posture, a single-point planning method is used to plan and obtain a first trajectory of the manipulator gripper to reach the target position and a target posture of the manipulator gripper at the target position in the first trajectory; Based on the current posture and the target posture, a second trajectory is planned by adopting a multi-point planning method; A target trajectory is determined based on the first trajectory and the second trajectory.

2. The method according to claim 1, characterized in that The target position includes the highest point position of the object and the landing point position of the object; Based on the target position and the current posture, a single-point planning method is used to plan and obtain a first trajectory of the manipulator gripper to reach the target position and a target posture of the manipulator gripper at the target position in the first trajectory, specifically including: Based on the landing point position and the highest point position, determining a plurality of initial postures; Determining a number of candidate poses that the robot arm can reach from each of the initial poses; Based on each of the candidate postures and the current posture, a single-point trajectory planning method is adopted to plan and obtain candidate trajectories corresponding to each candidate posture; The candidate trajectories are screened to obtain the first trajectory, and the candidate posture corresponding to the first trajectory is used as the target posture.

3. The method according to claim 2, characterized in that The step of determining a plurality of candidate poses that the robot arm can reach from each of the candidate initial poses specifically includes: Based on each of the initial postures, inverse calculation of the joint angles is performed respectively; An initial pose for which an inverse solution of a joint angle exists is determined as a candidate pose to obtain the plurality of candidate poses.

4. The method according to claim 2, characterized in that Before screening the candidate trajectories, the method further includes: The candidate trajectories are verified and adjusted by using a camera imaging verification method to obtain a number of candidate trajectories that pass the verification and are used for screening.

5. The method according to claim 4, characterized in that The method of using camera imaging to verify and adjust each of the candidate trajectories to obtain a number of candidate trajectories that have passed the verification and are used for screening specifically includes: For each trajectory point in the same candidate trajectory, determine the position of the object when the robot arm reaches the target trajectory point; Determine the position and posture of a camera disposed at the end of the robotic arm based on the position and posture of the robotic arm when the robotic arm is located at the target trajectory point; Based on the camera posture and the position of the object corresponding to the target trajectory point, determining whether the object is within the imaging range of the camera; When the object positions corresponding to the trajectory points in the same candidate trajectory are all within the imaging range of the camera, it is determined that the candidate trajectory passes the verification; When the object position corresponding to any trajectory point is not within the imaging range of the camera, the position and posture of the trajectory point is adjusted until the object position is within the imaging range of the camera corresponding to the adjusted trajectory point, thereby obtaining several candidate trajectories that have passed the verification and are used for screening.

6. The method according to claim 1, characterized in that The planning to obtain the second trajectory by adopting a multi-point planning method based on the current posture and the target posture specifically includes: Based on the current posture and the target posture, position interpolation and posture interpolation processing are performed respectively to obtain a plurality of interpolated postures; Based on the current posture, each of the interpolated postures and the target posture, a multi-point planning method is adopted to plan and obtain the second trajectory.

7. The method according to claim 6, characterized in that After obtaining the second trajectory, the method further includes: The second trajectory is verified and adjusted by using a camera imaging verification method to obtain a verified second trajectory.

8. The method according to claim 1, characterized in that The determining of the target trajectory based on the first trajectory and the second trajectory specifically includes: performing collision detection and over-limit detection on the second trajectory; When it is determined that the second trajectory passes the collision detection and the overrun detection, determining the second trajectory as the target trajectory; When it is determined that the second trajectory fails the collision detection or fails the overrun detection, the first trajectory is determined to be the target trajectory.

9. A robot arm motion trajectory planning device, characterized in that: include: An acquisition module is used to acquire the target position of the moving object at the target time and acquire the current position and posture of the robot arm at the current time; A first planning module is used to plan, based on the target position and the current posture, a first trajectory of the manipulator gripper to reach the target position and a target posture of the manipulator gripper at the target position in the first trajectory by adopting a single-point planning method; A second planning module is used to plan and obtain a second trajectory based on the current posture and the target posture by adopting a multi-point planning method; The trajectory determination module is used to determine a target trajectory based on the first trajectory and the second trajectory.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the robot arm motion trajectory planning method described in any one of claims 1 to 8 are implemented.

Images