WO2022110452A1 - 机器人运动规划方法、装置、可移动机器人及存储介质 - Google Patents

机器人运动规划方法、装置、可移动机器人及存储介质 Download PDF

Info

Publication number
WO2022110452A1
WO2022110452A1 PCT/CN2020/139907 CN2020139907W WO2022110452A1 WO 2022110452 A1 WO2022110452 A1 WO 2022110452A1 CN 2020139907 W CN2020139907 W CN 2020139907W WO 2022110452 A1 WO2022110452 A1 WO 2022110452A1
Authority
WO
WIPO (PCT)
Prior art keywords
motion
discrete
dynamic system
robot
point
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2020/139907
Other languages
English (en)
French (fr)
Inventor
张硕
郑大可
刘益彰
谢铮
熊友军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ubtech Robotics Corp
Original Assignee
Ubtech Robotics Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ubtech Robotics Corp filed Critical Ubtech Robotics Corp
Publication of WO2022110452A1 publication Critical patent/WO2022110452A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B25HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25JMANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00Program-controlled manipulators
    • B25J9/16Program controls
    • B25J9/1656Program controls characterised by programming, planning systems for manipulators
    • B25J9/1664Program controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B25HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25JMANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00Program-controlled manipulators
    • B25J9/16Program controls
    • B25J9/1602Program controls characterised by the control system, structure, architecture

Definitions

  • the present application relates to the technical field of robot control, and in particular, to a robot motion planning method, device, movable robot and storage medium.
  • the purpose of this application is to provide a robot motion planning method, device, movable robot and storage medium, which can plan a motion trajectory that conforms to the motion law for the robot, so that the robot can achieve the desired motion with reference to the planned motion trajectory effect, improve the instability of the robot.
  • the present application provides a robot motion planning method, the method comprising:
  • search for target dynamic system parameters that match the effective space discrete starting point and the effective space discrete end point wherein the dynamic system corresponding to the target dynamic system parameters is used for planning from the effective space.
  • the target dynamic system parameters are used to construct a desired dynamic system matching the desired motion end point, and a desired motion trajectory from the desired motion starting point to the desired motion end point is planned based on the desired motion system.
  • the step of determining an effective space discrete starting point adjacent to the desired motion starting point and an effective space discrete end point adjacent to the desired motion ending point in the working space of the robot includes:
  • the effective space discrete point corresponding to the smallest first Euclidean distance is used as the effective space discrete start point, and the effective space discrete point corresponding to the smallest second Euclidean distance is used as the effective space discrete end point.
  • the target dynamic system parameters are used to construct a desired dynamic system matching the desired end point of the motion, and based on the desired dynamic system, the desired motion starting point to the desired motion is planned based on the desired motion system
  • the steps of the desired motion trajectory of the end point including:
  • the position information of the desired motion starting point is input into the desired dynamic system for motion trajectory planning to obtain the desired motion trajectory.
  • the method further includes:
  • a dynamic system For each effective space discrete point in the workspace, a dynamic system is constructed according to the motion teaching trajectory from the effective space discrete point to other effective space discrete points, and the dynamic system parameters corresponding to the constructed dynamic system are calculated. to store.
  • the step of determining the discrete points in the effective space reachable by the robot joints in the working space of the robot includes:
  • Space division is performed on the workspace of the robot to obtain discrete points in space of the workspace;
  • Target discrete points that are unreachable by all joints of the robot are eliminated from the spatial discrete points of the workspace to obtain effective spatial discrete points of the workspace.
  • the present application provides a robot motion planning device, the device comprising:
  • the motion expectation confirmation module is used to determine the current desired motion starting point and the desired motion end point of the robot;
  • a discrete proximity confirmation module configured to determine an effective space discrete starting point adjacent to the desired motion starting point and an effective space discrete end point adjacent to the desired motion ending point in the working space of the robot;
  • the dynamic parameter search module is used to search for the target dynamic system parameter matching the effective space discrete starting point and the effective space discrete end point in the pre-stored multiple groups of dynamic system parameters, wherein the dynamic parameter corresponding to the target dynamic system parameter
  • the system is used to plan the motion trajectory from the discrete starting point of the effective space to the discrete end point of the effective space;
  • a desired trajectory planning module configured to use the target dynamic system parameters to construct a desired dynamic system matching the desired end point of the motion, and plan the desired motion from the desired starting point of the motion to the desired end point of the motion based on the desired dynamic system movement trajectory.
  • the discrete proximity confirmation module includes:
  • the Euclidean distance calculation sub-module is used to calculate the first Euclidean distance between the effective space discrete point and the desired motion starting point for each effective space discrete point in the workspace, and calculate the effective space discrete point the second Euclidean distance between the point and the desired starting point of the movement;
  • the discrete proximity determination sub-module is used to take the effective space discrete point corresponding to the minimum first Euclidean distance as the effective space discrete starting point, and the effective space discrete point corresponding to the smallest second Euclidean distance as the effective space Discrete endpoints.
  • the desired trajectory planning module includes:
  • a dynamic system reconstruction sub-module used for directly reconstructing the corresponding dynamic system by using the target dynamic system parameters
  • Convergence end point replacement submodule for using the motion desired end point to perform position replacement on the trajectory convergence end point of the reconstructed dynamic system, to obtain the desired dynamic system
  • the motion trajectory planning sub-module is used for inputting the position information of the desired starting point of the motion into the desired dynamic system for motion trajectory planning to obtain the desired motion trajectory.
  • the device further comprises:
  • an effective discrete confirmation module used for determining the effective space discrete points reachable by the robot joints in the working space of the robot
  • the dynamic parameter storage module is used for constructing a dynamic system for each effective space discrete point in the workspace, according to the motion teaching trajectory from the effective space discrete point to other effective space discrete points, and constructing the dynamic system.
  • the dynamic system parameters corresponding to the system are stored.
  • the valid discrete confirmation module includes:
  • an action space division sub-module used for space division of the working space of the robot to obtain discrete spatial points of the working space
  • the invalid discrete elimination sub-module is used to eliminate the target discrete points that are unreachable by all joints of the robot from the spatial discrete points of the workspace, so as to obtain the effective spatial discrete points of the workspace.
  • the present application provides a mobile robot, comprising a processor and a memory, wherein the memory stores a computer program executable by the processor, and the processor can execute the computer program to implement the aforementioned implementation
  • the robot motion planning method described in any one of the methods comprising a processor and a memory, wherein the memory stores a computer program executable by the processor, and the processor can execute the computer program to implement the aforementioned implementation
  • the present application provides a storage medium on which a computer program is stored, and when the computer program is executed by a processor, implements the robot motion planning method described in any one of the foregoing embodiments.
  • the present application determines the desired starting point and end point of the robot's current motion, and determines the discrete starting point of the effective space adjacent to the desired starting point of the motion and the discrete end point of the effective space adjacent to the desired end point of the motion in the working space of the robot.
  • the target dynamic system parameters used to plan the motion trajectory from the discrete starting point of the effective space to the discrete end point of the effective space and then use the target dynamic system parameters to construct the desired dynamic system matching the desired end point of the motion
  • the desired motion trajectory from the desired starting point of the motion to the desired end point of the motion is planned, so that by using the dynamic system to predict the characteristics of a reasonable motion trajectory within a limited range, a motion trajectory that conforms to the motion law is planned for the robot, so that the robot can Refer to the planned motion trajectory to achieve the expected motion effect and improve the motion stability of the robot.
  • 1 is a schematic diagram of the composition of a mobile robot provided by an embodiment of the present application.
  • FIG. 2 is one of the schematic flowcharts of the robot motion planning method provided by the embodiment of the present application.
  • FIG. 3 is a schematic diagram of a motion trajectory planning provided in an embodiment of the present application.
  • FIG. 4 is a schematic flowchart of the sub-steps included in step S220 in FIG. 2;
  • FIG. 5 is a schematic flowchart of sub-steps included in step S240 in FIG. 2;
  • FIG. 6 is the second schematic flowchart of the robot motion planning method provided by the embodiment of the present application.
  • FIG. 7 is a schematic flowchart of the sub-steps included in step S208 in FIG. 6;
  • FIG. 8 is one of the schematic diagrams of the composition of the robot motion planning apparatus provided by the embodiment of the present application.
  • FIG. 9 is a schematic diagram of the composition of the discrete proximity confirmation module in FIG. 8.
  • FIG. 10 is a schematic diagram of the composition of the desired trajectory planning module in FIG. 8;
  • FIG. 11 is the second schematic diagram of the composition of the robot motion planning device provided by the embodiment of the application.
  • FIG. 12 is a schematic diagram of the composition of the effective discrete confirmation module in FIG. 11 .
  • Icons 10-mobile robot; 11-memory; 12-processor; 13-communication unit; 14-drive mechanism; 100-robot motion planning device; 110-motion expectation confirmation module; 120-discrete proximity confirmation module; Dynamic parameter search module; 140-expected trajectory planning module; 121-Euclidean distance calculation sub-module; 122-discrete proximity determination sub-module; 141-dynamic system reconstruction sub-module; 142-convergence end point replacement sub-module; 143-motion trajectory Planning sub-module; 150-valid discrete confirmation module; 151-action space division sub-module; 152-invalid discrete elimination sub-module; 160-dynamic parameter storage module.
  • the existing robot motion trajectory planning scheme is usually based on the artificially taught motion trajectory of a specific motion to construct a dynamic system, and then use the constructed dynamic system for different motion starting points and/or different motions.
  • the motion trajectory between the end points is predicted and planned.
  • the dynamic system is constructed for the purpose of describing the aforementioned specific motion after all, and it has the limit prediction range of the effective trajectory (including the effective starting point variation range and the effective end point variation range).
  • the motion trajectory planned by the dynamic system will be severely deformed and will not conform to the motion law of the robot, making the robot refer to
  • the robot instability phenomenon caused by the deformation of the motion action is prone to occur, and the expected motion effect cannot be achieved.
  • the embodiment of the present application provides a robot motion
  • the planning method, device, movable robot and storage medium realize the aforementioned functions.
  • FIG. 1 is a schematic diagram of the composition of a mobile robot 10 provided by an embodiment of the present application.
  • the mobile robot 10 can plan a motion trajectory between any starting point and any end point in its own workspace that conforms to the motion law, and perform corresponding motion operations with reference to the planned motion trajectory It can achieve the expected movement effect and improve its own movement stability.
  • the workspace is a set of spatial points that can be reached by the end effector motion description reference point of the mobile robot 10 , which represents the maximum movable range of the mobile robot 10 .
  • the number of workspaces of the mobile robot 10 may be multiple, and each workspace corresponds to a motion mechanical structure of the mobile robot 10 (for example, the working arm of the working robot, or the left arm of the humanoid robot). , any of the right robotic arm, left robotic leg, and right robotic leg).
  • the movable robot 10 may be, but not limited to, a humanoid robot, a crawler robot, an industrial robot, and the like.
  • the mobile robot 10 may include a memory 11 , a processor 12 , a communication unit 13 , a driving mechanism 14 and a robot motion planning device 100 .
  • the elements of the memory 11 , the processor 12 , the communication unit 13 and the driving mechanism 14 are electrically connected to each other indirectly or indirectly to realize data transmission or interaction.
  • the elements of the memory 11 , the processor 12 , the communication unit 13 and the driving mechanism 14 can be electrically connected to each other through one or more communication buses or signal lines.
  • the memory 11 may be, but not limited to, a random access memory (Random Access Memory, RAM), a read only memory (Read Only Memory, ROM), a programmable read only memory (Programmable Read-Only Memory) Memory, PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Read-Only Memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc.
  • RAM Random Access Memory
  • ROM read only memory
  • PROM programmable read only memory
  • PROM Programmable Read-Only Memory
  • EPROM Erasable Programmable Read-Only Memory
  • EEPROM Electrically Erasable Read-Only Memory
  • the memory 11 can also be used to store dynamic system parameters corresponding to different workspaces for constructing dynamic systems between different starting positions and different ending positions, wherein a set of dynamic system parameters corresponds to one starting point position and one item. end position.
  • the processor 12 may be an integrated circuit chip with signal processing capability.
  • the processor 12 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU), a network processor (Network Processor, NP), a digital signal processor (DSP) ), an application specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, at least one of a discrete gate or transistor logic device, a discrete hardware component.
  • the general-purpose processor may be a microprocessor, or the processor may also be any conventional processor, etc., and may implement or execute the methods, steps, and logical block diagrams disclosed in the embodiments of this application.
  • the communication unit 13 is used to establish a communication connection between the mobile robot 10 and other electronic devices through a network, and to send and receive data through the network, wherein the network includes a wired communication network and a wireless Communications network.
  • the mobile robot 10 can obtain the movement sent by the operator for a certain movement mechanical structure (for example, the left mechanical arm or the right mechanical arm) of the mobile robot 10 from other electronic devices through the communication unit 13 .
  • instruction wherein the motion instruction includes the configured movement starting point and the moving end point, so that the mobile robot 10 can plan a movement trajectory that conforms to the movement law between the configured movement starting point and the movement end point, and control the movement with reference to the planned movement trajectory.
  • the movement of the mechanical structure can achieve the expected movement effect and ensure its own movement stability.
  • the driving mechanism 14 is used to realize the movable function of the mobile robot 10 .
  • the motion mechanical structure constitutes a drive module that changes its own motion state.
  • the mobile robot 10 can perform corresponding motion operations with reference to the planned motion trajectory through the drive mechanism 14 .
  • the robot motion planning apparatus 100 includes at least one software function module that can be stored in the memory 11 in the form of software or firmware or fixed in the operating system of the mobile robot 10 .
  • the processor 12 may be configured to execute executable modules stored in the memory 11 , such as software function modules and computer programs included in the robot motion planning apparatus 100 .
  • the movable robot 10 can use the dynamic system to predict the characteristics of a reasonable motion trajectory within a limited range through the robot motion planning device 100, and plan a motion trajectory that conforms to the motion law for any starting point and any end point in the workspace, so that The movable robot 10 can achieve the expected motion effect with reference to the planned motion trajectory, so as to ensure the motion stability of the robot.
  • FIG. 1 is only a schematic diagram of the composition of the mobile robot 10 , and the mobile robot 10 may further include more or less components than those shown in FIG. 1 , or have A different configuration from that shown in Figure 1.
  • Each component shown in FIG. 1 may be implemented in hardware, software, or a combination thereof.
  • the present application in order to ensure that the mobile robot 10 can always effectively plan a motion trajectory that conforms to the motion law, so as to achieve the expected motion effect of ensuring the motion stability of the robot, the present application achieves the aforementioned purpose by providing a robot motion planning method
  • the execution subject of the robot motion planning method may be the above-mentioned movable robot 10 , or may be an electronic device communicatively connected to the above-mentioned movable robot 10 .
  • the robot motion planning method provided by the present application will be described in detail below.
  • FIG. 2 is one of the schematic flowcharts of the robot motion planning method provided by the embodiment of the present application.
  • the specific flow and steps of the robot motion planning method shown in FIG. 2 are as follows.
  • Step S210 determining the current desired starting point and end point of the robot's motion.
  • the desired starting point of motion and the desired ending point of motion can be remotely configured by the operator of the mobile robot 10 through the network, or directly configured on the control display interface provided by the mobile robot 10 .
  • Step S220 in the working space of the robot, determine an effective space discrete starting point adjacent to the desired motion starting point, and an effective space discrete end point adjacent to the desired motion ending point.
  • each workspace of the mobile robot 10 can be subdivided into space, the workspace is divided into several small space blocks, and the space vertex of each small space block is confirmed. Whether it is the reachable point that can be reached by each joint included in the corresponding motion mechanical structure, and then the spatial vertex that can be reached by at least one joint determined in the workspace is used as the reachable point of the workspace for characterizing the movement of the robot. Effective space discrete points.
  • the desired starting point and the desired ending point of the motion can be determined according to the respective positions of the desired starting point and the desired ending point of the motion.
  • the end point is located, and the corresponding effective space discrete start point and effective space discrete end point are determined in the effective space discrete points of the workspace.
  • FIG. 3 Take Figure 3 as an example to illustrate: if there is a workspace that is abstracted as a cube whose length, width, and height are l, w, and h respectively, a space rectangular (XYZ) coordinate system can be established at the center of the workspace, Each position of the workspace is described by the space Cartesian coordinate system.
  • XYZ space rectangular
  • FIG. 4 is a schematic flowchart of sub-steps included in step S220 in FIG. 2 .
  • the step S220 may include sub-steps S221 to S222.
  • Sub-step S221 for each effective space discrete point in the workspace, calculate the first Euclidean distance between the effective space discrete point and the desired motion starting point, and calculate the first Euclidean distance between the effective space discrete point and the desired motion starting point. Two Euclidean distance.
  • the effective space discrete point corresponding to the minimum first Euclidean distance is used as the effective space discrete start point, and the effective space discrete point corresponding to the smallest second Euclidean distance is used as the effective space discrete end point.
  • the discrete starting point of the effective space can be obtained by executing the above sub-step S221 and sub-step S222 in the workspace. and the effective space discrete end point.
  • Step S230 in the pre-stored multiple groups of dynamic system parameters, search for target dynamic system parameters matching the effective space discrete starting point and effective space discrete end point, wherein the dynamic system corresponding to the target dynamic system parameters is used for planning from the effective space discrete starting point to The motion trajectory of the discrete end point in the effective space.
  • each effective space discrete point in the workspace is traversed in advance, and the visited effective space discrete point is used as a starting point during the traversal process.
  • the other effective space discrete points are the end points to construct a dynamic system, so that the constructed dynamic system can effectively plan a reasonable motion trajectory from the visited effective space discrete points to the other effective space discrete points, and then the dynamic system
  • the dynamic system parameters are stored.
  • FIG. 10 An example is used to illustrate the above dynamic system construction process: if the mobile robot 10 has a workspace a and a workspace b, and there are discrete points a1, a2, and a3 of effective spaces in the workspace a, and there are effective discrete points a1, a2, and a3 in the workspace b Space discrete points b1, b2, b3, for the workspace a, the dynamic system from a1 to a2, the dynamic system from a1 to a3, the dynamic system from a2 to a1, the dynamic system from a2 to a3, the dynamic system from a2 to a3 needs to be constructed.
  • a dynamic system from a3 to a1, a dynamic system from a3 to a2; for workspace b, a dynamic system from b1 to b2, a dynamic system from b1 to b3, a dynamic system from b2 to b1, and a dynamic system from b2 to b3 need to be constructed
  • the dynamic system is a conventional robot motion planning algorithm, the basic idea of which is to model n times of teaching activities of the robot as n instances of a first-order dynamic system.
  • a first-order dynamic system can be described as follows:
  • a first-order dynamic system can be described by a parameter set ⁇ .
  • the parameter set can be learned from the taught trajectory data using probabilistic methods.
  • the probability method can be used to model it as a mixture model of finite Gaussian functions.
  • the parameter set of the dynamic system can be expressed as a set of prior probability density, mean and covariance matrix of different Gaussian functions.
  • the prior probability density of the k-th Gaussian function can be expressed as ⁇ k
  • the mean of the k-th Gaussian function can be expressed as ⁇ k
  • K is the number of the Gaussian function.
  • n is used to represent the trajectory pose of the trajectory point at the t-th time on the n-th teaching trajectory, It is used to represent the trajectory velocity of the trajectory point at the t-th time on the nth teaching trajectory, then for each trajectory point, there will be the following probability density function:
  • the dynamic system parameters corresponding to the dynamic system from the effective space discrete starting point to the effective space discrete end point are used as the target dynamic system parameters.
  • Step S240 using the target dynamic system parameters to construct a desired dynamic system matching the desired end point of the motion, and planning a desired motion trajectory from the desired motion starting point to the desired end point of the motion based on the desired dynamic system.
  • the target dynamic system parameters can be directly transferred to the target point from the desired motion start point to In the process of planning the motion trajectory of the desired end point of the motion, a desired motion trajectory that conforms to the motion law is planned for the desired motion starting point and the desired end point of the motion by directly using the target dynamic system parameters, so that the mobile robot 10 can The desired motion effect is achieved with reference to the planned desired motion trajectory to ensure the stability of the robot motion.
  • step S240 may include sub-steps S241 to S243.
  • Sub-step S241 directly using the target dynamic system parameters to reconstruct the corresponding dynamic system.
  • Sub-step S242 using the desired motion end point to replace the position of the trajectory convergence end point of the reconstructed dynamic system to obtain the desired dynamic system.
  • sub-step S243 the position information of the desired starting point of the motion is input into the desired dynamic system for motion trajectory planning, and the desired motion trajectory is obtained.
  • the dynamic system directly reconstructed by using the target dynamic system parameters can plan a motion trajectory that conforms to the law of motion from a spatial position within a certain range around the discrete starting point of the effective space to the discrete end point of the effective space , at this time, the trajectory convergence end point of the dynamic system is the effective space discrete end point.
  • the desired motion end point is used to replace the position of the trajectory convergence end point of the reconstructed dynamic system
  • the corresponding desired dynamic system can be used to plan from the spatial position within a certain range around the discrete starting point of the effective space to the desired dynamic system.
  • the motion trajectory that conforms to the motion law of the desired end point of the motion is input into the desired dynamic system, and the desired motion from the desired starting point of the motion to the desired end point of the motion can be directly planned through the desired dynamic system. trajectory.
  • the present application can plan a motion trajectory that conforms to the motion law for any starting point and any ending point in the work space of the mobile robot 10 by executing the above steps S210 to S240, so that the mobile robot 10 When the corresponding motion operation is performed with reference to the planned motion trajectory, the expected motion effect is achieved to ensure the stability of the robot motion.
  • FIG. 6 is the second schematic flowchart of the robot motion planning method provided by the embodiment of the present application.
  • the robot motion planning method shown in FIG. 6 is compared with the robot motion planning method shown in FIG. 2 .
  • the robot motion planning method shown in FIG. 6 may further include steps S208 and S209, so as to The above steps S208 and S209 ensure that the robot motion planning method shown in FIG. 2 can be implemented normally.
  • Step S208 determining the discrete points in the effective space reachable by the joints of the robot in the working space of the robot.
  • each workspace of the mobile robot 10 can be subdivided. For each workspace, divide the workspace into several small space blocks, and confirm whether the space vertices of each small space block are reachable points that the robot joints can reach, and then at least one determined in the workspace The space vertex that the joint can reach is used as the effective space discrete point of the workspace to characterize the reachable motion of the robot.
  • step S208 may include sub-step S2081 and sub-step S2082.
  • sub-step S2081 the workspace of the robot is divided into spaces to obtain discrete points in the workspace.
  • sub-step S2082 the target discrete points that are unreachable by all the joints of the robot are eliminated from the spatial discrete points of the workspace, and the effective spatial discrete points of the workspace are obtained.
  • robot kinematics is used to verify whether the discrete points in the space are the joints of the mobile robot 10 reachable, to determine the target discrete points that are unreachable by all joints of the robot in the workspace, and then remove the target discrete points in the workspace, so as to use the remaining spatial discrete points in the workspace as the corresponding Effective space discrete points.
  • the present application can determine the effective spatial discrete points in the workspace that can actually be reached by the robot joints by executing the above sub-step S2081 and sub-step S2082.
  • Step S209 for each effective space discrete point in the workspace, construct a dynamic system according to the motion teaching trajectory from the effective space discrete point to other effective space discrete points, and construct a dynamic system corresponding to the constructed dynamic system. parameters are stored.
  • each effective space discrete point in the same workspace is traversed, and during the traversal process, access
  • the effective space discrete point is the starting point and the other effective space discrete points are the end points to construct the dynamic system, so that the constructed dynamic system can effectively plan the reasonable distance from the visited effective space discrete point to the other effective space discrete point.
  • the motion trajectory, and then the dynamic system parameters of the dynamic system are stored. Among them, when the dynamic system is constructed, it is necessary to obtain multiple motion trajectory data corresponding to the starting point and the end point.
  • the motion trajectory data may be the movement of the same limb from an effective space discrete point to the motion capture device worn by the teaching staff.
  • curvilinear motion trajectory of discrete points in effective space can also be a linear motion trajectory.
  • the present application can apply the characteristic that the dynamic system can predict a reasonable motion trajectory within a limited range to the robot motion planning process by performing the above steps S208 and S209, so as to ensure that the motion trajectory planned for the robot always conforms to the motion law , so that the robot can achieve the desired motion effect with reference to the planned motion trajectory.
  • the present application in order to ensure that the mobile robot 10 can execute the above-mentioned robot motion planning method through the robot motion planning apparatus 100 , the present application implements the aforementioned functions by dividing the robot motion planning apparatus 100 into functional modules.
  • the specific components of the robot motion planning apparatus 100 provided by the present application will be described below accordingly.
  • the robot motion planning apparatus 100 may include a motion expectation confirmation module 110 , a discrete proximity confirmation module 120 , a dynamic parameter search module 130 , and a desired trajectory planning module 140 .
  • the movement expectation confirmation module 110 is used to determine the current movement expectation starting point and movement end point of the robot.
  • the discrete proximity confirmation module 120 is used to determine, in the working space of the robot, an effective space discrete starting point adjacent to the desired motion starting point, and an effective space discrete end point adjacent to the motion desired ending point.
  • the dynamic parameter search module 130 is used for searching the target dynamic system parameters matching the discrete starting point and the discrete end point of the effective space among the pre-stored sets of dynamic system parameters, wherein the dynamic system corresponding to the target dynamic system parameters is used for planning the The motion trajectory from the discrete starting point of the effective space to the discrete end point of the effective space.
  • the desired trajectory planning module 140 is configured to use the target dynamic system parameters to construct a desired dynamic system matching the desired motion end point, and plan a desired motion trajectory from the desired motion starting point to the desired motion end point based on the desired dynamic system.
  • FIG. 9 is a schematic diagram of the composition of the discrete proximity confirmation module 120 in FIG. 8 .
  • the discrete proximity confirmation module 120 includes a Euclidean distance calculation sub-module 121 and a discrete proximity determination sub-module 122 .
  • the Euclidean distance calculation sub-module 121 is used to calculate the first Euclidean distance between the effective space discrete point and the desired motion starting point for each effective space discrete point in the workspace, and calculate the effective space discrete point and the motion The second Euclidean distance between the desired origins.
  • the discrete proximity determination sub-module 122 is configured to use the effective space discrete point corresponding to the smallest first Euclidean distance as the effective space discrete start point, and the effective space discrete point corresponding to the smallest second Euclidean distance as the effective space discrete end point.
  • FIG. 10 is a schematic diagram of the composition of the desired trajectory planning module 140 in FIG. 8 .
  • the desired trajectory planning module 140 includes a dynamic system reconstruction sub-module 141 , a convergence end point replacement sub-module 142 and a motion trajectory planning sub-module 143 .
  • the dynamic system reconstruction sub-module 141 is used to directly use the target dynamic system parameters to reconstruct the corresponding dynamic system.
  • the convergence end point replacement sub-module 142 is used to replace the position of the trajectory convergence end point of the reconstructed dynamic system by using the motion desired end point to obtain the desired dynamic system.
  • the motion trajectory planning sub-module 143 is used to input the position information of the desired starting point of the motion into the desired dynamic system for motion trajectory planning to obtain the desired motion trajectory.
  • FIG. 11 is the second schematic diagram of the composition of the robot motion planning apparatus 100 provided by the embodiment of the present application.
  • the robot motion planning apparatus 100 may further include an effective discrete confirmation module 150 and a dynamic parameter storage module 160 .
  • the valid discrete confirmation module 150 is used for determining the valid spatial discrete points reachable by the robot joint in the working space of the robot.
  • the dynamic parameter storage module 160 is used for constructing a dynamic system for each effective space discrete point in the workspace, according to the motion teaching trajectory from the effective space discrete point to other effective space discrete points, and constructing the dynamic system The corresponding dynamic system parameters are stored.
  • FIG. 12 is a schematic diagram of the composition of the effective discrete confirmation module 150 in FIG. 11 .
  • the valid discrete confirmation module 150 includes an action space division sub-module 151 and an invalid discrete elimination sub-module 152 .
  • the action space division sub-module 151 is used for space division of the working space of the robot to obtain spatial discrete points of the working space.
  • the invalid discrete elimination sub-module 152 is used to eliminate the target discrete points that are unreachable by all joints of the robot from the spatial discrete points of the workspace, so as to obtain the effective spatial discrete points of the workspace.
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more functions for implementing the specified logical function(s) executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented in dedicated hardware-based systems that perform the specified functions or actions , or can be implemented in a combination of dedicated hardware and computer instructions.
  • each functional module in each embodiment of the present application may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.
  • the functions are implemented in the form of software function modules and sold or used as independent products, they may be stored in a readable storage medium.
  • the technical solution of the present application can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution, and the computer software product is stored in a readable storage medium , including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned readable storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other various programs that can store program codes medium.
  • the present application determines the desired starting point and end point of the robot's current motion, and determines the desired starting point and end point of the motion in the working space of the robot.
  • use the target dynamic system parameters to construct the desired dynamic system matching the desired end point of the motion, and plan the desired motion trajectory from the desired starting point of the motion to the desired end point of the motion based on the desired dynamic system.
  • the system can predict the characteristics of a reasonable motion trajectory within a limited range, and plan a motion trajectory that conforms to the motion law for the robot, so that the robot can refer to the planned motion trajectory to achieve the expected motion effect and improve the motion stability of the robot.

Landscapes

  • Engineering & Computer Science (AREA)
  • Robotics (AREA)
  • Mechanical Engineering (AREA)
  • Automation & Control Theory (AREA)
  • Manipulator (AREA)

Abstract

一种机器人运动规划方法,包括:确定机器人当前的运动期望起点及运动期望终点,并在机器人的工作空间内确定与该运动期望起点邻近的有效空间离散起点,以及与该运动期望终点邻近的有效空间离散终点,而后在预存的多组动态系统参数中,查找用于规划从有效空间离散起点到有效空间离散终点的运动轨迹的目标动态系统参数,接着采用目标动态系统参数构建动态系统来规划从运动期望起点到运动期望终点的期望运动轨迹。该方法通过利用动态系统可在有限范围内预测合理运动轨迹的特性,为机器人规划出符合运动规律的运动轨迹,以达到预想运动效果,提升机器人运动稳定性。还提供一种机器人运动规划装置、可移动机器人及存储介质。

Description

机器人运动规划方法、装置、可移动机器人及存储介质
本申请要求于2020年11月30日在中国专利局提交的、申请号为202011383752.2的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及机器人控制技术领域,具体而言,涉及一种机器人运动规划方法、装置、可移动机器人及存储介质。
背景技术
随着科学技术的不断发展,机器人技术因具有极大的研究价值及应用价值受到了各行各业的广泛重视,而在机器人技术的实际应用过程中,通常需要机器人通过控制至少一个关节从一个起点位置运动到另外一个终点位置的方式,来实现从一个起始状态到目标状态的转换,以完成对应分配的任务。在此基础上,如何规划好机器人从一个起点运动到另外一个起点的整体运动轨迹,使机器人的运动轨迹符合运动规律,避免因机器人运动动作变形出现机器人失稳情况,对本领域技术人员而言便是为达到预想运动效果所需解决的技术问题。
技术问题
有鉴于此,本申请的目的在于提供一种机器人运动规划方法、装置、可移动机器人及存储介质,能够为机器人规划出符合运动规律的运动轨迹,使机器人能够参照规划出的运动轨迹达到预想运动效果,改善机器人失稳问题。
技术解决方案
为了实现上述目的,本申请实施例采用的技术方案如下:
第一方面,本申请提供一种机器人运动规划方法,所述方法包括:
确定机器人当前的运动期望起点及运动期望终点;
在所述机器人的工作空间内确定与所述运动期望起点邻近的有效空间离散起点,以及与所述运动期望终点邻近的有效空间离散终点;
在预存的多组动态系统参数中,查找与所述有效空间离散起点及所述有效空间离散终点匹配的目标动态系统参数,其中所述目标动态系统参数所对应的动态系统用于规划从所述有效空间离散起点到所述有效空间离散终点的运动轨迹;
采用所述目标动态系统参数构建与所述运动期望终点匹配的期望动态系统,并基于所述期望动态系统规划出从所述运动期望起点到所述运动期望终点的期望运动轨迹。
在可选的实施方式中,所述在所述机器人的工作空间内确定与所述运动期望起点邻近的有效空间离散起点,以及与所述运动期望终点邻近的有效空间离散终点的步骤,包括:
针对所述工作空间内的每个有效空间离散点,计算该有效空间离散点与所述运动期望起点之间的第一欧氏距离,并计算该有效空间离散点与所述运动期望起点之间的第二欧氏距离;
将最小第一欧氏距离所对应的有效空间离散点作为所述有效空间离散起点,并将最小第二欧氏距离所对应的有效空间离散点作为所述有效空间离散终点。
在可选的实施方式中,所述采用所述目标动态系统参数构建与所述运动期望终点匹配的期望动态系统,并基于所述期望动态系统规划出从所述运动期望起点到所述运动期望终 点的期望运动轨迹的步骤,包括:
直接采用所述目标动态系统参数重构对应的动态系统;
采用所述运动期望终点对重构出的动态系统的轨迹收敛终点进行位置替换,得到所述期望动态系统;
将所述运动期望起点的位置信息输入到所述期望动态系统中进行运动轨迹规划,得到所述期望运动轨迹。
在可选的实施方式中,所述方法还包括:
在所述机器人的工作空间内确定机器人关节可达的有效空间离散点;
针对所述工作空间中的每个有效空间离散点,根据从该有效空间离散点到其他有效空间离散点的运动示教轨迹进行动态系统构建,并对构建出的动态系统所对应的动态系统参数进行存储。
在可选的实施方式中,所述在所述机器人的工作空间内确定机器人关节可达的有效空间离散点的步骤,包括:
对所述机器人的工作空间进行空间划分,得到所述工作空间的空间离散点;
在所述工作空间的空间离散点中剔除所述机器人各关节均不可达的目标离散点,得到所述工作空间的有效空间离散点。
第二方面,本申请提供一种机器人运动规划装置,所述装置包括:
运动期望确认模块,用于确定机器人当前的运动期望起点及运动期望终点;
离散邻近确认模块,用于在所述机器人的工作空间内确定与所述运动期望起点邻近的有效空间离散起点,以及与所述运动期望终点邻近的有效空间离散终点;
动态参数查找模块,用于在预存的多组动态系统参数中,查找与所述有效空间离散起点及所述有效空间离散终点匹配的目标动态系统参数,其中所述目标动态系统参数所对应的动态系统用于规划从所述有效空间离散起点到所述有效空间离散终点的运动轨迹;
期望轨迹规划模块,用于采用所述目标动态系统参数构建与所述运动期望终点匹配的期望动态系统,并基于所述期望动态系统规划出从所述运动期望起点到所述运动期望终点的期望运动轨迹。
在可选的实施方式中,所述离散邻近确认模块包括:
欧氏距离计算子模块,用于针对所述工作空间内的每个有效空间离散点,计算该有效空间离散点与所述运动期望起点之间的第一欧氏距离,并计算该有效空间离散点与所述运动期望起点之间的第二欧氏距离;
离散邻近确定子模块,用于将最小第一欧氏距离所对应的有效空间离散点作为所述有效空间离散起点,并将最小第二欧氏距离所对应的有效空间离散点作为所述有效空间离散终点。
在可选的实施方式中,所述期望轨迹规划模块包括:
动态系统重构子模块,用于直接采用所述目标动态系统参数重构对应的动态系统;
收敛终点替换子模块,用于采用所述运动期望终点对重构出的动态系统的轨迹收敛终 点进行位置替换,得到所述期望动态系统;
运动轨迹规划子模块,用于将所述运动期望起点的位置信息输入到所述期望动态系统中进行运动轨迹规划,得到所述期望运动轨迹。
在可选的实施方式中,所述装置还包括:
有效离散确认模块,用于在所述机器人的工作空间内确定机器人关节可达的有效空间离散点;
动态参数存储模块,用于针对所述工作空间中的每个有效空间离散点,根据从该有效空间离散点到其他有效空间离散点的运动示教轨迹进行动态系统构建,并对构建出的动态系统所对应的动态系统参数进行存储。
在可选的实施方式中,所述有效离散确认模块包括:
动作空间划分子模块,用于对所述机器人的工作空间进行空间划分,得到所述工作空间的空间离散点;
无效离散剔除子模块,用于在所述工作空间的空间离散点中剔除所述机器人各关节均不可达的目标离散点,得到所述工作空间的有效空间离散点。
第三方面,本申请提供一种可移动机器人,包括处理器和存储器,所述存储器存储有能够被所述处理器执行的计算机程序,所述处理器可执行所述计算机程序,以实现前述实施方式中任意一项所述的机器人运动规划方法。
第四方面,本申请提供一种存储介质,其上存储有计算机程序,所述计算机程序被处理器执行时,实现前述实施方式中任意一项所述的机器人运动规划方法。
有益效果
本申请实施例的有益效果包括如下内容:
本申请通过确定机器人当前的运动期望起点及运动期望终点,并在机器人的工作空间内确定与该运动期望起点邻近的有效空间离散起点,以及与该运动期望终点邻近的有效空间离散终点,而后在预存的多组动态系统参数中,查找用于规划从有效空间离散起点到有效空间离散终点的运动轨迹的目标动态系统参数,接着采用目标动态系统参数构建与运动期望终点匹配的期望动态系统,并基于期望动态系统规划出从运动期望起点到运动期望终点的期望运动轨迹,从而通过利用动态系统能够在有限范围内预测合理运动轨迹的特性,为机器人规划出符合运动规律的运动轨迹,使机器人能够参照规划出的运动轨迹达到预想运动效果,提升机器人运动稳定性。
为使本申请的上述目的、特征和优点能更明显易懂,下文特举较佳实施例,并配合所附附图,作详细说明如下。
附图说明
为了更清楚地说明本申请实施例的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,应当理解,以下附图仅示出了本申请的某些实施例,因此不应被看作是对范围的限定,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他相关的附图。
图1为本申请实施例提供的可移动机器人的组成示意图;
图2为本申请实施例提供的机器人运动规划方法的流程示意图之一;
图3为本申请实施例提供的一种运动轨迹规划示意图;
图4为图2中的步骤S220包括的子步骤的流程示意图;
图5为图2中的步骤S240包括的子步骤的流程示意图;
图6为本申请实施例提供的机器人运动规划方法的流程示意图之二;
图7为图6中的步骤S208包括的子步骤的流程示意图;
图8为本申请实施例提供的机器人运动规划装置的组成示意图之一;
图9为图8中的离散邻近确认模块的组成示意图;
图10为图8中的期望轨迹规划模块的组成示意图;
图11为本申请实施例提供的机器人运动规划装置的组成示意图之二;
图12为图11中的有效离散确认模块的组成示意图。
图标:10-可移动机器人;11-存储器;12-处理器;13-通信单元;14-驱动机构;100-机器人运动规划装置;110-运动期望确认模块;120-离散邻近确认模块;130-动态参数查找模块;140-期望轨迹规划模块;121-欧氏距离计算子模块;122-离散邻近确定子模块;141-动态系统重构子模块;142-收敛终点替换子模块;143-运动轨迹规划子模块;150-有效离散确认模块;151-动作空间划分子模块;152-无效离散剔除子模块;160-动态参数存储模块。
本发明的实施方式
为使本申请实施例的目的、技术方案和优点更加清楚,下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本申请一部分实施例,而不是全部的实施例。通常在此处附图中描述和示出的本申请实施例的组件可以以各种不同的配置来布置和设计。
因此,以下对在附图中提供的本申请的实施例的详细描述并非旨在限制要求保护的本申请的范围,而是仅仅表示本申请的选定实施例。基于本申请中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。
应注意到:相似的标号和字母在下面的附图中表示类似项,因此,一旦某一项在一个附图中被定义,则在随后的附图中不需要对其进行进一步定义和解释。
在本申请的描述中,需要理解的是,术语“中心”、“上”、“下”、“左”、“右”、“竖直”、“水平”、“内”、“外”等指示的方位或位置关系为基于附图所示的方位或位置关系,或者是该申请产品使用时惯常摆放的方位或位置关系,或者是本领域技术人员惯常理解的方位或位置关系,仅是为了便于描述本申请和简化描述,而不是指示或暗示所指的设备或元件必须具有特定的方位、以特定的方位构造和操作,因此不能理解为对本申请的限制。
在本申请的描述中,还需要理解的是,术语“第一”和“第二”等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来,而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。对于本领域的普通技术人员而言,可以具体情况理解上述术语在本申请中的具体含义。
申请人通过辛苦调研发现,现有的机器人运动轨迹规划方案通常是基于人工示教的某个特定运动的运动轨迹进行动态系统构建,而后通过构建出的动态系统对不同运动起点和/或不同运动终点之间的运动轨迹进行预测规划。但需要注意的是,动态系统毕竟是以描述前述特定运动为目的构建出的,其存在有效轨迹的极限预测范围(包括有效起点变化范围及有效终点变化范围)。如果选定需要规划运动轨迹的运动起点超出有效起点变化范围和/或运动终点超出有效终点变化范围时,通过该动态系统规划出的运动轨迹将出现严重变形且不符合机器人运动规律,使机器人参照规划出的运动轨迹作出相应的运动操作时,容易出现因运动动作变形导致的机器人失稳现象,无法达到预期运动效果。
在此情况下,为确保给机器人规划出的运动轨迹始终符合运动规律,使机器人能够参照规划出的运动轨迹达到预想运动效果,并提升机器人运动稳定性,本申请实施例通过提供一种机器人运动规划方法、装置、可移动机器人及存储介质实现前述功能。
下面结合附图,对本申请的一些实施方式作详细说明。在不冲突的情况下,下述的实施例及实施例中的特征可以相互结合。
请参照图1,图1是本申请实施例提供的可移动机器人10的组成示意图。在本申请实施例中,所述可移动机器人10能够在自身工作空间内规划出任一起点与任一终点之间的符合运动规律的运动轨迹,并在参照规划出的运动轨迹作出相应的运动操作时达到预想运动效果,提升自身的运动稳定性。其中,所述工作空间为该可移动机器人10的末端执行器运动描述参考点所能够到达的空间点的集合,其代表该可移动机器人10的最大可移动范围。所述可移动机器人10的工作空间的数目可以为多个,每个工作空间对应该可移动机器人10的一种运动机械结构组成(例如,工作机器人的工作臂,或者仿人机器人的左机械臂、右机械臂、左机械腿和右机械腿中的任意一项)。在本实施例中,所述可移动机器人10可以是,但不限于,仿人机器人、履带机器人、工业机器人等。
在本实施例中,所述可移动机器人10可以包括存储器11、处理器12、通信单元13、驱动机构14及机器人运动规划装置100。其中,所述存储器11、所述处理器12、所述通信单元13及所述驱动机构14各个元件相互之间接或间接地电性连接,以实现数据的传输或交互。例如,所述存储器11、所述处理器12、所述通信单元13及所述驱动机构14这些元件相互之间可通过一条或多条通讯总线或信号线实现电性连接。
在本实施例中,所述存储器11可以是,但不限于,随机存取存储器(Random Access Memory,RAM),只读存储器(Read Only Memory,ROM),可编程只读存储器(Programmable Read-Only Memory,PROM),可擦除只读存储器(Erasable Programmable Read-Only Memory,EPROM),电可擦除只读存储器(Electric Erasable Programmable Read-Only Memory,EEPROM)等。其中,所述存储器11用于存储计算机程序,所述处理器12在接收到执行指令后,可相应地执行所述计算机程序。所述存储器11还可用于存储不同工作空间所对应的用于构建不同起点位置到不同终点位置之间的动态系统所需的动态系统参数,其中一组动态系统参数对应一项起点位置及一项终点位置。
在本实施例中,所述处理器12可以是一种具有信号的处理能力的集成电路芯片。所述处理器12可以是通用处理器,包括中央处理器(Central Processing Unit,CPU)、图形处理器(Graphics Processing Unit,GPU)及网络处理器(Network Processor,NP)、数字信号处理器(DSP)、专用集成电路(ASIC)、现成可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件中的至少一种。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等,可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。
在本实施例中,所述通信单元13用于通过网络建立所述可移动机器人10与其他电子设备之间的通信连接,并通过所述网络收发数据,其中所述网络包括有线通信网络及无线通信网络。例如,所述可移动机器人10能够通过所述通信单元13从其他电子设备处获取操作人员针对该可移动机器人10的某项运动机械结构组成(例如,左机械臂或右机械臂)发出的运动指令,其中该运动指令包括配置的运动起点及运动终点,使该可移动机器人10在配置的运动起点与运动终点之间规划出符合运动规律的运动轨迹,并参照规划出的运动轨迹控制该运动机械结构组成运动达到预想运动效果,确保自身的运动稳定性。
在本实施例中,所述驱动机构14用于实现所述可移动机器人10的可移动功能,所述驱动机构14可以包括该可移动机器人10的至少一种运动机械结构组成,以及驱动所述运动机械结构组成改变自身运动状态的驱动模块。所述可移动机器人10可通过所述驱动机构14参照规划出的运动轨迹执行对应的运动操作。
在本实施例中,所述机器人运动规划装置100包括至少一个能够以软件或固件的形式存储于所述存储器11中或固化在所述可移动机器人10的操作系统中的软件功能模块。所述处理器12可用于执行所述存储器11存储的可执行模块,例如所述机器人运动规划装置100所包括的软件功能模块及计算机程序等。所述可移动机器人10通过所述机器人运动规划装置100利用动态系统可在有限范围内预测合理运动轨迹的特性,针对工作空间内任一起点及任一终点规划出符合运动规律的运动轨迹,使可移动机器人10能够参照规划出的运动轨迹达到预想运动效果,确保机器人运动稳定性。
可以理解的是,图1所示的框图仅为所述可移动机器人10的一种组成示意图,所述可移动机器人10还可包括比图1中所示更多或者更少的组件,或者具有与图1所示不同的配置。图1中所示的各组件可以采用硬件、软件或其组合实现。
在本申请中,为确保所述可移动机器人10始终能够有效地规划出符合运动规律的运动轨迹,以达到确保机器人运动稳定性的预想运动效果,本申请通过提供机器人运动规划方法实现前述目的,其中所述机器人运动规划方法的执行主体可以是上述可移动机器人10,也可以是与上述可移动机器人10通信连接的电子设备。下面对本申请提供的机器人运动规划方法进行详细描述。
可选地,请参照图2,图2是本申请实施例提供的机器人运动规划方法的流程示意图之一。在本申请实施例中,图2所示的机器人运动规划方法的具体流程和步骤如下文所示。
步骤S210,确定机器人当前的运动期望起点及运动期望终点。
在本实施例中,所述运动期望起点与所述运动期望终点可由所述可移动机器人10的操作人员通过网络远程配置,或直接在所述可移动机器人10提供的操控显示界面上进行配置。
步骤S220,在机器人的工作空间内确定与运动期望起点邻近的有效空间离散起点,以及与运动期望终点邻近的有效空间离散终点。
在本实施例中,所述可移动机器人10的每个工作空间均可进行空间细分,将该工作空间划分为若干个空间小块,并针对每个空间小块的空间顶点确认该空间顶点是否为对应运动机械结构组成所包括的各关节能够到达的可达点,而后将该工作空间内确定出的至少一个关节能够到达的空间顶点,作为该工作空间的用于表征机器人运动可达的有效空间离散点。
当确定出所述可移动机器人10当前的运动期望起点及运动期望终点后,可相应地根据所述运动期望起点与所述运动期望终点各自的位置,确定所述运动期望起点与所述运动期 望终点位于哪个工作空间内,并在该工作空间的有效空间离散点中确定出对应的有效空间离散起点及有效空间离散终点。
以图3为例进行说明:若存在一个被抽象为长宽高分别是l,w,h的立方体的工作空间时,可在该工作空间的中心位置处建立一个空间直角(XYZ)坐标系,以通过该空间直角坐标系对该工作空间各位置进行描述。此时如果确定出当前需要规划运动轨迹的运动期望起点A及运动期望终点B,且运动期望起点A与运动期望终点B处于该工作空间内,则会在该工作空间内的各有效空间离散点中分别针对运动期望起点A及运动期望终点B查找邻近的有效空间离散点,得到对应的有效空间离散起点及有效空间离散终点。
可选地,请参照图4,图4是图2中的步骤S220包括的子步骤的流程示意图。在本实施例中,所述步骤S220可以包括子步骤S221~子步骤S222。
子步骤S221,针对工作空间内的每个有效空间离散点,计算该有效空间离散点与运动期望起点之间的第一欧氏距离,并计算该有效空间离散点与运动期望起点之间的第二欧氏距离。
子步骤S222,将最小第一欧氏距离所对应的有效空间离散点作为有效空间离散起点,并将最小第二欧氏距离所对应的有效空间离散点作为有效空间离散终点。
由此,当确定出所述运动期望起点与所述运动期望终点所处的工作空间后,可通过在该工作空间内执行上述子步骤S221及子步骤S222的方式,得到所述有效空间离散起点及所述有效空间离散终点。
步骤S230,在预存的多组动态系统参数中,查找与有效空间离散起点及有效空间离散终点匹配的目标动态系统参数,其中目标动态系统参数所对应的动态系统用于规划从有效空间离散起点到有效空间离散终点的运动轨迹。
在本实施例中,针对所述可移动机器人10的每个工作空间,会预先地遍历该工作空间中的每个有效空间离散点,并在遍历过程中以访问的有效空间离散点为起点而其他有效空间离散点为终点进行动态系统构建,使构建出的动态系统能够有效地规划出从所述访问的有效空间离散点到所述其他有效空间离散点的合理运动轨迹,接着对该动态系统的动态系统参数进行存储。
以一个例子对上述动态系统构建过程进行说明:若所述可移动机器人10存在工作空间a和工作空间b,且工作空间a中存在有效空间离散点a1、a2、a3,工作空间b中存在有效空间离散点b1、b2、b3,则针对工作空间a,需构建从a1到a2的动态系统,从a1到a3的动态系统,从a2到a1的动态系统,从a2到a3的动态系统,从a3到a1的动态系统,从a3到a2的动态系统;针对工作空间b,需构建从b1到b2的动态系统,从b1到b3的动态系统,从b2到b1的动态系统,从b2到b3的动态系统,从b3到b1的动态系统,从b3到b2的动态系统。
在本实施例中,需要注意的是,动态系统是一种常规的机器人运动规划算法,其基本思想是将机器人的n次示教活动建模为一个一阶动态系统的n个实例。其中,这样的一阶动态系统可描述如下:
Figure PCTCN2020139907-appb-000001
其中,
Figure PCTCN2020139907-appb-000002
用于表示对应轨迹上某位置处的轨迹速度,ζ用于表示对应轨迹上某位置处的轨迹位姿,
Figure PCTCN2020139907-appb-000003
是一个连续非线性函数,函数的导数连续并且有唯一的平衡点 即
Figure PCTCN2020139907-appb-000004
∈代表零均值的高斯噪声。一阶动态系统可以用参数集θ进行描述。参数集可以利用概率方法从示教轨迹数据中进行学习。
针对函数f,可利用概率方法将其建模为有限个高斯函数的混合模型,此时动态系统的参数集即可表示为不同高斯函数的先验概率密度、均值及协方差矩阵的集合。其中,第k个高斯函数的先验概率密度即可表达为π k,第k个高斯函数的均值即可表达为μ k,第k个高斯函数的协方差矩阵即可表达为Σ k,其中k=1..K为高斯函数的序号,K为高斯函数的个数。
当给定N条示教轨迹
Figure PCTCN2020139907-appb-000005
其中ζ t,n用于表示第n条示教轨迹上的第t时刻处的轨迹点的轨迹位姿,
Figure PCTCN2020139907-appb-000006
用于表示第n条示教轨迹上的第t时刻处的轨迹点的轨迹速度,那么对每一个轨迹点来说,都将对应存在以下的概率密度函数:
Figure PCTCN2020139907-appb-000007
其中,
Figure PCTCN2020139907-appb-000008
为先验概率,
Figure PCTCN2020139907-appb-000009
是条件概率密度函数,其可表达为:
Figure PCTCN2020139907-appb-000010
而后,针对上式取后验估计可得:
Figure PCTCN2020139907-appb-000011
若令:
Figure PCTCN2020139907-appb-000012
则:
Figure PCTCN2020139907-appb-000013
此时,可以确认在上述动态系统构建过程中,需首先利用示教轨迹数据学习高斯混合模型的各项参数,而后通过最小化估计速度和示教轨迹速度对学习到的高斯混合模型的各项参数进行处理,进而得到用于表征动态系统的具体构成的动态系统参数
Figure PCTCN2020139907-appb-000014
因此,当确定出与机器人当前的运动期望起点邻近的有效空间离散起点,以及与机器人当前的运动期望终点邻近的有效空间离散终点后,会在预存的多组动态系统参数中,查找与从所述有效空间离散起点到所述有效空间离散终点的动态系统相对应的动态系统参数,作为所述目标动态系统参数。
步骤S240,采用目标动态系统参数构建与运动期望终点匹配的期望动态系统,并基于期望动态系统规划出从运动期望起点到运动期望终点的期望运动轨迹。
在本实施例中,当查找到与所述有效空间离散起点及所述有效空间离散终点匹配的目标动态系统参数后,因所述运动期望起点与所述有效空间离散起点邻近,且所述运动期望终点与所述有效空间离散终点邻近,而动态系统具有能够在有限起/终点变化范围内预测合理运动轨迹的特性,那么可以直接将该目标动态系统参数挪用到针对从所述运动期望起点到所述运动期望终点的运动轨迹规划过程中,以直接利用该目标动态系统参数针对所述运动期望起点及所述运动期望终点规划出符合运动规律的期望运动轨迹,使所述可移动机器人10能够参照规划出的期望运动轨迹达到预想运动效果,以确保机器人运动稳定性。
其中,请参照图5,图5是图2中的步骤S240包括的子步骤的流程示意图。在本实施例中,所述步骤S240可以包括子步骤S241~子步骤S243。
子步骤S241,直接采用目标动态系统参数重构对应的动态系统。
子步骤S242,采用运动期望终点对重构出的动态系统的轨迹收敛终点进行位置替换,得到期望动态系统。
子步骤S243,将运动期望起点的位置信息输入到期望动态系统中进行运动轨迹规划,得到期望运动轨迹。
在本实施例中,直接采用所述目标动态系统参数重构出的动态系统能够规划从所述有效空间离散起点周边一定范围内的空间位置到所述有效空间离散终点的符合运动规律的运动轨迹,此时该动态系统的轨迹收敛终点即为所述有效空间离散终点。而当采用所述运动期望终点对重构出的动态系统的轨迹收敛终点进行位置替换后,对应得到的期望动态系统则可用于规划从所述有效空间离散起点周边一定范围内的空间位置到所述运动期望终点的符合运动规律的运动轨迹。此时,将所述运动期望起点的位置信息输入到所述期望动态系统中,即可通过该期望动态系统直接规划出符合运动规律的从所述运动期望起点到所述运动期望终点的期望运动轨迹。
由此,本申请可通过执行上述步骤S210~步骤S240,为所述可移动机器人10的工作空间内的任一起点及任一终点规划出符合运动规律的运动轨迹,使所述可移动机器人10在参照规划出的运动轨迹作出相应的运动操作时达到预想运动效果,确保机器人运动稳定性。
可选地,请参照图6,图6是本申请实施例提供的机器人运动规划方法的流程示意图之二。在本申请实施例中,图6所示的机器人运动规划方法与图2所示的机器人运动规划方法相比,图6所示的机器人运动规划方法还可以包括步骤S208及步骤S209,以通过所述步骤S208及步骤S209确保图2所示的机器人运动规划方法能够正常实施。
步骤S208,在机器人的工作空间内确定机器人关节可达的有效空间离散点。
在本实施例中,所述可移动机器人10的每个工作空间均可进行空间细分。针对每个工作空间,将该工作空间划分为若干个空间小块,并确认每个空间小块的空间顶点是否为机器人关节能够到达的可达点,而后将该工作空间内确定出的至少一个关节能够到达的空间顶点,作为该工作空间的用于表征机器人运动可达的有效空间离散点。
其中,请参照图7,图7是图6中的步骤S208包括的子步骤的流程示意图。在本实施例中,所述步骤S208可以包括子步骤S2081及子步骤S2082。
子步骤S2081,对机器人的工作空间进行空间划分,得到工作空间的空间离散点。
在本实施例中,针对所述可移动机器人10的每个工作空间,可采用预设三维尺寸对该工作空间进行空间等分,并将得到的每个空间小块的各空间顶点作为该工作空间的空间离散点。以图3为例,若图3中的工作空间的尺寸为1m×1m×1m,那么当将这个工作空间按照10cm等距离划分,则对应划分出的空间小块的尺寸为10cm×10cm×10cm,此时该工作空间的空间离散点数目为11×11×11=1331个。
子步骤S2082,在工作空间的空间离散点中剔除机器人各关节均不可达的目标离散点,得到工作空间的有效空间离散点。
在本实施例中,当确定出工作空间的所有空间离散点后,会针对该工作空间的每个空间离散点,利用机器人运动学验证该空间离散点是否为所述可移动机器人10的各关节可达,以确定出该工作空间中的机器人各关节均不可达的目标离散点,而后在该工作空间中剔除掉所述目标离散点,从而将该工作空间内剩余的空间离散点作为对应的有效空间离散点。
由此,本申请可通过执行上述子步骤S2081及子步骤S2082,确定出工作空间内能被机器人关节真正够得到的有效空间离散点。
步骤S209,针对工作空间中的每个有效空间离散点,根据从该有效空间离散点到其他有效空间离散点的运动示教轨迹进行动态系统构建,并对构建出的动态系统所对应的动态系统参数进行存储。
在本实施例中,当确定出所述可移动机器人10的每个工作空间所包括的有效空间离散点后,会遍历同一工作空间中的每个有效空间离散点,并在遍历过程中以访问的有效空间离散点为起点而其他有效空间离散点为终点进行动态系统构建,使构建出的动态系统可有效地规划出从所述访问的有效空间离散点到所述其他有效空间离散点的合理运动轨迹,接着对该动态系统的动态系统参数进行存储。其中,动态系统构建时需要获取对应起点到终点的多条运动轨迹数据,所述运动轨迹数据可以是由示教人员所穿戴的动捕设备采集到的同一肢体部位从一个有效空间离散点运动到另外一个有效空间离散点的曲线运动轨迹,也可以是直线运动轨迹。此外,动态系统构建时所涉及的具体运算过程,可参照上文中对步骤S230的动态系统的相关描述,在此就不再一一赘述了。
由此,本申请可通过执行上述步骤S208及步骤S209,将动态系统可在有限范围内预测合理运动轨迹的特性应用到机器人运动规划过程中,以确保为机器人规划出的运动轨迹 始终符合运动规律,使机器人能够参照规划出的运动轨迹达到预想运动效果。
在本申请中,为确保所述可移动机器人10能够通过所述机器人运动规划装置100执行上述机器人运动规划方法,本申请通过对所述机器人运动规划装置100进行功能模块划分的方式实现前述功能。下面对本申请提供的机器人运动规划装置100的具体组成进行相应描述。
可选地,请参照图8,图8是本申请实施例提供的机器人运动规划装置100的组成示意图之一。在本申请实施例中,所述机器人运动规划装置100可以包括运动期望确认模块110、离散邻近确认模块120、动态参数查找模块130及期望轨迹规划模块140。
运动期望确认模块110,用于确定机器人当前的运动期望起点及运动期望终点。
离散邻近确认模块120,用于在机器人的工作空间内确定与运动期望起点邻近的有效空间离散起点,以及与运动期望终点邻近的有效空间离散终点。
动态参数查找模块130,用于在预存的多组动态系统参数中,查找与有效空间离散起点及有效空间离散终点匹配的目标动态系统参数,其中目标动态系统参数所对应的动态系统用于规划从有效空间离散起点到有效空间离散终点的运动轨迹。
期望轨迹规划模块140,用于采用目标动态系统参数构建与运动期望终点匹配的期望动态系统,并基于期望动态系统规划出从运动期望起点到运动期望终点的期望运动轨迹。
可选地,请参照图9,图9是图8中的离散邻近确认模块120的组成示意图。在本实施例中,所述离散邻近确认模块120包括欧氏距离计算子模块121及离散邻近确定子模块122。
欧氏距离计算子模块121,用于针对工作空间内的每个有效空间离散点,计算该有效空间离散点与运动期望起点之间的第一欧氏距离,并计算该有效空间离散点与运动期望起点之间的第二欧氏距离。
离散邻近确定子模块122,用于将最小第一欧氏距离所对应的有效空间离散点作为有效空间离散起点,并将最小第二欧氏距离所对应的有效空间离散点作为有效空间离散终点。
可选地,请参照图10,图10是图8中的期望轨迹规划模块140的组成示意图。在本实施例中,所述期望轨迹规划模块140包括动态系统重构子模块141、收敛终点替换子模块142及运动轨迹规划子模块143。
动态系统重构子模块141,用于直接采用目标动态系统参数重构对应的动态系统。
收敛终点替换子模块142,用于采用运动期望终点对重构出的动态系统的轨迹收敛终点进行位置替换,得到期望动态系统。
运动轨迹规划子模块143,用于将运动期望起点的位置信息输入到期望动态系统中进行运动轨迹规划,得到期望运动轨迹。
可选地,请参照图11,图11是本申请实施例提供的机器人运动规划装置100的组成示意图之二。在本申请实施例中,所述机器人运动规划装置100还可以包括有效离散确认模块150及动态参数存储模块160。
有效离散确认模块150,用于在机器人的工作空间内确定机器人关节可达的有效空间离散点。
动态参数存储模块160,用于针对工作空间中的每个有效空间离散点,根据从该有效 空间离散点到其他有效空间离散点的运动示教轨迹进行动态系统构建,并对构建出的动态系统所对应的动态系统参数进行存储。
可选地,请参照图12,图12是图11中的有效离散确认模块150的组成示意图。在本实施例中,所述有效离散确认模块150包括动作空间划分子模块151及无效离散剔除子模块152。
动作空间划分子模块151,用于对机器人的工作空间进行空间划分,得到工作空间的空间离散点。
无效离散剔除子模块152,用于在工作空间的空间离散点中剔除机器人各关节均不可达的目标离散点,得到工作空间的有效空间离散点。
需要说明的是,本申请实施例所提供的机器人运动规划装置100,其基本原理及产生的技术效果与前述的机器人运动规划方法相同,为简要描述,本实施例部分未提及之处,可参考上述的针对机器人运动规划方法的描述内容。
在本申请所提供的实施例中,应该理解到,所揭露的装置和方法,也可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的,例如,附图中的流程图和框图显示了根据本申请的实施例的装置、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上,流程图或框图中的每个方框可以代表一个模块、程序段或代码的一部分,所述模块、程序段或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意,在有些作为替换的实现方式中,方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如,两个连续的方框实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这依所涉及的功能而定。也要注意的是,框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合,可以用执行规定的功能或动作的专用的基于硬件的系统来实现,或者可以用专用硬件与计算机指令的组合来实现。
另外,在本申请各个实施例中的各功能模块可以集成在一起形成一个独立的部分,也可以是各个模块单独存在,也可以两个或两个以上模块集成形成一个独立的部分。
所述功能如果以软件功能模块的形式实现并作为独立的产品销售或使用时,可以存储在一个可读存储介质中。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个可读存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的可读存储介质包括:U盘、移动硬盘、只读存储器(ROM,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
综上所述,在本申请提供的一种机器人运动规划方法、装置、可移动机器人及存储介质中,本申请通过确定机器人当前的运动期望起点及运动期望终点,并在机器人的工作空间内确定与该运动期望起点邻近的有效空间离散起点,以及与该运动期望终点邻近的有效空间离散终点,而后在预存的多组动态系统参数中,查找用于规划从有效空间离散起点到有效空间离散终点的运动轨迹的目标动态系统参数,接着采用目标动态系统参数构建与运动期望终点匹配的期望动态系统,并基于期望动态系统规划出从运动期望起点到运动期望终点的期望运动轨迹,从而通过利用动态系统能够在有限范围内预测合理运动轨迹的特性,为机器人规划出符合运动规律的运动轨迹,使机器人能够参照规划出的运动轨迹达到预想运动效果,提升机器人运动稳定性。
以上所述,仅为本申请的各种实施方式,但本申请的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本申请揭露的技术范围内,可轻易想到变化或替换,都应涵盖在本申请的保护范围之内。因此,本申请的保护范围应当以权利要求的保护范围为准。

Claims (12)

  1. 一种机器人运动规划方法,其特征在于,所述方法包括:
    确定机器人当前的运动期望起点及运动期望终点;
    在所述机器人的工作空间内确定与所述运动期望起点邻近的有效空间离散起点,以及与所述运动期望终点邻近的有效空间离散终点;
    在预存的多组动态系统参数中,查找与所述有效空间离散起点及所述有效空间离散终点匹配的目标动态系统参数,其中所述目标动态系统参数所对应的动态系统用于规划从所述有效空间离散起点到所述有效空间离散终点的运动轨迹;
    采用所述目标动态系统参数构建与所述运动期望终点匹配的期望动态系统,并基于所述期望动态系统规划出从所述运动期望起点到所述运动期望终点的期望运动轨迹。
  2. 根据权利要求1所述的方法,其特征在于,所述在所述机器人的工作空间内确定与所述运动期望起点邻近的有效空间离散起点,以及与所述运动期望终点邻近的有效空间离散终点的步骤,包括:
    针对所述工作空间内的每个有效空间离散点,计算该有效空间离散点与所述运动期望起点之间的第一欧氏距离,并计算该有效空间离散点与所述运动期望起点之间的第二欧氏距离;
    将最小第一欧氏距离所对应的有效空间离散点作为所述有效空间离散起点,并将最小第二欧氏距离所对应的有效空间离散点作为所述有效空间离散终点。
  3. 根据权利要求1所述的方法,其特征在于,所述采用所述目标动态系统参数构建与所述运动期望终点匹配的期望动态系统,并基于所述期望动态系统规划出从所述运动期望起点到所述运动期望终点的期望运动轨迹的步骤,包括:
    直接采用所述目标动态系统参数重构对应的动态系统;
    采用所述运动期望终点对重构出的动态系统的轨迹收敛终点进行位置替换,得到所述期望动态系统;
    将所述运动期望起点的位置信息输入到所述期望动态系统中进行运动轨迹规划,得到所述期望运动轨迹。
  4. 根据权利要求1-3中任意一项所述的方法,其特征在于,所述方法还包括:
    在所述机器人的工作空间内确定机器人关节可达的有效空间离散点;
    针对所述工作空间中的每个有效空间离散点,根据从该有效空间离散点到其他有效空间离散点的运动示教轨迹进行动态系统构建,并对构建出的动态系统所对应的动态系统参数进行存储。
  5. 根据权利要求4所述的方法,其特征在于,所述在所述机器人的工作空间内确定机器人关节可达的有效空间离散点的步骤,包括:
    对所述机器人的工作空间进行空间划分,得到所述工作空间的空间离散点;
    在所述工作空间的空间离散点中剔除所述机器人各关节均不可达的目标离散点,得到所述工作空间的有效空间离散点。
  6. 一种机器人运动规划装置,其特征在于,所述装置包括:
    运动期望确认模块,用于确定机器人当前的运动期望起点及运动期望终点;
    离散邻近确认模块,用于在所述机器人的工作空间内确定与所述运动期望起点邻近的有效空间离散起点,以及与所述运动期望终点邻近的有效空间离散终点;
    动态参数查找模块,用于在预存的多组动态系统参数中,查找与所述有效空间离散起点及所述有效空间离散终点匹配的目标动态系统参数,其中所述目标动态系统参数所对应的动态系统用于规划从所述有效空间离散起点到所述有效空间离散终点的运动轨迹;
    期望轨迹规划模块,用于采用所述目标动态系统参数构建与所述运动期望终点匹配的期望动态系统,并基于所述期望动态系统规划出从所述运动期望起点到所述运动期望终点的期望运动轨迹。
  7. 根据权利要求6所述的装置,其特征在于,所述离散邻近确认模块包括:
    欧氏距离计算子模块,用于针对所述工作空间内的每个有效空间离散点,计算该有效空间离散点与所述运动期望起点之间的第一欧氏距离,并计算该有效空间离散点与所述运动期望起点之间的第二欧氏距离;
    离散邻近确定子模块,用于将最小第一欧氏距离所对应的有效空间离散点作为所述有效空间离散起点,并将最小第二欧氏距离所对应的有效空间离散点作为所述有效空间离散终点。
  8. 根据权利要求6所述的装置,其特征在于,所述期望轨迹规划模块包括:
    动态系统重构子模块,用于直接采用所述目标动态系统参数重构对应的动态系统;
    收敛终点替换子模块,用于采用所述运动期望终点对重构出的动态系统的轨迹收敛终点进行位置替换,得到所述期望动态系统;
    运动轨迹规划子模块,用于将所述运动期望起点的位置信息输入到所述期望动态系统中进行运动轨迹规划,得到所述期望运动轨迹。
  9. 根据权利要求6-8中任意一项所述的装置,其特征在于,所述装置还包括:
    有效离散确认模块,用于在所述机器人的工作空间内确定机器人关节可达的有效空间离散点;
    动态参数存储模块,用于针对所述工作空间中的每个有效空间离散点,根据从该有效空间离散点到其他有效空间离散点的运动示教轨迹进行动态系统构建,并对构建出的动态系统所对应的动态系统参数进行存储。
  10. 根据权利要求9所述的装置,其特征在于,所述有效离散确认模块包括:
    动作空间划分子模块,用于对所述机器人的工作空间进行空间划分,得到所述工作空间的空间离散点;
    无效离散剔除子模块,用于在所述工作空间的空间离散点中剔除所述机器人各关节均不可达的目标离散点,得到所述工作空间的有效空间离散点。
  11. 一种可移动机器人,其特征在于,包括处理器和存储器,所述存储器存储有能够被所述处理器执行的计算机程序,所述处理器可执行所述计算机程序,以实现权利要求1-5中任意一项所述的机器人运动规划方法。
  12. 一种存储介质,其上存储有计算机程序,其特征在于,所述计算机程序被处理器执 行时,实现权利要求1-5中任意一项所述的机器人运动规划方法。
PCT/CN2020/139907 2020-11-30 2020-12-28 机器人运动规划方法、装置、可移动机器人及存储介质 Ceased WO2022110452A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011383752.2 2020-11-30
CN202011383752.2A CN112428275B (zh) 2020-11-30 2020-11-30 机器人运动规划方法、装置、可移动机器人及存储介质

Publications (1)

Publication Number Publication Date
WO2022110452A1 true WO2022110452A1 (zh) 2022-06-02

Family

ID=74698113

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/139907 Ceased WO2022110452A1 (zh) 2020-11-30 2020-12-28 机器人运动规划方法、装置、可移动机器人及存储介质

Country Status (2)

Country Link
CN (1) CN112428275B (zh)
WO (1) WO2022110452A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115816454A (zh) * 2022-12-09 2023-03-21 中车青岛四方车辆研究所有限公司 一种机器人控制性能动态特性评估方法及系统
CN116840826A (zh) * 2023-05-06 2023-10-03 北京电子工程总体研究所 一种离散点坐标的轨迹生成方法、装置、介质及设备
CN117359629A (zh) * 2023-10-31 2024-01-09 国网新疆电力有限公司超高压分公司 一种基于DMPs的机器人运动规划方法及系统
CN117798926A (zh) * 2024-01-24 2024-04-02 广东环境保护工程职业学院 一种机器人运行监控方法、装置、系统和介质
CN121169899A (zh) * 2025-09-29 2025-12-19 上海万怡医学科技股份有限公司 基于视觉检测的机器人自动调研方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160354930A1 (en) * 2013-03-05 2016-12-08 Autofuss Programming of a Robotic Arm Using a Motion Capture System
CN108972554A (zh) * 2018-08-06 2018-12-11 中汽研汽车检验中心(武汉)有限公司 一种基于拟合曲线曲率特征的复杂曲面机器人路径点提取方法
CN109931942A (zh) * 2019-03-13 2019-06-25 浙江大华技术股份有限公司 机器人路径生成方法、装置、机器人和存储介质
CN109940619A (zh) * 2019-04-09 2019-06-28 深圳前海达闼云端智能科技有限公司 一种轨迹规划方法、电子设备及存储介质
CN110645991A (zh) * 2019-10-30 2020-01-03 深圳市银星智能科技股份有限公司 一种基于节点调节的路径规划方法、装置及服务器

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3797986B2 (ja) * 2003-07-03 2006-07-19 ファナック株式会社 ロボットオフラインシミュレーション装置
CN102087530B (zh) * 2010-12-07 2012-06-13 东南大学 基于手绘地图和路径的移动机器人视觉导航方法
CN102528802B (zh) * 2010-12-31 2014-12-03 北京中科广视科技有限公司 九自由度机器人的运动驱动方法
CN102998684B (zh) * 2012-11-21 2016-12-21 厦门雅迅网络股份有限公司 一种基于贝塞尔曲线的终端定位轨迹拟合方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160354930A1 (en) * 2013-03-05 2016-12-08 Autofuss Programming of a Robotic Arm Using a Motion Capture System
CN108972554A (zh) * 2018-08-06 2018-12-11 中汽研汽车检验中心(武汉)有限公司 一种基于拟合曲线曲率特征的复杂曲面机器人路径点提取方法
CN109931942A (zh) * 2019-03-13 2019-06-25 浙江大华技术股份有限公司 机器人路径生成方法、装置、机器人和存储介质
CN109940619A (zh) * 2019-04-09 2019-06-28 深圳前海达闼云端智能科技有限公司 一种轨迹规划方法、电子设备及存储介质
CN110645991A (zh) * 2019-10-30 2020-01-03 深圳市银星智能科技股份有限公司 一种基于节点调节的路径规划方法、装置及服务器

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115816454A (zh) * 2022-12-09 2023-03-21 中车青岛四方车辆研究所有限公司 一种机器人控制性能动态特性评估方法及系统
CN116840826A (zh) * 2023-05-06 2023-10-03 北京电子工程总体研究所 一种离散点坐标的轨迹生成方法、装置、介质及设备
CN117359629A (zh) * 2023-10-31 2024-01-09 国网新疆电力有限公司超高压分公司 一种基于DMPs的机器人运动规划方法及系统
CN117798926A (zh) * 2024-01-24 2024-04-02 广东环境保护工程职业学院 一种机器人运行监控方法、装置、系统和介质
CN121169899A (zh) * 2025-09-29 2025-12-19 上海万怡医学科技股份有限公司 基于视觉检测的机器人自动调研方法

Also Published As

Publication number Publication date
CN112428275A (zh) 2021-03-02
CN112428275B (zh) 2022-04-19

Similar Documents

Publication Publication Date Title
WO2022110452A1 (zh) 机器人运动规划方法、装置、可移动机器人及存储介质
Khan et al. Obstacle avoidance and tracking control of redundant robotic manipulator: An RNN-based metaheuristic approach
CN109434831B (zh) 机器人运行方法、装置、机器人、电子设备及可读介质
US10894322B2 (en) Robot motion planning
Li et al. Representing robot geometry as distance fields: Applications to whole-body manipulation
Hauser et al. Multi-modal motion planning for a humanoid robot manipulation task
CN116079747A (zh) 机器人跨具身控制方法、系统、计算机设备和存储介质
Liu et al. Review on motion planning of robotic manipulator in dynamic environments
Li Robot target localization and interactive multi-mode motion trajectory tracking based on adaptive iterative learning
Hashemian et al. Kinematically smoothing trajectories by NURBS reparameterization–an innovative approach
Wan et al. Integrated assembly and motion planning using regrasp graphs
Zeng et al. A two-stage path planning approach for multiple car-like robots based on PH curves and a modified harmony search algorithm
Sun et al. Digital twin-driven reinforcement learning for obstacle avoidance in robot manipulators: A self-improving online training framework
Xidias et al. Time-optimal task scheduling for articulated manipulators in environments cluttered with obstacles
Suzuki et al. Posture evaluation for mobile manipulators using manipulation ability, tolerance on grasping, and pose error of end-effector
CN114705191A (zh) 地图生成方法、装置、设备和存储介质
CN120023818A (zh) 机械臂控制方法、装置、电子设备及计算机可读存储介质
Sacks Path planning for planar articulated robots using configuration spaces and compliant motion
Van Do et al. An Efficient Improved A* Algorithm for Mobile Robot Path Planning in Complex Environments
Iwasaki et al. Online motion planning based on swept volume search with replanning using sequential quadratic programming
CN108858205A (zh) 一种基于人形机器人关节控制的平滑处理方法、装置和系统
Masehian et al. Mobile robot online motion planning using generalized Voronoi graphs
Laumond Motion planning for PLM: state of the art and perspectives
Karnad et al. Modeling human motion patterns for multi-robot planning
Eberhard et al. Graph Neural Model Predictive Control for High-Dimensional Systems

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20963340

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20963340

Country of ref document: EP

Kind code of ref document: A1