WO2022198992A1 - 一种机械臂运动规划方法、装置、可读存储介质及机械臂 - Google Patents

一种机械臂运动规划方法、装置、可读存储介质及机械臂 Download PDF

Info

Publication number
WO2022198992A1
WO2022198992A1 PCT/CN2021/124618 CN2021124618W WO2022198992A1 WO 2022198992 A1 WO2022198992 A1 WO 2022198992A1 CN 2021124618 W CN2021124618 W CN 2021124618W WO 2022198992 A1 WO2022198992 A1 WO 2022198992A1
Authority
WO
WIPO (PCT)
Prior art keywords
path
motion planning
robotic arm
preset
gradient
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/CN2021/124618
Other languages
English (en)
French (fr)
Inventor
陈金亮
刘益彰
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 WO2022198992A1 publication Critical patent/WO2022198992A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Program-controlled manipulators
    • B25J9/16—Program controls
    • B25J9/1656—Program controls characterised by programming, planning systems for manipulators
    • B25J9/1664—Program controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
    • B25J9/1666—Avoiding collision or forbidden zones
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J18/00—Arms
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Program-controlled manipulators
    • B25J9/16—Program controls
    • B25J9/1679—Program controls characterised by the tasks executed

Definitions

  • the present application belongs to the field of robotics technology, and in particular relates to a method, device, computer-readable storage medium and a robotic arm for motion planning of a robotic arm.
  • RRT Rapidly-exploring Random Trees
  • BiRRT Bi-directional Rapidly Expanding Random Trees
  • the embodiments of the present application provide a method, device, computer-readable storage medium and a manipulator for motion planning of a manipulator, so as to solve the problem that the motion planning path obtained by the existing manipulator motion planning method is often different from the optimal path. There is a big gap.
  • a first aspect of the embodiments of the present application provides a method for planning a motion of a robotic arm, which may include:
  • the first motion planning path is iteratively optimized according to a preset optimization evaluation function to obtain an optimized second motion planning path.
  • performing iterative optimization on the first motion planning path according to a preset optimization evaluation function to obtain an optimized second motion planning path may include:
  • the current planned path is updated and calculated according to the gradient of the current planned path to obtain an updated planned path;
  • the updated planned path is taken as the new current planned path, and the process of calculating the gradient of the current planned path according to the optimization evaluation function is returned to be executed. and its subsequent steps;
  • the updated planning path is determined as the optimized second motion planning path.
  • optimization evaluation function can be:
  • K is a preset differential operator matrix
  • I N is a preset differential operator
  • A is the Hessian matrix of the optimization evaluation function
  • A K T K
  • x is The motion planning path of the robotic arm
  • f(x) is the optimization evaluation function.
  • the updating calculation of the current planning path according to the gradient of the current planning path to obtain the updated planning path may include:
  • the current planned path is updated and calculated according to the following formula:
  • x i is the current planned path, is the gradient of the current planned path, n is the preset update step size, and x i+1 is the update planned path.
  • calculating the gradient of the current planned path according to the optimization evaluation function may include:
  • the iterative termination condition may be: the gradient of the current planned path is less than a preset gradient threshold, or the iterative optimization duration is greater than a preset duration threshold.
  • the robotic arm motion planning algorithm may be a fast expanding random tree planning algorithm or a bidirectional fast expanding random tree planning algorithm.
  • a second aspect of the embodiments of the present application provides a robotic arm motion planning device, which may include:
  • a motion planning module configured to perform motion planning on the robotic arm using a preset robotic arm motion planning algorithm, and obtain a first motion planning path for the robotic arm to move from a preset initial pose to a preset target pose;
  • the iterative optimization module is configured to iteratively optimize the first motion planning path according to a preset optimization evaluation function to obtain an optimized second motion planning path.
  • the iterative optimization module may include:
  • a current planning path determining unit configured to use the first motion planning path as the current planning path
  • a gradient calculation unit configured to calculate the gradient of the current planned path according to the optimization evaluation function
  • an update calculation unit configured to update and calculate the current planned path according to the gradient of the current planned path to obtain an updated planned path
  • a current planned path update unit configured to use the updated planned path as a new current planned path if the gradient of the current planned path does not meet a preset iteration termination condition
  • a second motion planning path determining unit configured to determine the updated planning path as an optimized second motion planning path if the gradient of the current planning path satisfies the iteration termination condition.
  • optimization evaluation function is:
  • K is a preset differential operator matrix
  • I N is a preset differential operator
  • A is the Hessian matrix of the optimization evaluation function
  • A K T K
  • x is The motion planning path of the robotic arm
  • f(x) is the optimization evaluation function.
  • the update calculation unit is specifically configured to update and calculate the current planned path according to the following formula:
  • x i is the current planned path, is the gradient of the current planned path, n is the preset update step size, and x i+1 is the update planned path.
  • the gradient calculation unit is specifically configured to calculate the gradient of the current planned path according to the following formula:
  • the iterative termination condition is: the gradient of the current planned path is less than a preset gradient threshold, or the iterative optimization duration is greater than a preset duration threshold.
  • the robotic arm motion planning algorithm is a fast expanding random tree planning algorithm or a bidirectional fast expanding random tree planning algorithm.
  • a third aspect of the embodiments of the present application provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any one of the above-mentioned robotic arm motion planning methods is implemented. step.
  • a fourth aspect of the embodiments of the present application provides a robotic arm, including a memory, a processor, and a computer program stored in the memory and executable on the processor, when the processor executes the computer program The steps of implementing any one of the above-mentioned robotic arm motion planning methods.
  • a fifth aspect of the embodiments of the present application provides a computer program product, which, when the computer program product runs on a robotic arm, causes the robotic arm to execute the steps of any of the above-mentioned methods for motion planning of a robotic arm.
  • the embodiment of the present application has the beneficial effect that: the embodiment of the present application uses a preset motion planning algorithm for the manipulator to plan the motion of the manipulator, and obtains that the manipulator moves from the preset initial pose to the position of the manipulator.
  • an optimization evaluation function for evaluating the motion planning path is constructed, and based on this optimization evaluation function, the motion planning path (ie, the first motion planning path) obtained by the initial planning is iteratively optimized, so as to obtain a more approximate The motion planning path of the optimal path (ie, the second motion planning path).
  • FIG. 1 is a flowchart of an embodiment of a method for planning a motion of a robotic arm in an embodiment of the present application
  • FIG. 2 is a schematic flowchart of iterative optimization of the first motion planning path according to a preset optimization evaluation function
  • FIG. 3 is a schematic diagram of a comparison between a first motion planning path and a second motion planning path
  • FIG. 4 is a structural diagram of an embodiment of a robotic arm motion planning device in an embodiment of the application.
  • FIG. 5 is a schematic block diagram of a robotic arm in an embodiment of the present application.
  • the term “if” may be contextually interpreted as “when” or “once” or “in response to determining” or “in response to detecting” .
  • the phrases “if it is determined” or “if the [described condition or event] is detected” may be interpreted, depending on the context, to mean “once it is determined” or “in response to the determination” or “once the [described condition or event] is detected. ]” or “in response to detection of the [described condition or event]”.
  • an embodiment of a robotic arm motion planning method in the embodiment of the present application may include:
  • Step S101 using a preset motion planning algorithm of the manipulator to plan the motion of the manipulator, and obtain a first motion planning path for the manipulator to move from a preset initial pose to a preset target pose.
  • the set composed of the poses of all joints of the manipulator can be described by the configuration space, that is, the C space, and when the manipulator and obstacles are considered, the C space will be divided into two spaces , namely the obstacle space C Obs and the free space C free .
  • C Obs can be described by the following formula:
  • C Obs is a set of poses that meet the following conditions: the pose (ie q) belongs to the C space and the robot arm (ie Robot(q)) in this pose and the obstacle (ie Obs) intersect not empty, the two collide.
  • C free can be described by the following formula:
  • C free is the complement of C Obs .
  • C free is an optional area in which the robotic arm can move and find the optimal trajectory and the shortest time.
  • the basic idea of the manipulator motion planning algorithm is to establish a path diagram for solving the manipulator motion planning problem based on C free .
  • the specific process can include:
  • the collision-free path ⁇ of the manipulator is obtained by sampling according to the motion planning algorithm of the manipulator, and the path must satisfy ⁇ [0,h] ⁇ C free , where 0 represents the starting time point of the motion planning , h represents the termination time point of the motion planning, the pose of the robot arm at any planning time point between the start time point and the termination time point of the path is within the range of the free space C free , and the path
  • any robot arm motion planning algorithm in the prior art may be used to perform motion planning for the robot arm, including but not limited to specific planning algorithms such as RRT or BiRRT. Due to the strong randomness of these algorithms, the obtained motion planning path often has a large gap with the optimal path, so it needs to be optimized through subsequent steps. For the convenience of distinction, the motion planning path at this time is recorded as the first motion planning path here.
  • Step S102 iteratively optimize the first motion planning path according to a preset optimization evaluation function to obtain an optimized second motion planning path.
  • the motion planning path of the robotic arm can be defined as a (h+1) ⁇ (n+1)-dimensional matrix, that is, Among them, the right subscripts 0, 1, ..., h represent each planned time point from the start time point to the end time point, Q represents the pose of the robot arm at a certain planned time point, and each joint of the robot arm can be used.
  • an optimization evaluation function f(x) is introduced in the embodiment of the present application to evaluate the motion planning path of the manipulator. Specifically, each joint angle of the manipulator can be moved The sum of the squares of the Euclidean distance is used as the optimization evaluation function, namely:
  • the optimization evaluation function can be transformed into the following form:
  • e is the matrix corresponding to the initial pose
  • Q 0 is the initial pose, namely Q init
  • K is the preset differential operator matrix
  • I N is the preset differential operator
  • A is the Hessian Matrix of the optimization evaluation function
  • A K T K.
  • the evaluation problem of the motion planning of the manipulator can be transformed into a non-convex optimization problem, that is, the manipulator motion planning algorithm can satisfy the joint configuration constraints and end effector constraints, joint limit constraints and obstacles when sampling and expanding.
  • the local optimal path is obtained, so that the optimization evaluation function approaches the minimum value, or the motion planning path of the robot arm from the initial pose to the target pose approaches the optimal path, namely: argmin x (f(x)).
  • the first motion planning path may be iteratively optimized through the process shown in FIG. 2 :
  • Step S1021 taking the first motion planning path as the current planning path.
  • Step S1022 Calculate the gradient of the current planned path according to the optimization evaluation function.
  • the gradient of the current planned path can be calculated according to the following formula:
  • x i is the current planned path
  • x i is the gradient of the current planned path
  • x i is the partial derivative corresponding to x i .
  • Step S1023 Perform update calculation on the current planned path according to the gradient of the current planned path to obtain an updated planned path.
  • the current planned path can be updated and calculated according to the following formula:
  • ⁇ is the preset update step size, and its specific value can be set according to the actual situation
  • x i+1 is the update planning path.
  • Step S1024 judging whether the gradient of the current planned path satisfies a preset iteration termination condition.
  • the iteration termination condition may be: the gradient of the current planned path is less than a preset gradient threshold, or the iterative optimization duration is greater than a preset duration threshold.
  • the specific values of the gradient threshold and the duration threshold can be set according to actual conditions.
  • step S1025 is performed, and if the gradient of the current planned path satisfies the iteration termination condition, step S1026 is performed.
  • Step S1025 taking the updated planned path as a new current planned path.
  • step S1025 After step S1025 is performed, step S1022 and subsequent steps are returned to perform a new round of iterative optimization.
  • Step S1026 Determine the updated planning path as the optimized motion planning path.
  • FIG. 3 is a schematic diagram showing the comparison between the first motion planning path and the second motion planning path, from which it can be seen that the second motion planning path is closer to the optimal path than the first motion planning path.
  • the embodiment of the present application uses a preset motion planning algorithm for the manipulator to plan the motion of the manipulator, and obtains the first motion planning path for the manipulator to move from the preset initial pose to the preset target pose;
  • the set optimization evaluation function performs iterative optimization on the first motion planning path to obtain the optimized second motion planning path.
  • an optimization evaluation function for evaluating the motion planning path is constructed, and based on this optimization evaluation function, the motion planning path (ie, the first motion planning path) obtained by the initial planning is iteratively optimized, so as to obtain a more approximate The motion planning path of the optimal path (ie, the second motion planning path).
  • FIG. 4 shows a structural diagram of an embodiment of a robotic arm motion planning apparatus provided in an embodiment of the present application.
  • a robotic arm motion planning device may include:
  • the motion planning module 401 is configured to perform motion planning on the robotic arm using a preset robotic arm motion planning algorithm, and obtain a first motion planning path for the robotic arm to move from a preset initial pose to a preset target pose;
  • the iterative optimization module 402 is configured to iteratively optimize the first motion planning path according to a preset optimization evaluation function to obtain an optimized second motion planning path.
  • the iterative optimization module may include:
  • a current planning path determining unit configured to use the first motion planning path as the current planning path
  • a gradient calculation unit configured to calculate the gradient of the current planned path according to the optimization evaluation function
  • an update calculation unit configured to update and calculate the current planned path according to the gradient of the current planned path to obtain an updated planned path
  • a current planned path update unit configured to use the updated planned path as a new current planned path if the gradient of the current planned path does not meet a preset iteration termination condition
  • a second motion planning path determining unit configured to determine the updated planning path as an optimized second motion planning path if the gradient of the current planning path satisfies the iteration termination condition.
  • optimization evaluation function is:
  • K is a preset differential operator matrix
  • I N is a preset differential operator
  • A is the Hessian matrix of the optimization evaluation function
  • A K T K
  • x is The motion planning path of the robotic arm
  • f(x) is the optimization evaluation function.
  • the update calculation unit is specifically configured to update and calculate the current planned path according to the following formula:
  • x i is the current planned path, is the gradient of the current planned path, n is the preset update step size, and x i+1 is the update planned path.
  • the gradient calculation unit is specifically configured to calculate the gradient of the current planned path according to the following formula:
  • the iterative termination condition is: the gradient of the current planned path is less than a preset gradient threshold, or the iterative optimization duration is greater than a preset duration threshold.
  • the robotic arm motion planning algorithm is a fast expanding random tree planning algorithm or a bidirectional fast expanding random tree planning algorithm.
  • FIG. 5 shows a schematic block diagram of a robotic arm provided by an embodiment of the present application. For the convenience of description, only parts related to the embodiment of the present application are shown.
  • the robotic arm 5 of this embodiment includes: a processor 50 , a memory 51 , and a computer program 52 stored in the memory 51 and executable on the processor 50 .
  • the processor 50 executes the computer program 52
  • the steps in each of the above embodiments of the robot arm motion planning method are implemented, for example, steps S101 to S102 shown in FIG. 1 .
  • the processor 50 executes the computer program 52
  • the functions of the modules/units in the foregoing device embodiments, such as the functions of the modules 401 to 402 shown in FIG. 4 are implemented.
  • the computer program 52 can be divided into one or more modules/units, and the one or more modules/units are stored in the memory 51 and executed by the processor 50 to complete the this application.
  • the one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 52 in the robotic arm 5 .
  • FIG. 5 is only an example of the robot arm 5, and does not constitute a limitation to the robot arm 5. It may include more or less components than the one shown, or combine some components, or different components
  • the robotic arm 5 may further include an input and output device, a network access device, a bus, and the like.
  • the processor 50 may be a central processing unit (Central Processing Unit, CPU), or other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • the memory 51 may be an internal storage unit of the robotic arm 5 , such as a hard disk or a memory of the robotic arm 5 .
  • the memory 51 may also be an external storage device of the robotic arm 5, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) equipped on the robotic arm 5 card, Flash Card, etc.
  • the memory 51 may also include both an internal storage unit of the robotic arm 5 and an external storage device.
  • the memory 51 is used to store the computer program and other programs and data required by the robotic arm 5 .
  • the memory 51 can also be used to temporarily store data that has been output or will be output.
  • the disclosed apparatus/robot and method may be implemented in other ways.
  • the device/manipulator embodiments described above are only illustrative.
  • the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units. Or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented.
  • the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.
  • the integrated modules/units if implemented in the form of software functional units and sold or used as independent products, may be stored in a computer-readable storage medium.
  • the present application can implement all or part of the processes in the methods of the above embodiments, and can also be completed by instructing the relevant hardware through a computer program.
  • the computer program can be stored in a computer-readable storage medium, and the computer When the program is executed by the processor, the steps of the foregoing method embodiments can be implemented.
  • the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form, and the like.
  • the computer-readable storage medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read-Only Memory) ), random access memory (RAM, Random Access Memory), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content contained in the computer-readable storage medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, computer-readable Storage media exclude electrical carrier signals and telecommunications signals.

Landscapes

  • Engineering & Computer Science (AREA)
  • Robotics (AREA)
  • Mechanical Engineering (AREA)
  • Manipulator (AREA)

Abstract

本申请属于机器人技术领域，尤其涉及一种机械臂运动规划方法、装置、计算机可读存储介质及机械臂。所述方法包括：使用预设的机械臂运动规划算法对机械臂进行运动规划，得到所述机械臂从预设的初始位姿运动至预设的目标位姿的第一运动规划路径；根据预设的优化评价函数对所述第一运动规划路径进行迭代优化，得到优化后的第二运动规划路径。通过本申请，构建了对运动规划路径进行评价的优化评价函数，基于这一优化评价函数对初始规划得到的第一运动规划路径进行迭代优化，从而得到更加趋近于最优路径的第二运动规划路径。

Description

一种机械臂运动规划方法、装置、可读存储介质及机械臂
本申请要求于2021年03月22日在中国专利局提交的、申请号为202110301126.2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
本申请属于机器人技术领域，尤其涉及一种机械臂运动规划方法、装置、计算机可读存储介质及机械臂。
背景技术
在现有技术中，一般是使用快速扩展随机树(Rapidly-exploring Random Trees，RRT)或者双向快速扩展随机树(Bi-directional RRT，BiRRT)等规划算法对机械臂进行运动规划。但这些算法都具有很强的随机性，所得到的运动规划路径往往与最优路径存在较大的差距。
技术问题
有鉴于此，本申请实施例提供了一种机械臂运动规划方法、装置、计算机可读存储介质及机械臂，以解决现有的机械臂运动规划方法所得到的运动规划路径往往与最优路径存在较大的差距的问题。
技术解决方案
本申请实施例的第一方面提供了一种机械臂运动规划方法，可以包括：
使用预设的机械臂运动规划算法对机械臂进行运动规划，得到所述机械臂从预设的初始位姿运动至预设的目标位姿的第一运动规划路径；
根据预设的优化评价函数对所述第一运动规划路径进行迭代优化，得到优化后的第二运动规划路径。
进一步地，所述根据预设的优化评价函数对所述第一运动规划路径进行迭代优化，得到优化后的第二运动规划路径，可以包括：
将所述第一运动规划路径作为当前规划路径；
根据所述优化评价函数计算所述当前规划路径的梯度；
根据当前规划路径的梯度对所述当前规划路径进行更新计算，得到更新规划路径；
若所述当前规划路径的梯度不满足预设的迭代终止条件，则将所述更新规划路径作为新的当前规划路径，并返回执行所述根据所述优化评价函数计算所述当前规划路径的梯度的步骤及其后续步骤；
若所述当前规划路径的梯度满足所述迭代终止条件，则将所述更新规划路径确定为优化后的第二运动规划路径。
进一步地，所述优化评价函数可以为：
f(x)＝||Kx+e|| 2＝x TAx+2x TKe+e Te
Figure PCTCN2021124618-appb-000001
其中，e为与所述初始位姿对应的矩阵，且
Figure PCTCN2021124618-appb-000002
Q 0为所述初始位姿，K为预设的微分算子矩阵，I N为预设的微分算子，A为所述优化评价函数的黑塞矩阵，且A＝K TK，x为所述机械臂的运动规划路径，f(x)为所述优化评价函数。
进一步地，所述根据当前规划路径的梯度对所述当前规划路径进行更新计算，得到更新规划路径，可以包括：
根据下式对所述当前规划路径进行更新计算：
Figure PCTCN2021124618-appb-000003
其中，x i为所述当前规划路径，
Figure PCTCN2021124618-appb-000004
为所述当前规划路径的梯度，η为预设的更新步长，x i+1为所述更新规划路径。
进一步地，所述根据所述优化评价函数计算所述当前规划路径的梯度，可以包括：
根据下式计算所述当前规划路径的梯度：
Figure PCTCN2021124618-appb-000005
进一步地，所述迭代终止条件可以为：所述当前规划路径的梯度小于预设的梯度阈值，或迭代优化时长大于预设的时长阈值。
进一步地，所述机械臂运动规划算法可以为快速扩展随机树规划算法或双向快速扩展随机树规划算法。
本申请实施例的第二方面提供了一种机械臂运动规划装置，可以包括：
运动规划模块，用于使用预设的机械臂运动规划算法对机械臂进行运动规划，得到所述机械臂从预设的初始位姿运动至预设的目标位姿的第一运动规划路径；
迭代优化模块，用于根据预设的优化评价函数对所述第一运动规划路径进行迭代优化，得到优化后的第二运动规划路径。
进一步地，所述迭代优化模块可以包括：
当前规划路径确定单元，用于将所述第一运动规划路径作为当前规划路径；
梯度计算单元，用于根据所述优化评价函数计算所述当前规划路径的梯度；
更新计算单元，用于根据当前规划路径的梯度对所述当前规划路径进行更新计算，得到更新规划路径；
当前规划路径更新单元，用于若所述当前规划路径的梯度不满足预设的迭代终止条件，则将所述更新规划路径作为新的当前规划路径；
第二运动规划路径确定单元，用于若所述当前规划路径的梯度满足所述迭代终止条件，则将所述更新规划路径确定为优化后的第二运动规划路径。
进一步地，所述优化评价函数为：
f(x)＝||Kx+e|| 2＝x TAx+2x TKe+e Te
Figure PCTCN2021124618-appb-000006
其中，e为与所述初始位姿对应的矩阵，且
Figure PCTCN2021124618-appb-000007
Q 0为所述初始位姿，K为预设的微分算子矩阵，I N为预设的微分算子，A为所述优化评价函数的黑塞矩阵，且A＝K TK，x为所述机械臂的运动规划路径，f(x)为所述优化评价函数。
进一步地，所述更新计算单元具体用于根据下式对所述当前规划路径进行更新计算：
Figure PCTCN2021124618-appb-000008
其中，x i为所述当前规划路径，
Figure PCTCN2021124618-appb-000009
为所述当前规划路径的梯度，η为预设的更新步长，x i+1为所述更新规划路径。
进一步地，所述梯度计算单元具体用于根据下式计算所述当前规划路径的梯度：
Figure PCTCN2021124618-appb-000010
进一步地，所述迭代终止条件为：所述当前规划路径的梯度小于预设的梯度阈值，或迭代优化时长大于预设的时长阈值。
进一步地，所述机械臂运动规划算法为快速扩展随机树规划算法或双向快速扩展随机树规划算法。
本申请实施例的第三方面提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时实现上述任一种机械臂运动规划方法的步骤。
本申请实施例的第四方面提供了一种机械臂，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现上述任一种机械臂运动规划方法的步骤。
本申请实施例的第五方面提供了一种计算机程序产品，当计算机程序产品在机械臂上运行时，使得机械臂执行上述任一种机械臂运动规划方法的步骤。
有益效果
本申请实施例与现有技术相比存在的有益效果是：本申请实施例使用预设的机械臂运动规划算法对机械臂进行运动规划，得到所述机械臂从预设的初始位姿运动至预设的目标位姿的第一运动规划路径；根据预设的优化评价函数对所述第一运动规划路径进行迭代优化，得到优化后的第二运动规划路径。通过本申请实施例，构建了对运动规划路径进行评价的优化评价函数，基于这一优化评价函数对初始规划得到的运动规划路径(即第一运动规划路径)进行迭代优化，从而得到更加趋近于最优路径的运动规划路径(即第二运动规划路径)。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，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它的附图。
图1为本申请实施例中一种机械臂运动规划方法的一个实施例流程图；
图2为根据预设的优化评价函数对第一运动规划路径进行迭代优化的示意流程图；
图3为第一运动规划路径和第二运动规划路径的对比示意图；
图4为本申请实施例中一种机械臂运动规划装置的一个实施例结构图；
图5为本申请实施例中一种机械臂的示意框图。
本发明的实施方式
为使得本申请的发明目的、特征、优点能够更加的明显和易懂，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，下面所描述的实施例仅仅是本申请一部分实施例，而非全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例，都属于本申请保护的范围。
应当理解，当在本说明书和所附权利要求书中使用时，术语“包括”指示所描述特征、整体、步骤、操作、元素和/或组件的存在，但并不排除一个或多个其它特征、整体、步骤、操作、元素、组件和/或其集合的存在或添加。
还应当理解，在此本申请说明书中所使用的术语仅仅是出于描述特定实施例的目的而并不意在限制本申请。如在本申请说明书和所附权利要求书中所使用的那样，除非上下文清楚地指明其它情况，否则单数形式的“一”、“一个”及“该”意在包括复数形式。
还应当进一步理解，在本申请说明书和所附权利要求书中使用的术语“和/或”是指相关联列出的项中的一个或多个的任何组合以及所有可能组合，并且包括这些组合。
如在本说明书和所附权利要求书中所使用的那样，术语“如果”可以依据上下文被解释为“当...时”或“一旦”或“响应于确定”或“响应于检测到”。类似地，短语“如果确定”或“如果检测到[所描述条件或事件]”可以依据上下文被解释为意指“一旦确定”或“响应于确定”或“一旦检测到[所描述条件或事件]”或“响应于检测到[所描述条件或事件]”。
另外，在本申请的描述中，术语“第一”、“第二”、“第三”等仅用于区分描述，而不能理解为指示或暗示相对重要性。
请参阅图1，本申请实施例中一种机械臂运动规划方法的一个实施例可以包括：
步骤S101、使用预设的机械臂运动规划算法对机械臂进行运动规划，得到机械臂从预设的初始位姿运动至预设的目标位姿的第一运动规划路径。
在本申请实施例中，可以通过位姿空间(configuration space)描述机械臂所有关节的位姿构成的集合，即C空间，而当考虑机械臂和障碍物时，C空间会分为两个空间，即障碍物空间C Obs和自由空间C free。
其中，C Obs可以用下式进行描述：
Figure PCTCN2021124618-appb-000011
即C Obs为满足以下条件的位姿构成的集合：该位姿(即q)属于C空间且在该位姿下的机械臂(即Robot(q))与障碍物(即Obs)相交不为空，两者发生碰撞。
相应地，C free可以用下式进行描述：
C free＝C-C Obs
即C free为C Obs的补集。
C free是机械臂能够在其中运动并发现轨迹最优、时间最短的可选区域。机械臂运动规划算法的基本思想是基于C free建立用于解决机械臂运动规划问题的路径图，其具体流程可以包括：
(1)确定机械臂的工作空间W；
(2)确定工作空间W中的障碍物Obs以及机械臂Robot；
(3)确定机械臂对应的C空间，以及障碍物空间C Obs和自由空间C free；
(4)确定机械臂的初始位姿Q init和目标位姿Q end；
(5)在自由空间C free中根据机械臂运动规划算法采样获得机械臂的无碰撞路径τ，该路径需满足τ[0,h]→C free，其中，0表示运动规划的起始时间点，h表示运动规划的终止时间点，该路径在从起始时间点至终止时间点之间的任意一个规划时间点时的机械臂位姿均处在自由空间C free的范围内，且该路径在起始时间点时的机械臂位姿为初始位姿，即τ[0]＝Q init，该路径在终止时间点时的机械臂位姿为目标位姿，即τ[h]＝Q end。
在本申请实施例中，可以使用现有技术中的任意一种机械臂运动规划算法来对机械臂进行运动规划，包括但不限于RRT或BiRRT等具体的规划算法。由于这些算法都具有很强的随机性，所得到的运动规划路径往往与最优路径存在较大的差距，因此需要通过后续步骤对其进行优化处理。为了便于区分，此处将此时的运动规划路径记为第一运动规划路径。
步骤S102、根据预设的优化评价函数对第一运动规划路径进行迭代优化，得到优化后的第二运动规划路径。
在本申请实施例中，可以将机械臂的运动规划路径定义为(h+1)×(n+1)维的矩阵，即
Figure PCTCN2021124618-appb-000012
其中，右下标的0，1，…，h表示从起始时间点至终止时间点之间的各个规划时间点，Q表示某个规划时间点的机械臂位姿，可以用机械臂的各个关节角所构成的向量进行表示，即：Q＝[q 0,q 1,…,q n] T，其中，n+1表示机械臂的运动自由度，q 0,q 1,…,q n分别为机械臂的各个关节角。
为了衡量机械臂的运动规划路径的优劣，在本申请实施例中引入了优化评价函数f(x)来对机械臂的运动规划路径进行评价，具体地，可以将机械臂的各个关节角运动的欧式距离的平方和作为优化评价函数，即：
Figure PCTCN2021124618-appb-000013
在实际计算过程中，可以将该优化评价函数转化为如下形式：
f(x)＝||Kx+e|| 2＝x TAx+2x TKe+e Te
Figure PCTCN2021124618-appb-000014
其中，e为与初始位姿对应的矩阵，且
Figure PCTCN2021124618-appb-000015
Q 0为初始位 姿，也即Q init，K为预设的微分算子矩阵，I N为预设的微分算子，且
Figure PCTCN2021124618-appb-000016
A为优化评价函数的黑塞矩阵(Hessian Matrix)，且A＝K TK。
通过该优化评价函数，可以将机械臂的运动规划的评价问题转化为非凸优化问题，即机械臂运动规划算法采样扩展时在满足关节构型约束与末端执行器约束，关节限位约束与障碍物避碰约束的同时，获得局部最优路径，使得优化评价函数趋近最小值，或者说使机械臂从初始位姿运动至目标位姿的运动规划路径趋近于最优路径，即：argmin x(f(x))。
为了使得运动规划路径趋近于最优路径，在本申请实施例中可以通过如图2所示的过程对第一运动规划路径进行迭代优化：
步骤S1021、将第一运动规划路径作为当前规划路径。
步骤S1022、根据优化评价函数计算当前规划路径的梯度。
具体地，可以根据下式计算当前规划路径的梯度：
Figure PCTCN2021124618-appb-000017
其中，x i为当前规划路径，
Figure PCTCN2021124618-appb-000018
为当前规划路径的梯度，
Figure PCTCN2021124618-appb-000019
为与x i对应的偏导数。
步骤S1023、根据当前规划路径的梯度对当前规划路径进行更新计算，得到更新规划路径。
具体地，可以根据下式对当前规划路径进行更新计算：
Figure PCTCN2021124618-appb-000020
其中，η为预设的更新步长，其具体取值可以根据实际情况进行设置，x i+1为更新规划路径。
步骤S1024、判断当前规划路径的梯度是否满足预设的迭代终止条件。
在本申请实施例中，迭代终止条件可以为：当前规划路径的梯度小于预设的梯度阈值，或迭代优化时长大于预设的时长阈值。其中，梯度阈值和时长阈值的具体取值均可以根据实际情况进行设置。
若当前规划路径的梯度不满足预设的迭代终止条件，则执行步骤S1025，若当前规划路径的梯度满足迭代终止条件，则执行步骤S1026。
步骤S1025、将更新规划路径作为新的当前规划路径。
在执行步骤S1025之后，返回执行步骤S1022及其后续步骤，即进行新一轮的迭代优化。
步骤S1026、将更新规划路径确定为优化后的运动规划路径。
为了便于区分，此处将优化后的运动规划路径记为第二运动规划路径。图3所示即为第一运动规划路径和第二运动规划路径的对比示意图，从中可以看出，第二运动规划路径较之于第一运动规划路径更加趋近于最优路径。
综上，本申请实施例使用预设的机械臂运动规划算法对机械臂进行运动规划，得到机械臂从预设的初始位姿运动至预设的目标位姿的第一运动规划路径；根据预设的优化评价函数对第一运动规划路径进行迭代优化，得到优化后的第二运动规划路径。通过本申请实施例，构建了对运动规划路径进行评价的优化评价函数，基于这一优化评价函数对初始规划得到的运动规划路径(即第一运动规划路径)进行迭代优化，从而得到更加趋近于最优路径的运动规划路径(即第二运动规划路径)。
应理解，上述实施例中各步骤的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
对应于上文实施例所述的一种机械臂运动规划方法，图4示出了本申请实施例提供的一种机械臂运动规划装置的一个实施例结构图。
本实施例中，一种机械臂运动规划装置可以包括：
运动规划模块401，用于使用预设的机械臂运动规划算法对机械臂进行运动规划，得到所述机械臂从预设的初始位姿运动至预设的目标位姿的第一运动规划路径；
迭代优化模块402，用于根据预设的优化评价函数对所述第一运动规划路径进行迭代优化，得到优化后的第二运动规划路径。
进一步地，所述迭代优化模块可以包括：
当前规划路径确定单元，用于将所述第一运动规划路径作为当前规划路径；
梯度计算单元，用于根据所述优化评价函数计算所述当前规划路径的梯度；
更新计算单元，用于根据当前规划路径的梯度对所述当前规划路径进行更新计算，得到更新规划路径；
当前规划路径更新单元，用于若所述当前规划路径的梯度不满足预设的迭代终止条件，则将所述更新规划路径作为新的当前规划路径；
第二运动规划路径确定单元，用于若所述当前规划路径的梯度满足所述迭代终止条件，则将所述更新规划路径确定为优化后的第二运动规划路径。
进一步地，所述优化评价函数为：
f(x)＝||Kx+e|| 2＝x TAx+2x TKe+e Te
Figure PCTCN2021124618-appb-000021
其中，e为与所述初始位姿对应的矩阵，且
Figure PCTCN2021124618-appb-000022
Q 0为所述初始位姿，K为预设的微分算子矩阵，I N为预设的微分算子，A为所述优化评价函数的黑塞矩阵，且A＝K TK，x为所述机械臂的运动规划路径，f(x)为所述优化评价函数。
进一步地，所述更新计算单元具体用于根据下式对所述当前规划路径进行更新计算：
Figure PCTCN2021124618-appb-000023
其中，x i为所述当前规划路径，
Figure PCTCN2021124618-appb-000024
为所述当前规划路径的梯度，η为预设的更新步长，x i+1为所述更新规划路径。
进一步地，所述梯度计算单元具体用于根据下式计算所述当前规划路径的梯度：
Figure PCTCN2021124618-appb-000025
进一步地，所述迭代终止条件为：所述当前规划路径的梯度小于预设的梯度阈值，或迭代优化时长大于预设的时长阈值。
进一步地，所述机械臂运动规划算法为快速扩展随机树规划算法或双向快速扩展随机树规划算法。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的装置，模块和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述或记载的部分，可以参见其它实施例的相关描述。
图5示出了本申请实施例提供的一种机械臂的示意框图，为了便于说明，仅示出了与本申请实施例相关的部分。
如图5所示，该实施例的机械臂5包括：处理器50、存储器51以及存储在所述存储器51中并可在所述处理器50上运行的计算机程序52。所述处理器50执行所述计算机程序52时实现上述各个机械臂运动规划方法实施例中的步骤，例如图1所示的步骤S101至步骤S102。或者，所述处理器50执行所述计算机程序52时实现上述各装置实施例中各模块/单元的功能，例如图4所示模块401至模块402的功能。
示例性的，所述计算机程序52可以被分割成一个或多个模块/单元，所述一个或者多 个模块/单元被存储在所述存储器51中，并由所述处理器50执行，以完成本申请。所述一个或多个模块/单元可以是能够完成特定功能的一系列计算机程序指令段，该指令段用于描述所述计算机程序52在所述机械臂5中的执行过程。
本领域技术人员可以理解，图5仅仅是机械臂5的示例，并不构成对机械臂5的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件，例如所述机械臂5还可以包括输入输出设备、网络接入设备、总线等。
所述处理器50可以是中央处理单元(Central Processing Unit，CPU)，还可以是其它通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现场可编程门阵列(Field-Programmable Gate Array，FPGA)或者其它可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。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。
所述存储器51可以是所述机械臂5的内部存储单元，例如机械臂5的硬盘或内存。所述存储器51也可以是所述机械臂5的外部存储设备，例如所述机械臂5上配备的插接式硬盘，智能存储卡(Smart Media Card，SMC)，安全数字(Secure Digital，SD)卡，闪存卡(Flash Card)等。进一步地，所述存储器51还可以既包括所述机械臂5的内部存储单元也包括外部存储设备。所述存储器51用于存储所述计算机程序以及所述机械臂5所需的其它程序和数据。所述存储器51还可以用于暂时地存储已经输出或者将要输出的数据。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，仅以上述各功能单元、模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元、模块完成，即将所述装置的内部结构划分成不同的功能单元或模块，以完成以上描述的全部或者部分功能。实施例中的各功能单元、模块可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中，上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。另外，各功能单元、模块的具体名称也只是为了便于相互区分，并不用于限制本申请的保护范围。上述系统中单元、模块的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述或记载的部分，可以参见其它实施例的相关描述。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可 以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
在本申请所提供的实施例中，应该理解到，所揭露的装置/机械臂和方法，可以通过其它的方式实现。例如，以上所描述的装置/机械臂实施例仅仅是示意性的，例如，所述模块或单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通讯连接可以是通过一些接口，装置或单元的间接耦合或通讯连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读存储介质中。基于这样的理解，本申请实现上述实施例方法中的全部或部分流程，也可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一计算机可读存储介质中，该计算机程序在被处理器执行时，可实现上述各个方法实施例的步骤。其中，所述计算机程序包括计算机程序代码，所述计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。所述计算机可读存储介质可以包括：能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、电载波信号、电信信号以及软件分发介质等。需要说明的是，所述计算机可读存储介质包含的内容可以根据司法管辖区内立法和专利实践的要求进行适当的增减，例如在某些司法管辖区，根据立法和专利实践，计算机可读存储介质不包括电载波信号和电信信号。
以上所述实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围，均应包含在本申请的保护范围之内。

Claims (10)

  1. 一种机械臂运动规划方法，其特征在于，包括：
    使用预设的机械臂运动规划算法对机械臂进行运动规划，得到所述机械臂从预设的初始位姿运动至预设的目标位姿的第一运动规划路径；
    根据预设的优化评价函数对所述第一运动规划路径进行迭代优化，得到优化后的第二运动规划路径。
  2. 根据权利要求1所述的机械臂运动规划方法，其特征在于，所述根据预设的优化评价函数对所述第一运动规划路径进行迭代优化，得到优化后的第二运动规划路径，包括：
    将所述第一运动规划路径作为当前规划路径；
    根据所述优化评价函数计算所述当前规划路径的梯度；
    根据当前规划路径的梯度对所述当前规划路径进行更新计算，得到更新规划路径；
    若所述当前规划路径的梯度不满足预设的迭代终止条件，则将所述更新规划路径作为新的当前规划路径，并返回执行所述根据所述优化评价函数计算所述当前规划路径的梯度的步骤及其后续步骤；
    若所述当前规划路径的梯度满足所述迭代终止条件，则将所述更新规划路径确定为优化后的第二运动规划路径。
  3. 根据权利要求2所述的机械臂运动规划方法，其特征在于，所述优化评价函数为：
    f(x)＝||Kx+e|| 2＝x TAx+2x TKe+e Te
    Figure PCTCN2021124618-appb-100001
    其中，e为与所述初始位姿对应的矩阵，且
    Figure PCTCN2021124618-appb-100002
    Q 0为所述初始位姿，K为预设的微分算子矩阵，I N为预设的微分算子，A为所述优化评价函数的黑塞矩阵，且A＝K TK，x为所述机械臂的运动规划路径，f(x)为所述优化评价函数。
  4. 根据权利要求2所述的机械臂运动规划方法，其特征在于，所述根据当前规划路径的梯度对所述当前规划路径进行更新计算，得到更新规划路径，包括：
    根据下式对所述当前规划路径进行更新计算：
    Figure PCTCN2021124618-appb-100003
    其中，x i为所述当前规划路径，
    Figure PCTCN2021124618-appb-100004
    为所述当前规划路径的梯度，η为预设的更新步长，x i+1为所述更新规划路径。
  5. 根据权利要求2所述的机械臂运动规划方法，其特征在于，所述根据所述优化评价函数计算所述当前规划路径的梯度，包括：
    根据下式计算所述当前规划路径的梯度：
    Figure PCTCN2021124618-appb-100005
    其中，f(x)为所述优化评价函数，x i为所述当前规划路径，
    Figure PCTCN2021124618-appb-100006
    为所述当前规划路径的梯度。
  6. 根据权利要求2所述的机械臂运动规划方法，其特征在于，所述迭代终止条件为：所述当前规划路径的梯度小于预设的梯度阈值，或迭代优化时长大于预设的时长阈值。
  7. 根据权利要求1至6中任一项所述的机械臂运动规划方法，其特征在于，所述机械臂运动规划算法为快速扩展随机树规划算法或双向快速扩展随机树规划算法。
  8. 一种机械臂运动规划装置，其特征在于，包括：
    运动规划模块，用于使用预设的机械臂运动规划算法对机械臂进行运动规划，得到所述机械臂从预设的初始位姿运动至预设的目标位姿的第一运动规划路径；
    迭代优化模块，用于根据预设的优化评价函数对所述第一运动规划路径进行迭代优化，得到优化后的第二运动规划路径。
  9. 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1至7中任一项所述的机械臂运动规划方法的步骤。
  10. 一种机械臂，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现如权利要求1至7中任一项所述的机械臂运动规划方法的步骤。
PCT/CN2021/124618 2021-03-22 2021-10-19 一种机械臂运动规划方法、装置、可读存储介质及机械臂 Ceased WO2022198992A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110301126.2A CN113119114B (zh) 2021-03-22 2021-03-22 一种机械臂运动规划方法、装置、可读存储介质及机械臂
CN202110301126.2 2021-03-22

Publications (1)

Publication Number Publication Date
WO2022198992A1 true WO2022198992A1 (zh) 2022-09-29

Family

ID=76773589

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/124618 Ceased WO2022198992A1 (zh) 2021-03-22 2021-10-19 一种机械臂运动规划方法、装置、可读存储介质及机械臂

Country Status (2)

Country Link
CN (1) CN113119114B (zh)
WO (1) WO2022198992A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113119114B (zh) * 2021-03-22 2022-10-21 深圳市优必选科技股份有限公司 一种机械臂运动规划方法、装置、可读存储介质及机械臂
CN115946127A (zh) * 2023-03-02 2023-04-11 张国强 工业机械臂智能路径规划方法、系统、电子设备以及存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20120069949A (ko) * 2010-12-21 2012-06-29 고려대학교 산학협력단 이동 로봇의 최적 경로 생성 방법 및 이를 이용한 이동 로봇
WO2016177963A1 (fr) * 2015-05-04 2016-11-10 Commissariat à l'énergie atomique et aux énergies alternatives Procédé, programme d'ordinateur et système pour la commande d'un déplacement d'un agent navigant dans un environnement organisé en réseau
CN109895097A (zh) * 2019-02-19 2019-06-18 宁波凯德科技服务有限公司 一种焊接机器人运动模型次梯度方法
CN110640736A (zh) * 2019-10-23 2020-01-03 南京工业大学 用于智能制造的机械臂运动规划方法
CN111629867A (zh) * 2017-12-12 2020-09-04 皮尔茨公司 封闭运动系统中的无碰撞运动规划
CN112091979A (zh) * 2020-10-10 2020-12-18 哈尔滨工业大学 一种基于位置级逆运动学的七自由度机械臂限位优化方法
CN113119114A (zh) * 2021-03-22 2021-07-16 深圳市优必选科技股份有限公司 一种机械臂运动规划方法、装置、可读存储介质及机械臂

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106909151A (zh) * 2017-01-22 2017-06-30 无锡卡尔曼导航技术有限公司 用于农机无人驾驶的路径规划及其控制方法
CN108326852B (zh) * 2018-01-16 2021-01-05 西北工业大学 一种多目标优化的空间机械臂轨迹规划方法
CN109318230A (zh) * 2018-09-29 2019-02-12 鲁东大学 机器人动作优化方法、装置、计算机设备和存储介质
CN109202904B (zh) * 2018-09-30 2020-10-20 湘潭大学 一种机械臂运动路径的确定方法及确定系统
CN109636077B (zh) * 2019-02-19 2022-11-25 浙江大学 基于双重局部位姿变换的变节点装配路径规划方法
CN111216132A (zh) * 2020-01-21 2020-06-02 桂林电子科技大学 基于改进rrt算法的六自由度机械臂路径规划方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20120069949A (ko) * 2010-12-21 2012-06-29 고려대학교 산학협력단 이동 로봇의 최적 경로 생성 방법 및 이를 이용한 이동 로봇
WO2016177963A1 (fr) * 2015-05-04 2016-11-10 Commissariat à l'énergie atomique et aux énergies alternatives Procédé, programme d'ordinateur et système pour la commande d'un déplacement d'un agent navigant dans un environnement organisé en réseau
CN111629867A (zh) * 2017-12-12 2020-09-04 皮尔茨公司 封闭运动系统中的无碰撞运动规划
CN109895097A (zh) * 2019-02-19 2019-06-18 宁波凯德科技服务有限公司 一种焊接机器人运动模型次梯度方法
CN110640736A (zh) * 2019-10-23 2020-01-03 南京工业大学 用于智能制造的机械臂运动规划方法
CN112091979A (zh) * 2020-10-10 2020-12-18 哈尔滨工业大学 一种基于位置级逆运动学的七自由度机械臂限位优化方法
CN113119114A (zh) * 2021-03-22 2021-07-16 深圳市优必选科技股份有限公司 一种机械臂运动规划方法、装置、可读存储介质及机械臂

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
HUANG, WENBING ET AL.: "PLANNING METHOD CONSIDERING THE KINETIC CHARACTERISTICS OF THE END EFFECTOR OF A REDUNDANT MANIPULATOR", JOURNAL OF TSINGHUA UNIVERSITY (SCIENCE AND TECHNOLOGY), vol. 54, no. 12, 20 December 2014 (2014-12-20), pages 1544 - 1548, XP055969507, ISSN: 1000-0054 *
ZHANG, TING ET AL.: "Application of Optimizing the Robot Manipulator's Path with Mixed Chaos", DEVELOPMENT & INNOVATION OF MACHINERY & ELECTRICAL PRODUCTS, vol. 20, no. 4, 28 July 2007 (2007-07-28), pages 14 - 15,17, XP055969502, ISSN: 1002-6673 *

Also Published As

Publication number Publication date
CN113119114A (zh) 2021-07-16
CN113119114B (zh) 2022-10-21

Similar Documents

Publication Publication Date Title
WO2022198994A1 (zh) 一种机械臂运动规划方法、装置、可读存储介质及机械臂
CN112936301A (zh) 一种机器人手眼标定方法、装置、可读存储介质及机器人
WO2022198993A1 (zh) 一种机械臂运动规划方法、装置、可读存储介质及机械臂
US10821605B2 (en) Robot motion path planning method, apparatus and terminal device
WO2022193639A1 (zh) 机械臂及其轨迹规划方法和装置
US11833692B2 (en) Method and device for controlling arm of robot
WO2022227429A1 (zh) 一种步态轨迹规划方法、装置、可读存储介质及机器人
WO2022110451A1 (zh) 机器人定位方法、装置、计算机可读存储介质及机器人
WO2021082229A1 (zh) 数据处理方法及相关装置
US10349035B2 (en) Automatically scanning and representing an environment having a plurality of features
WO2022198992A1 (zh) 一种机械臂运动规划方法、装置、可读存储介质及机械臂
WO2023197668A1 (zh) 机器人避障控制方法和装置
CN116766172B (zh) 机械臂的路径规划方法、装置、电子设备和存储介质
CN113110423A (zh) 步态轨迹规划方法、装置、计算机可读存储介质及机器人
CN113084791A (zh) 机械臂控制方法、机械臂控制装置及终端设备
CN117901090A (zh) 一种持镜机器人视觉伺服方法及系统
CN118918365A (zh) 一种工程机械设备的姿态生成方法、装置、终端设备及存储介质
WO2022193640A1 (zh) 一种机器人标定方法、装置、机器人及存储介质
WO2024230476A1 (zh) 视觉惯性融合定位方法及设备
CN117908536A (zh) 机器人避障方法、终端设备及计算机可读存储介质
Naik et al. Robotic task success evaluation under multi-modal non-parametric object pose uncertainty
CN117707146A (zh) 一种机器人避障控制方法及相关设备
CN109416748B (zh) 基于svm的样本数据更新方法、分类系统和存储装置
CN115256372B (zh) 机械臂控制方法、装置、控制设备及存储介质
Li et al. An image-based visual servo system to operate a flexible wire

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: 21932601

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: 21932601

Country of ref document: EP

Kind code of ref document: A1