CN-122008239-A - Robot movement control method and system for intelligent inspection

CN122008239ACN 122008239 ACN122008239 ACN 122008239ACN-122008239-A

Abstract

The application discloses a robot movement control method and system for intelligent inspection, and belongs to the technical field of computers. The technical scheme provided by the embodiment of the application solves the problems of limited perception dimension, insufficient dynamic coupling effect compensation and poor dynamic strategy adjustment capability of the traditional inspection robot in a complex unstructured environment, and enables the robot to maintain the track tracking precision of the movable base and the tail end operation stability of the mechanical arm under severe working conditions such as steep slopes, muddy and the like through the construction of holographic state characteristics and the parameter self-adaptive configuration of the virtual model, thereby completing the inspection operation with high self-adaptability.

Inventors

Nie Mingzhe
SUN YUHANG
MAO HONGLIANG
WANG ZHE
LIU JIANPENG
LUO XIANQI

Assignees

中国中铁股份有限公司
中铁资源集团有限公司
伊春鹿鸣矿业有限公司

Dates

Publication Date: 20260512
Application Date: 20260401

Claims (10)

1. A robot movement control method for intelligent inspection, the method comprising: fusing the environment multidimensional sensing information, the body dynamic state information and the task control instruction stream of the robot to generate the holographic running state characteristics of the robot; Based on the holographic running state characteristics and the task control instruction stream, carrying out collaborative strategy planning on the mobile base and the mechanical arm through a self-adaptive collaborative decision mechanism to obtain a global collaborative control strategy and a virtual dynamics model reconstruction instruction; based on the global cooperative control strategy and the virtual dynamics model reconstruction instruction, performing virtual dynamics model parameter online configuration on a bottom control loop of the robot to obtain a task-adaptive virtual compliance dynamics model; and carrying out integrated cooperative motion control on the moving base and the mechanical arm of the robot based on the task self-adaptive virtual compliance dynamic model and the global cooperative control strategy so as to finish inspection operation.
2. The method according to claim 1, wherein the fusing the environmental multidimensional sensing information, the body dynamic state information and the task control instruction stream of the robot to generate the robot holographic running state feature comprises: Carrying out multi-source feature extraction on the environmental multi-dimensional perception information to obtain environmental topographic geometric features, environmental semantic features and non-visual environmental features; performing time-frequency domain feature analysis on the body dynamic state information to obtain dynamic features and mechanical vibration spectrum features of a motor driving system of the robot; And carrying out multi-mode feature fusion and time alignment processing on the task control instruction stream, the environmental topographic geometric feature, the environmental semantic feature, the non-visual environmental feature, the dynamic feature of the motor drive system and the mechanical vibration spectrum feature to obtain the robot holographic running state feature.
3. The method according to claim 1, wherein the performing collaborative strategy planning of the mobile base and the mechanical arm by the adaptive collaborative decision mechanism based on the holographic running state feature and the task control instruction stream to obtain a global collaborative control strategy and a virtual dynamics model reconstruction instruction includes: Based on the holographic running state characteristics, determining behavior situation space description of the robot, and calculating situation deviation degree of a current state point and an expected state area of the robot in the behavior situation space description; Based on the situation deviation degree and the task control instruction stream, configuring a multi-objective optimization function of a dynamic weight coefficient, and carrying out parallel optimization solving on a plurality of candidate strategy schemes through the multi-objective optimization function to generate a plurality of collaborative strategy candidate schemes, wherein each collaborative strategy candidate scheme comprises a candidate control strategy and a candidate model reconstruction parameter; And selecting an optimal cooperative strategy candidate scheme from the multiple cooperative strategy candidate schemes based on the evaluation result, and extracting the global cooperative control strategy and the virtual dynamics model reconstruction instruction from the optimal cooperative strategy candidate scheme.
4. The method of claim 3, wherein the determining a behavioral situation space description of the robot based on the holographic operational state characteristics comprises: carrying out dimension abstraction processing on the multi-mode perception features in the holographic running state features to obtain a plurality of abstract behavior dimension definitions of a behavior situation space; Determining real-time state quantization values of the abstract behavior dimensions based on dynamic state features in the holographic running state features; and determining the behavior situation space description of the robot based on the abstract behavior dimension definition and the real-time state quantification value of each abstract behavior dimension.
5. A method according to claim 3, wherein said configuring a multi-objective optimization function of dynamic weight coefficients based on said attitude deviation and said task control instruction stream comprises: Determining a plurality of optimization targets and corresponding relative priority relationships respectively based on task stage characteristics in the task control instruction stream; Determining the dynamic weight coefficient of each optimization target based on the magnitude and the direction of the situation deviation; and constructing an objective function comprising a plurality of weighted optimization objective items based on the plurality of optimization objectives, the relative priority relation and the dynamic weight coefficient of each optimization objective.
6. The method of claim 3, wherein the parallel optimization solving of the plurality of candidate strategy solutions by the multi-objective optimization function generates a plurality of collaborative strategy candidate solutions, comprising: Generating an initial strategy population comprising combinations of motion trajectories of different mobile bases and joint trajectories of the mechanical arm; Carrying out parallel fitness evaluation on each strategy scheme in the initial strategy population by utilizing the multi-objective optimization function to obtain a comprehensive fitness value of each strategy scheme under the multi-objective optimization function; Based on the comprehensive fitness value, iteratively updating the initial strategy population through elite retention strategy and population evolution operation, and outputting a collaborative strategy candidate scheme set comprising a plurality of non-dominant solutions, wherein each non-dominant solution corresponds to a collaborative strategy candidate scheme which achieves pareto optimal among a plurality of optimization targets.
7. The method of claim 1, wherein the performing on-line configuration of virtual dynamics model parameters on the bottom control loop of the robot based on the global cooperative control strategy and the virtual dynamics model reconstruction instruction to obtain a task-adaptive virtual compliance dynamics model comprises: Analyzing the virtual dynamics model reconstruction instruction to obtain a plurality of dynamic stiffness parameters and a plurality of variable damping parameters aiming at interaction of the mobile base and the mechanical arm; integrating the dynamic stiffness parameters and the variable damping parameters into a unified virtual compliance dynamics model framework based on a collaborative mode instruction in the global collaborative control strategy; And on-line adjustment and optimization are carried out on parameters in the virtual compliance dynamics model frame based on the real-time motion state of the robot, so that the task-adaptive virtual compliance dynamics model is obtained.
8. The method of claim 7, wherein the parsing the virtual dynamics model reconstruction command to obtain a plurality of dynamic stiffness parameters and a plurality of variable damping parameters for mobile base-to-robotic arm interactions comprises: Extracting parameter configuration information from the virtual dynamics model reconstruction instruction, and identifying rigidity parameter characteristics and damping parameter characteristics contained in the parameter configuration information; mapping the stiffness parameter characteristics into dynamic stiffness parameters of multiple directions based on the cooperative mode requirements in the global cooperative control strategy, and mapping the damping parameter characteristics into variable damping parameters of multiple directions; and carrying out normalization processing and parameter range constraint on the dynamic stiffness parameters and the variable damping parameters based on the real-time interaction state of the robot to obtain the plurality of dynamic stiffness parameters and the plurality of variable damping parameters which meet the current interaction requirement.
9. The method of claim 1, wherein the performing integrated cooperative motion control of the mobile base and the robotic arm of the robot based on the task-adaptive virtual compliance dynamics model and the global cooperative control strategy comprises: acquiring cooperative control parameters from the task self-adaptive virtual compliance dynamic model, wherein the cooperative control parameters comprise dynamic stiffness parameters and variable damping parameters; Generating a track tracking control instruction of the mobile base and an impedance control instruction of the mechanical arm based on the global cooperative control strategy, the dynamic stiffness parameter and the variable damping parameter; and respectively distributing the track tracking control instruction and the impedance control instruction to a mobile base control unit and a mechanical arm control unit to realize integrated cooperative motion control of the mobile base and the mechanical arm.
10. A robotic movement control system for intelligent inspection, the system comprising: The fusion processing module is used for carrying out fusion processing on the environment multidimensional sensing information, the body dynamic state information and the task control instruction stream of the robot to generate the holographic running state characteristics of the robot; The strategy planning module is used for carrying out collaborative strategy planning on the mobile base and the mechanical arm through a self-adaptive collaborative decision mechanism based on the holographic running state characteristics and the task control instruction stream to obtain a global collaborative control strategy and a virtual dynamics model reconstruction instruction; The on-line configuration module is used for carrying out on-line configuration on virtual dynamics model parameters on a bottom control loop of the robot based on the global cooperative control strategy and the virtual dynamics model reconstruction instruction to obtain a task self-adaptive virtual compliance dynamics model; and the control module is used for carrying out integrated cooperative motion control on the moving base and the mechanical arm of the robot based on the task self-adaptive virtual compliance dynamic model and the global cooperative control strategy so as to finish the inspection operation.

Description

Robot movement control method and system for intelligent inspection Technical Field The application relates to the technical field of computers, in particular to a robot movement control method and system for intelligent inspection. Background In a complex unstructured environment in the heavy industrial fields such as metal ore mining and selecting, the intelligent inspection robot needs to synchronously operate the mechanical arm in the moving process to finish fine operations such as equipment detection, pipeline inspection and the like. The environment usually has complex terrains such as steep slopes, mud and the like, and meanwhile, the environment is accompanied by strong vibration, temperature and humidity rapid change, specific chemical substances and other interference factors, so that extremely high requirements are put on the collaborative operation capability of the robot. Therefore, in an industrial inspection environment with complex terrains and severe working conditions, how to break through the bottleneck of multi-source information fusion and realize high-precision and high-self-adaptive cooperative control of a mobile base and a mechanical arm becomes a key difficulty for restricting the technical development of the industry. Disclosure of Invention The embodiment of the application provides a robot movement control method and a system for intelligent inspection, which can realize high-precision and high-self-adaption cooperative control of a mobile base and a mechanical arm, and the technical scheme is as follows: in one aspect, a method for controlling movement of a robot for intelligent inspection is provided, the method comprising: fusing the environment multidimensional sensing information, the body dynamic state information and the task control instruction stream of the robot to generate the holographic running state characteristics of the robot; Based on the holographic running state characteristics and the task control instruction stream, carrying out collaborative strategy planning on the mobile base and the mechanical arm through a self-adaptive collaborative decision mechanism to obtain a global collaborative control strategy and a virtual dynamics model reconstruction instruction; based on the global cooperative control strategy and the virtual dynamics model reconstruction instruction, performing virtual dynamics model parameter online configuration on a bottom control loop of the robot to obtain a task-adaptive virtual compliance dynamics model; and carrying out integrated cooperative motion control on the moving base and the mechanical arm of the robot based on the task self-adaptive virtual compliance dynamic model and the global cooperative control strategy so as to finish inspection operation. In one aspect, a robot movement control system for intelligent inspection is provided, the system comprising: The fusion processing module is used for carrying out fusion processing on the environment multidimensional sensing information, the body dynamic state information and the task control instruction stream of the robot to generate the holographic running state characteristics of the robot; The strategy planning module is used for carrying out collaborative strategy planning on the mobile base and the mechanical arm through a self-adaptive collaborative decision mechanism based on the holographic running state characteristics and the task control instruction stream to obtain a global collaborative control strategy and a virtual dynamics model reconstruction instruction; The on-line configuration module is used for carrying out on-line configuration on virtual dynamics model parameters on a bottom control loop of the robot based on the global cooperative control strategy and the virtual dynamics model reconstruction instruction to obtain a task self-adaptive virtual compliance dynamics model; and the control module is used for carrying out integrated cooperative motion control on the moving base and the mechanical arm of the robot based on the task self-adaptive virtual compliance dynamic model and the global cooperative control strategy so as to finish the inspection operation. Drawings In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Fig. 1 is a schematic diagram of an implementation environment of a robot movement control method for intelligent patrol according to an embodiment of the present application; Fig. 2 is a flowchart of a robot movement control method for intelligent patrol according to an embodiment of the present application; FIG. 3 is a partial flow chart of a robot movement