Navigation and obstacle avoidance method and system of a manipulator for live-line work in a power distribution network

Abstract

The present invention proposes a method and system for navigating and avoiding obstacles of a manipulator for live work in a power distribution network. The method obtains the state space set s of the manipulator in the actual operation scene; The strategy neural network model is used to obtain the joint rotation angle set a used to control the movement of each joint of the manipulator; if the movement of each joint of the manipulator is driven according to the angle change in the joint rotation angle set a to meet all the preset safety conditions, then to the manipulator A signal to execute the motion of each joint in the joint rotation angle set a is issued. The method and system can not only realize the autonomous navigation and obstacle avoidance of the live working manipulator under the premise of safe operation, but also improve the operation accuracy.

Description

technical field [0001] The invention relates to the technical field of live work in distribution network, in particular to a method and system for navigating and avoiding obstacles of a manipulator for live work in distribution network. Background technique [0002] In the prior art, most live working robots in the 10kV distribution network are master-slave robots. During the operation, the operator needs to stand in the raised insulating bucket and control the mechanical arm to complete the operation by operating the control lever. The positioning method is mainly For camera observation or operator visual observation. The existing operation method has the following problems: the robot body and the high-voltage line body are in direct contact with the operator, and electrical safety issues need to be considered; the master-slave operation method requires high control accuracy, and manual operation requires skilled technology as a support; in order to maintain The safe worki...

AI Technical Summary

Problems solved by technology

The existing operation method has the following problems: the robot body and the high-voltage line body are in direct contact with the operator, and electrical safety issues need to be considered; the master-slave operation method requires high control accuracy, and manual operation requires skilled technology as a support; in order to maintain The safe working distance often chooses a long-distance working path, thereby reducing working efficiency; visual observation and fixed camera shooting may easily cause obstacles to block the line of sight, and the distance information cannot be accurately grasped, resulting in dangers such as the arm touching the line

This method has the following problems when it is used in the line operation environment: the search tree method requires high-precision three-dimensional modeling, and the lines are densely distributed, which makes it difficult to model clearly, which will cause errors in subsequent random exploration and cause line collisions; the geometric size of the cables is relatively small. If the random sampling step size is too small, the existence of cable obstacles may not be felt, resulting in the planned routes obtained through exploration not meeting the electrical safety distance requirements or line collisions; the scene is required to be relatively stable during operation, and the route needs to be re-planned for changes in the scene, resulting in a large amount of calculation And it is easy to cause failure to find a suitable line

Images