Redundant robot repetitive motion planning method adopting parabolic final state neural network

Abstract

The invention discloses a redundant robot repetitive motion planning method adopting a parabolic final state neural network. The redundant robot repetitive motion planning method adopting the parabolic final state neural network comprises the following steps: giving an expected trajectory rd(t) of a robot end-actuator in cartesian space, and giving expected folding angles theta d (0) of each joint; and taking the parabolic final state neural network as a solver for repetitive motion of a robot by converting a quadratic optimizing problem about redundant robot trajectory planning into a time-varying matrix equation solving problem by adopting an asymptotically convergent performance index. In the situation of initial position offset, a repetitive motion planning task with finite time convergence of the redundant robot is realized. The invention provides the redundant robot repetitive motion planning method adopting the parabolic final state neural network, which has the finite time convergence, high computing accuracy and easiness in implementation.

Description

technical field [0001] The invention relates to a repetitive motion planning technology for industrial robots. Specifically, it proposes a redundant robot repetitive motion planning method using a parabolic final state neural network that converges in a limited time and the initial position deviates from the expected trajectory. Background technique [0002] Redundant robots have good flexibility and fault tolerance. It can use the extra degrees of freedom to enhance obstacle avoidance without affecting the operation of the end effector, and can complete variable tasks in complex working environments. At present, redundant robots have played an important role in many application fields, such as manufacturing, medical equipment, logistics and transportation, military defense, etc. [0003] The number of joints n of the redundant robot is greater than the degree of freedom m required by the end effector to perform the expected task, which makes the redundant robot have greater...

AI Technical Summary

Problems solved by technology

[0025] In order to overcome the shortcomings of the existing redundant robot repetitive motion planning method that cannot converge in a limited time, the calculation accuracy is low, and it is not easy to implement, the present invention provides a parabolic final state that has a limited time convergence, high calculation accuracy, and is easy to implement. Redundant robot motion planning method based on neural network

Images