Robot control method and equipment

Abstract

The purpose of the application is to provide a robot control method and equipment. The exploration speed is dynamically adjusted by simulating an anterior cingulate cortex nerve adjustment mechanism in the brain physiological mechanism of primates, and the exploration and utilization degree is adjusted in real time according to the environment, so that the dynamic balance between the utilization environment and the exploration environment of the robot is realized, the learning convergence speed in the behavior decision process of the robot is improved, and a better global solution is obtained.

Description

technical field [0001] The present application relates to the field of computers, in particular to a robot control method and equipment. Background technique [0002] In the existing technology, the robot needs to learn and adapt to the environment in an unknown environment, and reinforcement learning is one of the key technologies. The advantage of reinforcement learning is that it does not need to give the expected output, but according to the reinforcement signal through online interactive training, the robot can obtain the maximum cumulative return when moving in the environment, so as to obtain a better control strategy. Therefore, reinforcement learning is often used in the research of robot behavior decision-making. [0003] At present, an important problem faced by reinforcement learning algorithms is the balance between environment exploration and environment utilization. The coordination state of exploration and utilization directly affects the efficiency of reinf...

AI Technical Summary

Problems solved by technology

[0007] One purpose of this application is to provide a robot control method and equipment to solve the problem of how to adjust the degree of exploration and utilization in the process of robot learning in the prior art, so as to improve the learning convergence speed and obtain a better global solution

Images