Heterogeneous modular robot self-reconfiguration planning method based on enhanced learning algorithm

Abstract

The invention relates to a heterogeneous modular robot self-reconfiguration planning method based on an enhanced learning algorithm. Firstly, an initial modular robot configuration and a target configuration are given, the total number N of modules is input, and a graph structure of the modules is established through an initialization process; and the initial configuration is taken as a root node,a Monte Carlo tree search is established, and the search is stopped when a termination condition (the target configuration is found or the n-time exploration has been performed) is met. After each search is finished, a planning path is given, and a sample is stored; when the number of the samples reaches a given value, the samples are input into a neural network for training, and training parameters are updated; and after the parameters are updated, the Monte Carlo search is carried out again. The average number of steps of a search result should be smaller, and the planning path with the minimum number of steps is updated after each search is completed.

Description

technical field [0001] The invention belongs to the field of artificial intelligence planning, and in particular relates to the application of a reinforcement learning algorithm to optimize the planning of a modular robot in the process of autonomous deformation. Background technique [0002] With the wide application of robots in various fields, more and more robots are used in unstructured environments to complete tasks. For unknown working environments and different tasks, robots need to adapt to the environment by changing their configuration. Requirements, this kind of robot that can dynamically and autonomously change its configuration to meet the needs of the task is called a self-reconfigurable modular robot. Self-reconfigurable modular robots are composed of a series of unit modules with simple structures and different functions. In order to achieve better task performance and environmental adaptability, when the multi-module system is running, each module unit ind...

AI Technical Summary

Problems solved by technology

For robots with complex configurations and many modules, in order to ensure the solvability from the initial configuration to the target configuration, the existing algorithm will introduce an intermediate configuration as a transition, which will lead to too many modules moving and inefficiency

Images