PPMC RL Training Algorithm: Rough Terrain Intelligent Robots through Reinforcement Learning

TL;DR

This paper introduces a novel reinforcement learning-based training algorithm, PPMC, enabling robots to effectively navigate and generalize in rough, uneven terrains, demonstrated on different robot structures with high success rates.

Contribution

The paper presents the first generic training algorithm for PPMC in rough environments applicable to any robot structure using reinforcement learning.

Findings

Successfully applied to wheeled and quadruped robots

Achieved 100% success rate in generalizing to new rough terrains

Demonstrated effectiveness in highly uneven terrains

Abstract

Robots can now learn how to make decisions and control themselves, generalizing learned behaviors to unseen scenarios. In particular, AI powered robots show promise in rough environments like the lunar surface, due to the environmental uncertainties. We address this critical generalization aspect for robot locomotion in rough terrain through a training algorithm we have created called the Path Planning and Motion Control (PPMC) Training Algorithm. This algorithm is coupled with any generic reinforcement learning algorithm to teach robots how to respond to user commands and to travel to designated locations on a single neural network. In this paper, we show that the algorithm works independent of the robot structure, demonstrating that it works on a wheeled rover in addition the past results on a quadruped walking robot. Further, we take several big steps towards real world practicality by introducing a rough highly uneven terrain. Critically, we show through experiments that the robot learns to generalize to new rough terrain maps, retaining a 100% success rate. To the best of our knowledge, this is the first paper to introduce a generic training algorithm teaching generalized PPMC in rough environments to any robot, with just the use of reinforcement learning.