Make Bipedal Robots Learn How to Imitate

TL;DR

This paper introduces a novel imitation learning method for bipedal robots using a single video of an instructor, leveraging joint angle data and deep reinforcement learning to enable robots to mimic human movements efficiently.

Contribution

First to train bipedal robots to imitate movements from a single video using joint angles and deep Q networks, ensuring physical joint limits and faster training.

Findings

Robot successfully mimics instructor movements.

Joint angle data smoothing improves learning accuracy.

Method is publicly available for further research.

Abstract

Bipedal robots do not perform well as humans since they do not learn to walk like we do. In this paper we propose a method to train a bipedal robot to perform some basic movements with the help of imitation learning (IL) in which an instructor will perform the movement and the robot will try to mimic the instructor movement. To the best of our knowledge, this is the first time we train the robot to perform movements with a single video of the instructor and as the training is done based on joint angles the robot will keep its joint angles always in physical limits which in return help in faster training. The joints of the robot are identified by OpenPose architecture and then joint angle data is extracted with the help of angle between three points resulting in a noisy solution. We smooth the data using Savitzky-Golay filter and preserve the Simulatore data anatomy. An ingeniously written Deep Q Network (DQN) is trained with experience replay to make the robot learn to perform the movements as similar as the instructor. The implementation of the paper is made publicly available.