Modelling Human Kinetics and Kinematics during Walking using Reinforcement Learning

TL;DR

This paper introduces a deep reinforcement learning-based method to generate realistic 3D human walking motions in simulation, matching real-world biomechanics and generalizing across different subjects.

Contribution

It presents a novel approach combining policy learning and parameter identification to replicate human gait dynamics in virtual agents.

Findings

Generated motions closely match real human kinematics and kinetics.

Method generalizes well across subjects with different gait characteristics.

Robustness to environmental variations demonstrated.

Abstract

In this work, we develop an automated method to generate 3D human walking motion in simulation which is comparable to real-world human motion. At the core, our work leverages the ability of deep reinforcement learning methods to learn high-dimensional motor skills while being robust to variations in the environment dynamics. Our approach iterates between policy learning and parameter identification to match the real-world bio-mechanical human data. We present a thorough evaluation of the kinematics, kinetics and ground reaction forces generated by our learned virtual human agent. We also show that the method generalizes well across human-subjects with different kinematic structure and gait-characteristics.