QuestSim: Human Motion Tracking from Sparse Sensors with Simulated Avatars

TL;DR

This paper introduces QuestSim, a reinforcement learning framework that enables real-time full-body human motion tracking from sparse sensor data, using simulated avatars to produce plausible and physically valid movements.

Contribution

QuestSim is the first to use sparse HMD and controller signals with reinforcement learning to generate full-body motions in real-time, demonstrating robustness across styles and environments.

Findings

Leg motions closely match ground truth despite limited data

Single policy handles diverse locomotion styles and body sizes

System works with only 6D HMD transformations as input

Abstract

Real-time tracking of human body motion is crucial for interactive and immersive experiences in AR/VR. However, very limited sensor data about the body is available from standalone wearable devices such as HMDs (Head Mounted Devices) or AR glasses. In this work, we present a reinforcement learning framework that takes in sparse signals from an HMD and two controllers, and simulates plausible and physically valid full body motions. Using high quality full body motion as dense supervision during training, a simple policy network can learn to output appropriate torques for the character to balance, walk, and jog, while closely following the input signals. Our results demonstrate surprisingly similar leg motions to ground truth without any observations of the lower body, even when the input is only the 6D transformations of the HMD. We also show that a single policy can be robust to diverse locomotion styles, different body sizes, and novel environments.