QuestSim: Human Motion Tracking from Sparse Sensors with Simulated Avatars
This addresses the challenge of immersive AR/VR experiences by enabling full-body tracking with limited wearable devices, though it is incremental as it builds on existing reinforcement learning and simulation methods.
The paper tackles the problem of real-time full-body human motion tracking from sparse sensors like HMDs and controllers, using a reinforcement learning framework to simulate plausible and physically valid motions, achieving surprisingly similar leg motions to ground truth without lower-body observations.
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.