Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Universal Humanoid Motion Representations for Physics-Based Control

About

We present a universal motion representation that encompasses a comprehensive range of motor skills for physics-based humanoid control. Due to the high dimensionality of humanoids and the inherent difficulties in reinforcement learning, prior methods have focused on learning skill embeddings for a narrow range of movement styles (e.g. locomotion, game characters) from specialized motion datasets. This limited scope hampers their applicability in complex tasks. We close this gap by significantly increasing the coverage of our motion representation space. To achieve this, we first learn a motion imitator that can imitate all of human motion from a large, unstructured motion dataset. We then create our motion representation by distilling skills directly from the imitator. This is achieved by using an encoder-decoder structure with a variational information bottleneck. Additionally, we jointly learn a prior conditioned on proprioception (humanoid's own pose and velocities) to improve model expressiveness and sampling efficiency for downstream tasks. By sampling from the prior, we can generate long, stable, and diverse human motions. Using this latent space for hierarchical RL, we show that our policies solve tasks using human-like behavior. We demonstrate the effectiveness of our motion representation by solving generative tasks (e.g. strike, terrain traversal) and motion tracking using VR controllers.

Zhengyi Luo, Jinkun Cao, Josh Merel, Alexander Winkler, Jing Huang, Kris Kitani, Weipeng Xu• 2023

Related benchmarks

TaskDatasetResultRank
Humanoid SteeringIsaac Gym Steering
Success Rate0.4072
6
Humanoid DirectionIsaac Gym Direction
Success Rate97.6
6
Humanoid ReachIsaac Gym Reach
Success Rate83.96
6
Humanoid StrikeIsaac Gym Strike
Success Rate83.18
5
Humanoid Long JumpIsaac Gym Long Jump
Success Rate99.37
5
Tennis ReturnTennis Return Forehand
SR71.85
4
Tennis ReturnTennis Return Backhand
SR63.38
4
Tennis ReturnTennis Return Forecourt
SR74.52
4
Tennis ReturnTennis Return Backcourt
SR0.7294
4
Showing 9 of 9 rows

Other info

Follow for update