Self-Supervised Motion Retargeting with Safety Guarantee
This addresses motion retargeting for humanoid robots, offering a practical solution with safety guarantees, though it appears incremental as it builds on existing data-driven approaches.
The paper tackles the problem of generating natural motions for humanoid robots from motion capture or video data by introducing a self-supervised method that reduces the need for time-consuming paired data collection, and it guarantees collision-free and position-limited robot poses.
In this paper, we present self-supervised shared latent embedding (S3LE), a data-driven motion retargeting method that enables the generation of natural motions in humanoid robots from motion capture data or RGB videos. While it requires paired data consisting of human poses and their corresponding robot configurations, it significantly alleviates the necessity of time-consuming data-collection via novel paired data generating processes. Our self-supervised learning procedure consists of two steps: automatically generating paired data to bootstrap the motion retargeting, and learning a projection-invariant mapping to handle the different expressivity of humans and humanoid robots. Furthermore, our method guarantees that the generated robot pose is collision-free and satisfies position limits by utilizing nonparametric regression in the shared latent space. We demonstrate that our method can generate expressive robotic motions from both the CMU motion capture database and YouTube videos.