PDF-HR: Pose Distance Fields for Humanoid Robots
This addresses the problem of limited motion priors for humanoid robots, enabling better optimization and control, though it is incremental as it adapts existing human motion recovery concepts to robotics.
The paper tackles the scarcity of high-quality humanoid motion data by introducing PDF-HR, a lightweight prior that represents robot pose distributions as a continuous manifold, and shows it consistently strengthens baselines in tasks like motion tracking and retargeting.
Pose and motion priors play a crucial role in humanoid robotics. Although such priors have been widely studied in human motion recovery (HMR) domain with a range of models, their adoption for humanoid robots remains limited, largely due to the scarcity of high-quality humanoid motion data. In this work, we introduce Pose Distance Fields for Humanoid Robots (PDF-HR), a lightweight prior that represents the robot pose distribution as a continuous and differentiable manifold. Given an arbitrary pose, PDF-HR predicts its distance to a large corpus of retargeted robot poses, yielding a smooth measure of pose plausibility that is well suited for optimization and control. PDF-HR can be integrated as a reward shaping term, a regularizer, or a standalone plausibility scorer across diverse pipelines. We evaluate PDF-HR on various humanoid tasks, including single-trajectory motion tracking, general motion tracking, style-based motion mimicry, and general motion retargeting. Experiments show that this plug-and-play prior consistently and substantially strengthens strong baselines. Code and models will be released.