Pose Distance Fields for Humanoid Robots
Overview
This paper presents Pose Distance Fields for Humanoid Robots (PDF-HR), a lightweight prior that encodes robot pose distributions as a continuous, differentiable manifold. By predicting the distance from an arbitrary pose to a large corpus of retargeted robot poses, PDF-HR provides a smooth measure of pose plausibility suitable for optimization and control. The method can be integrated as a reward shaping term, regularizer, or standalone scorer across diverse pipelines. Experiments on humanoid tasks including single-trajectory motion tracking, general motion tracking, style-based motion mimicry, and general motion retargeting show that PDF-HR consistently strengthens strong baselines. Code and models are publicly available.
Generated from attributed reports · Updated 38 minutes ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Artifact availability · code: available
“se 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 are publicly available at https://gaoyukang33.github.io/PDF-HR.”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalPose Distance Fields for Humanoid Robots
This paper presents Pose Distance Fields for Humanoid Robots (PDF-HR), a lightweight prior that encodes robot pose distributions as a continuous, differentiable manifold. By predicting the distance from an arbitrary pose to a large corpus of retargeted robot poses, PDF-HR provides a smooth measure of pose plausibility suitable for optimization and control. The method can be integrated as a reward shaping term, regularizer, or standalone scorer across diverse pipelines. Experiments on humanoid tasks including single-trajectory motion tracking, general motion tracking, style-based motion mimicry, and general motion retargeting show that PDF-HR consistently strengthens strong baselines. Code and models are publicly available.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).