PDF-HR: Pose Distance Fields for Humanoid Robots

2026-02-04

AI Summary

This work addresses the challenge of leveraging pose priors in humanoid robotics due to the scarcity of high-quality motion data. To this end, it introduces, for the first time, a lightweight and continuously differentiable Pose Distance Field (PDF) that learns the distribution of a large-scale retargeted pose corpus to provide a smooth, differentiable measure of pose plausibility for any given configuration. Notably, the method operates without requiring real robot data and is plug-and-play compatible, enabling its flexible integration—as a reward shaping term, regularization component, or standalone evaluator—into diverse motion control frameworks. Experiments demonstrate that the proposed approach significantly outperforms existing baselines across multiple tasks, including single-trajectory tracking, general motion imitation, style transfer, and motion retargeting.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Computer Vision: Biometrics, Face, Gesture & Pose

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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.

Problem

• humanoid robots
• pose priors
• motion data scarcity
• motion plausibility
• human motion recovery

Innovation

• Pose Distance Fields
• Humanoid Robots
• Motion Priors
• Differentiable Manifold
• Pose Plausibility