RL from Physical Feedback: Aligning Large Motion Models with Humanoid Control

• URL: http://arxiv.org/abs/2506.12769v1
• Date: Sun, 15 Jun 2025 08:39:49 GMT
• Title: RL from Physical Feedback: Aligning Large Motion Models with Humanoid Control
• Authors: Junpeng Yue, Zepeng Wang, Yuxuan Wang, Weishuai Zeng, Jiangxing Wang, Xinrun Xu, Yu Zhang, Sipeng Zheng, Ziluo Ding, Zongqing Lu,
• Abstract summary: This paper focuses on translating text-driven human motions into executable actions for humanoid robots.<n>Existing text-to-motion generation methods produce kinematically or physically infeasible motions unsuitable for real-world deployment.<n>We propose Reinforcement Learning from Physical Feedback, a novel framework that integrates physics-aware motion evaluation with text-conditioned motion generation.
• Score: 32.37239524019001
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper focuses on a critical challenge in robotics: translating text-driven human motions into executable actions for humanoid robots, enabling efficient and cost-effective learning of new behaviors. While existing text-to-motion generation methods achieve semantic alignment between language and motion, they often produce kinematically or physically infeasible motions unsuitable for real-world deployment. To bridge this sim-to-real gap, we propose Reinforcement Learning from Physical Feedback (RLPF), a novel framework that integrates physics-aware motion evaluation with text-conditioned motion generation. RLPF employs a motion tracking policy to assess feasibility in a physics simulator, generating rewards for fine-tuning the motion generator. Furthermore, RLPF introduces an alignment verification module to preserve semantic fidelity to text instructions. This joint optimization ensures both physical plausibility and instruction alignment. Extensive experiments show that RLPF greatly outperforms baseline methods in generating physically feasible motions while maintaining semantic correspondence with text instruction, enabling successful deployment on real humanoid robots.

Related papers

• Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis [51.95817740348585]
  Human-X is a novel framework designed to enable immersive and physically plausible human interactions across diverse entities.<n>Our method jointly predicts actions and reactions in real-time using an auto-regressive reaction diffusion planner.<n>Our framework is validated in real-world applications, including virtual reality interface for human-robot interaction.
  arXiv  Detail & Related papers  (2025-08-04T06:35:48Z)
• KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills [50.34487144149439]
  This paper presents a physics-based humanoid control framework, aiming to master highly-dynamic human behaviors such as Kungfu and dancing.<n>For motion processing, we design a pipeline to extract, filter out, correct, and retarget motions, while ensuring compliance with physical constraints.<n>For motion imitation, we formulate a bi-level optimization problem to dynamically adjust the tracking accuracy tolerance.<n>In experiments, we train whole-body control policies to imitate a set of highly-dynamic motions.
  arXiv  Detail & Related papers  (2025-06-15T13:58:53Z)
• PhysiInter: Integrating Physical Mapping for High-Fidelity Human Interaction Generation [35.563978243352764]
  We introduce physical mapping, integrated throughout the human interaction generation pipeline.<n>Specifically, motion imitation within a physics-based simulation environment is used to project target motions into a physically valid space.<n>Experiments show our method achieves impressive results in generated human motion quality, with a 3%-89% improvement in physical fidelity.
  arXiv  Detail & Related papers  (2025-06-09T06:04:49Z)
• FlexMotion: Lightweight, Physics-Aware, and Controllable Human Motion Generation [12.60677181866807]
  We propose a novel framework that leverages a computationally lightweight diffusion model operating in the latent space.<n> FlexMotion employs a multimodal pre-trained Transformer encoder-decoder, integrating joint locations, contact forces, joint actuations and muscle activations.<n>We evaluate FlexMotion on extended datasets and demonstrate its superior performance in terms of realism, physical plausibility, and controllability.
  arXiv  Detail & Related papers  (2025-01-28T08:02:21Z)
• Morph: A Motion-free Physics Optimization Framework for Human Motion Generation [25.51726849102517]
  Our framework achieves state-of-the-art motion generation quality while improving physical plausibility drastically.<n>Experiments on text-to-motion and music-to-dance generation tasks demonstrate that our framework achieves state-of-the-art motion generation quality.
  arXiv  Detail & Related papers  (2024-11-22T14:09:56Z)
• ReinDiffuse: Crafting Physically Plausible Motions with Reinforced Diffusion Model [9.525806425270428]
  We present emphReinDiffuse that combines reinforcement learning with motion diffusion model to generate physically credible human motions. Our method adapts Motion Diffusion Model to output a parameterized distribution of actions, making them compatible with reinforcement learning paradigms. Our approach outperforms existing state-of-the-art models on two major datasets, HumanML3D and KIT-ML.
  arXiv  Detail & Related papers  (2024-10-09T16:24:11Z)
• Learning Generalizable Human Motion Generator with Reinforcement Learning [95.62084727984808]
  Text-driven human motion generation is one of the vital tasks in computer-aided content creation. Existing methods often overfit specific motion expressions in the training data, hindering their ability to generalize. We present textbfInstructMotion, which incorporate the trail and error paradigm in reinforcement learning for generalizable human motion generation.
  arXiv  Detail & Related papers  (2024-05-24T13:29:12Z)
• I-CTRL: Imitation to Control Humanoid Robots Through Constrained Reinforcement Learning [8.97654258232601]
  We develop a framework to control humanoid robots through bounded residual reinforcement learning (I-CTRL)<n>I-CTRL excels in motion imitation with simple and unique rewards that generalize across five robots.<n>Our framework introduces an automatic priority scheduler to manage large-scale motion datasets.
  arXiv  Detail & Related papers  (2024-05-14T16:12:27Z)
• TLControl: Trajectory and Language Control for Human Motion Synthesis [68.09806223962323]
  We present TLControl, a novel method for realistic human motion synthesis. It incorporates both low-level Trajectory and high-level Language semantics controls. It is practical for interactive and high-quality animation generation.
  arXiv  Detail & Related papers  (2023-11-28T18:54:16Z)
• TEMOS: Generating diverse human motions from textual descriptions [53.85978336198444]
  We address the problem of generating diverse 3D human motions from textual descriptions. We propose TEMOS, a text-conditioned generative model leveraging variational autoencoder (VAE) training with human motion data. We show that TEMOS framework can produce both skeleton-based animations as in prior work, as well more expressive SMPL body motions.
  arXiv  Detail & Related papers  (2022-04-25T14:53:06Z)
• Nonprehensile Riemannian Motion Predictive Control [57.295751294224765]
  We introduce a novel Real-to-Sim reward analysis technique to reliably imagine and predict the outcome of taking possible actions for a real robotic platform. We produce a closed-loop controller to reactively push objects in a continuous action space. We observe that RMPC is robust in cluttered as well as occluded environments and outperforms the baselines.
  arXiv  Detail & Related papers  (2021-11-15T18:50:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.