analiza aiqbench
This research presents a novel framework for humanoid robotics that successfully bridges the gap between mechanical command tracking and natural human-like motion using reinforcement learning. By distilling complex policies into lightweight models conditioned on proprioception, the approach enables robust, real-time locomotion across diverse robots like the Atlas and Unitree G1 without relying solely on pre-existing human motion data distributions. The work advances embodied AI by demonstrating how to generalize biomimetic gaits while maintaining control flexibility in unstructured environments.
HuMBLE: Human Motion-Driven Behavior Learning for Embodied Locomotion
arXiv:2610.10489v1 Announce Type: new Abstract: Despite recent advances in humanoid locomotion, controllers optimized for command tracking and robustness tend to produce mechanical gaits, whereas controllers tied to human motion data often fail to generalize to commands outside the data distribution. This work introduces a learning framework that balances these competing objectives to synthesize real-time steerable, robust, and biomimetic locomotion policies from human data. Using an in-house curated locomotion dataset covering diverse speeds and directions, we first learn a natural locomotion prior policy through a teacher-student distillation process. Specifically, we train a full-body reference-conditioned policy with Reinforcement Learning (RL), then distill it into a lightweight prior policy conditioned solely on proprioception and a planar torso-velocity steering command. Next, we fine-tune the prior policy with multi-task RL to expand command coverage and robustness beyond the data distribution, pairing a goal-conditioned task that tracks arbitrary commands with a reference-guided task that tracks the human data as an explicit style regularizer. We validate our framework on three humanoid robots: the Boston Dynamics Atlas R1, Atlas D1, and Unitree G1. Experimental results demonstrate robust performance across real-world scenarios, including direct user-controlled locomotion in indoor and outdoor environments, and integration as the locomotion layer within hierarchical control stacks. Benchmarks against Tabula Rasa RL policies trained without human data and ablation studies confirm that our framework yields a lightweight, deployable policy that reconstructs coordinated whole-body behavior from a steering command, retaining the human gait characteristics while remaining robust and fully steerable.
Authors:Mike Zhang, Dongho Kang, Kevin Bergamin, Nicola Burger, Robin Deits, Jonathan Foster, Bilal Hammoud, Katie Hughes, Francesco Iacobelli, Twan Koolen, M. Eva Mungai, Zach Nobles, Shane Rozen-Levy, Jean Pierre Sleiman, Fangzhou Yu, Yunbo Zhang, Alfred Rizzi, Jessica Hodgins, Scott Kuindersma, Yeuhi Abe, Sylvain Bertrand, Farbod Farshidian
Abstract:Despite recent advances in humanoid locomotion, controllers optimized for command tracking and robustness tend to produce mechanical gaits, whereas controllers tied to human motion data often fail to generalize to commands outside the data distribution. This work introduces a learning framework that balances these competing objectives to synthesize real-time steerable, robust, and biomimetic locomotion policies from human data. Using an in-house curated locomotion dataset covering diverse speeds and directions, we first learn a natural locomotion prior policy through a teacher-student distillation process. Specifically, we train a full-body reference-conditioned policy with Reinforcement Learning (RL), then distill it into a lightweight prior policy conditioned solely on proprioception and a planar torso-velocity steering command. Next, we fine-tune the prior policy with multi-task RL to expand command coverage and robustness beyond the data distribution, pairing a goal-conditioned task that tracks arbitrary commands with a reference-guided task that tracks the human data as an explicit style regularizer. We validate our framework on three humanoid robots: the Boston Dynamics Atlas R1, Atlas D1, and Unitree G1. Experimental results demonstrate robust performance across real-world scenarios, including direct user-controlled locomotion in indoor and outdoor environments, and integration as the locomotion layer within hierarchical control stacks. Benchmarks against Tabula Rasa RL policies trained without human data and ablation studies confirm that our framework yields a lightweight, deployable policy that reconstructs coordinated whole-body behavior from a steering command, retaining the human gait characteristics while remaining robust and fully steerable.
Robotics (cs.RO)
arXiv:2610.10489 [cs.RO]
(or arXiv:2610.10489v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.10489 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 302 cuvinte
Subiecte conexe
How to Train a Cross-Embodiment Robot Navigation Policy with AI Agents
NVIDIA · 26 aug. 2026
BRIDGE: An Open-Source Humanoid Platform via Morphology-Control Co-Design for Physical AI
arXiv · 5 sept. 2026
Building a Foundation Stack for General-Purpose Robots
IEEE Spectrum · 13 iul. 2026
Learning Vision-Driven Reactive Soccer Skills for Humanoid Robots
arXiv · 21 aug. 2026