← Back to all news
arXiv Machine Learning

UniExo: Unified Multi-Skill Policies for Musculoskeletal Locomotion and Co-Adaptive Exoskeleton Control

UniExo is a framework that builds a single, multi-skill musculoskeletal human policy by distilling four imitation experts—walking, turning, running, and backward walking—into one network guided by a skill latent. The human policy is fine‑tuned with reinforcement learning on transition sequences, achieving a 94.7% tracking success rate on unseen clips and greater robustness to perturbations. A hip exoskeleton controller is then co‑adapted with this human policy via multi‑agent reinforcement learning, enabling it to assist across four treadmill speeds and a continuous route of all four skills without explicit mode switching.

Related stories

arXiv Machine Learning
Aug 4

Staged Multi-Agent Training (SMAT) for Hip Exoskeletons: Metabolic and Biomechanical Validation of a Simulation-Trained Co-Adaptive Controller

arXiv:2608. 00715v1 Announce Type: cross Abstract: Learning-based controllers can deliver exoskeleton assistance after training entirely in physics-based simulation, yet few controllers that address human-device co-adaptation have been validated on real users by whole-body metabolic measurement, the standard benchmark for assistive walking.

By Yifei Yuan, Jakob Wolf, Ghaith Androwis, Xianlian Zhou
agentsbenchmarks
More like this →
arXiv Machine Learning
Jun 5

OLIVE: Online Low-Rank Incremental Learning for Efficient Adaptive Exoskeletons

arXiv:2606. 05234v1 Announce Type: cross Abstract: Wearable exoskeleton systems hold promise for restoring mobility in individuals with physical impairments, yet most existing controllers rely on static gait policies that lack the ability to adapt to dynamic real-world environments or individual user characteristics.

By Dong Liu, Yanxuan Yu, Ben Lengerich, Tony Geng, Ying Nian Wu
reinforcement-learning
More like this →
arXiv Machine Learning
Aug 19

Lambda-Hold Control: Human-Like Movement Emerges from a Minimal Task Reward in Predictive Musculoskeletal Simulation

The paper introduces the λ-hold controller, a minimal-task-reward approach inspired by the equilibrium-point hypothesis, to train a muscle-actuated skeletal model for human-like sprinting. By fixing each muscle’s EP threshold length λ over gait-phase intervals, the controller dramatically reduces the action space and the frequency of policy queries, enabling efficient exploration and learning within an hour of training. This method demonstrates that physiologically grounded control can produce realistic human motion in predictive musculoskeletal simulations.

By Jun Hyuk Lee, Chihyeong Lee, Jooeun Ahn
reinforcement-learning
More like this →
arXiv Machine Learning
Jul 28

Learning Reusable Hybrid Motion Priors for Humanoid Locomotion from Motion Imitation

arXiv:2607. 24083v1 Announce Type: new Abstract: Reinforcement learning can produce robust humanoid controllers, but each new task is typically trained as a separate policy with its own reward design and training process.

By Valerio Belli (UNIROMA, UCL), Valerio Modugno (UCL), Enrico Mingo Hoffman (HUCEBOT), Fabio Amadio (HUCEBOT)
reinforcement-learningroboticsefficiency
More like this →
arXiv Machine Learning
Sep 11

Reflex-Informed Neuromuscular Reinforcement Learning for Muscle-Driven Locomotion

The paper introduces a Reflex-Informed Neuromuscular Reinforcement Learning framework for muscle-driven locomotion. It combines a fixed phase-dependent reflex controller with a reinforcement learning policy that adjusts reflex gains and thresholds for hip swing, knee support, and ankle propulsion. Experiments show the method produces physiologically plausible walking with improved kinematic accuracy, dynamic consistency, symmetry, and stride consistency, and remains robust to muscle weakness and perturbations without retraining.

By Jian Zhou, Xingyu Zhang, Rui Ma, Yu Cao, Shane Xie, Zhi-qiang Zhang
reinforcement-learningrobotics
More like this →
arXiv Machine Learning
Sep 21

Beyond Kinematics: Benchmarking Simulation Fidelity for Muscle-Driven Imitation Learning

The paper compares two leading motion‑imitation reinforcement learning pipelines—HyFyDy, which uses detailed musculotendon modeling, and MuJoCo, which focuses on computational speed. Using the same human motion‑capture and EMG data, both pipelines reproduce kinematics similarly, but HyFyDy’s muscle activation predictions align more closely with experimental EMG (RMSE 0.164, r = 0.4) than MuJoCo’s (RMSE 0.344, r = 0.11). The authors conclude that HyFyDy’s higher physiological realism makes it currently more suitable for musculoskeletal modeling, though both systems need further development for GPU‑parallelizable environments and robotic assistive‑device design.

By Ayah G. Ahmad, Claire E. Borden, Maegan Tucker
reinforcement-learningroboticsbenchmarks
More like this →
arXiv Computer Vision
Sep 18

OmniMimic: Dynamics-completed Motion Augmentation for Multi-style Omnidirectional Quadruped Locomotion

OmniMimic is a training framework that expands limited animal demonstration data into a single multi‑gait policy for omnidirectional quadruped locomotion. It uses temporal reversal, constrained dynamics completion, and sagittal reflection to generate kinematic and physical supervision beyond the observed directions, then progressively expands command ranges and employs a shared actor with soft‑gated gait‑specialized residual experts. In simulation, OmniMimic improves foot‑position accuracy by 12.9% and velocity‑tracking error by 63.1% over the APEX baseline across four gaits.

By Sheng Wu, Guoqiang Zhao, Zhe Yang, Fei Teng, Zhikun Zhou, Yanlin Yang, Zheng Fang, Hong Zheng, Yaonan Wang, Kailun Yang
robotics
More like this →