2025/02/12 by Tao Huang, Junli Ren, Huang, Tao +16 · 1 voice · 40 citations
Computer Science · Engineering · Health Professions · Medicine · #Artificial Intelligence (cs.AI) #Balance, Gait, and Falls Prevention #FOS: Computer and information sciences #Machine Learning (cs.LG) #Prosthetics and Rehabilitation Robotics #Robotics (cs.RO) #Stroke Rehabilitation and Recovery #cs.AI #cs.LG #cs.RO
paper · pdf · doi:10.48550/arxiv.2502.08378
openalex publication_date 2025/02/12 · arxiv published 2025/02/12 · arxiv updated 2025/04/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Standing-up control is crucial for humanoid robots, with the potential for integration into current locomotion and loco-manipulation systems, such as fall recovery. Existing approaches are either limited to simulations that overlook hardware constraints or rely on predefined ground-specific motion trajectories, failing to enable standing up across postures in real-world scenes. To bridge this gap, we present HoST (Humanoid Standing-up Control), a reinforcement learning framework that learns standing-up control from scratch, enabling robust sim-to-real transfer across diverse postures. HoST effectively learns posture-adaptive motions by leveraging a multi-critic architecture and curriculum-based training on diverse simulated terrains. To ensure successful real-world deployment, we constrain the motion with smoothness regularization and implicit motion speed bound to alleviate oscillatory and violent motions on physical hardware, respectively. After simulation-based training, the learned control policies are directly deployed on the Unitree G1 humanoid robot. Our experimental results demonstrate that the controllers achieve smooth, stable, and robust standing-up motions across a wide range of laboratory and outdoor environments. Videos and code are available at https://taohuang13.github.io/humanoid-standingup.github.io/.