Constrained Reinforcement Learning for Unstable Point-Feet Bipedal Locomotion Applied to the Bolt Robot
Year: 2025
Type: conference-paper
Abstract: Bipedal locomotion is a key challenge in robotics, particularly for robots like Bolt, which have a point-foot design. This study explores the control of such underactuated robots using constrained reinforcement learning, addressing their inherent instability, lack of arms, and limited foot actuation. We present a methodology that leverages Constraints-as-Terminations and domain randomization techniques to enable sim-to-real transfer. Through a series of qualitative and quantitative experiments, we evaluate our approach in terms of balance maintenance, velocity control, and responses to slip and push disturbances. Additionally, we analyze autonomy through metrics like the cost of transport and ground reaction force. Our method advances robust control strategies for point-foot bipedal robots, offering insights into broader locomotion. Videos and code are available at https://gepetto.github.io/BoltLocomotion/.
Language: English
Subfield: Biomedical Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
Awards: G1145502871, Artificial and Natural Intelligence Toulouse Institute, G3010527862, Robot motion with physical interactions and social adaptation, G3441976835, G3778207229, G3879958799, Infrastructure technologique pour la recherche d’excellence en robotique, Réseau national de plateformes robotiques d'excellence, G602161992, G693040958, G7240651115, G8510727784, G8771110305
OpenAlex ID: W4414852096