Anticipatory and Adaptive Footstep Streaming for Teleoperated Bipedal Robots
2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids), 2025
Recommended citation: Penco, L., Park, B., Fasano, S., Poddar, N., McCrory, S., Kitchel, N., Bialek, T., Anderson, D., Calvert, D., & Griffin, R. (2025). Anticipatory and Adaptive Footstep Streaming for Teleoperated Bipedal Robots. IEEE-RAS Humanoids 2025. https://arxiv.org/abs/2508.11802
TL;DR: Footstep retargeting + step anticipation for teleoperated bipedal robots. Instead of copying operator foot poses, the system predicts and retargets steps to the robot’s own dynamics — handling terrain differences between flat operator space and uneven robot ground.
Abstract
Teleoperation of bipedal robots during fast-paced tasks requires seamless synchronization between user and robot motion. Rather than directly replicating foot poses, we retarget user steps to robot footstep locations, allowing the robot to utilize its own dynamics for locomotion. The system anticipates upcoming user steps to reduce timing delays and continuously refines estimates based on actual user movements. It also adapts for terrain differences between the operator’s flat surface and the robot’s uneven ground. Validated on the humanoid robot Nadia at the 2025 IEEE-RAS Humanoids conference.