CHIP: Adaptive Compliance for Humanoid Control through Hindsight Perturbation
This addresses the problem of limited manipulation capabilities in humanoid robots for real-world applications, representing an incremental improvement by building on existing motion-tracking controllers.
The paper tackles the challenge of enabling humanoid robots to perform forceful manipulation tasks by proposing CHIP, a plug-and-play module that allows controllable end-effector stiffness while maintaining agile motion tracking, resulting in successful execution of tasks like multi-robot collaboration and door opening.
Recent progress in humanoid robots has unlocked agile locomotion skills, including backflipping, running, and crawling. Yet it remains challenging for a humanoid robot to perform forceful manipulation tasks such as moving objects, wiping, and pushing a cart. We propose adaptive Compliance Humanoid control through hIsight Perturbation (CHIP), a plug-and-play module that enables controllable end-effector stiffness while preserving agile tracking of dynamic reference motions. CHIP is easy to implement and requires neither data augmentation nor additional reward tuning. We show that a generalist motion-tracking controller trained with CHIP can perform a diverse set of forceful manipulation tasks that require different end-effector compliance, such as multi-robot collaboration, wiping, box delivery, and door opening.