Learning Compliance Adaptation in Contact-Rich Manipulation
This work addresses the need for adaptive control in robotics to handle unexpected situations during contact-rich tasks, representing an incremental improvement in combining anomaly detection with adaptive control.
The paper tackled the problem of enabling compliant robot behavior in contact-rich manipulation tasks by learning predictive models of force profiles, achieving simultaneous high tracking accuracy of desired motions and force profiles along with adaptation to force perturbations from physical human interaction.
Compliant robot behavior is crucial for the realization of contact-rich manipulation tasks. In such tasks, it is important to ensure a high stiffness and force tracking accuracy during normal task execution as well as rapid adaptation and complaint behavior to react to abnormal situations and changes. In this paper, we propose a novel approach for learning predictive models of force profiles required for contact-rich tasks. Such models allow detecting unexpected situations and facilitates better adaptive control. The approach combines an anomaly detection based on Bidirectional Gated Recurrent Units (Bi-GRU) and an adaptive force/impedance controller. We evaluated the approach in simulated and real world experiments on a humanoid robot.The results show that the approach allow simultaneous high tracking accuracy of desired motions and force profile as well as the adaptation to force perturbations due to physical human interaction.