Modeling, identification and joint impedance control of the atlas arms

Compliant manipulation has become central to robots that are sought to safely act in and interact with unstructured as well as only partially known environments. In this paper we equip the hydraulically actuated, usually position controlled arms of the Atlas robot with model-based joint impedance control, including suitable damping design, and experimentally verify the proposed algorithm. Our approach, which originates from the advances in soft-robotics control, relies on high-performance low-level joint torque control. This makes it independent from the actual technology being hydraulic or electromechanical. This paper describes the approach to accurately model the dynamics, and design the optimal excitation trajectory for system identification to enable the specification of model-based feed-forward controls. In conclusion, the implemented controller enables the robot arm to execute significantly smoother motions, be compliant against external forces, and have similar tracking performance as compared to the existing position control scheme. Finally, unknown modeling inaccuracies and contact forces are accurately estimated by a suitable disturbance observer, which could be used in the future to further enhance our controller's performance.