Human-robot coexistence and contact handling with redundant robots

Abstract

We present further computational tools and control results in the framework of human-robot coexistence and collaboration. A GPU parallel processing algorithm is introduced for real-time monitoring of dynamic distances between a robot and generic obstacles moving in its environment, taking advantage of the handling of RGB-D data directly in the depth space of the sensor. Combined with the use of model-based residual signals, this approach allows efficient detection of contact points on the robot with simultaneous estimation of the exchanged contact forces. When the robot is kinematically redundant for the original task and undergoes a physical contact, a control scheme accommodates collaboration trying to preserve task execution, or reacts by abandoning the task if the estimated contact forces exceed some safety threshold. Experimental results are reported for a KUKA LWR.