An Artificial Robot Nervous System To Teach Robots How To Feel Pain And Reflexively React To Potentially Damaging Contacts

Abstract

In this letter, we introduce the concept of an artificial Robot Nervous System (aRNS) as a novel way of unifying multimodal physical stimuli sensation with robot pain-reflex movements. We focus on the formalization of robot pain, based on insights from human pain research, as an interpretation of tactile sensation. Specifically, pain signals are used to adapt the equilibrium position, stiffness, and feedforward torque of a pain-based impedance controller. The schemes are experimentally validated with the KUKA LWR4+ for simulated and real physical collisions using the BioTac sensor.