Multiobjective Optimization for Stiffness and Position Control in a Soft Robot Arm Module

Abstract

The central concept of this letter is to develop an assistive manipulator that can automate the bathing task for elderly citizens. We propose to exploit principles of soft robotic technologies to design and control a compliant system to ensure safe human–robot interaction, a primary requirement for the task. The overall system is intended to be modular with a proximal segment that provides structural integrity to overcome gravitational challenges and a distal segment to perform the main bathing activities. The focus of this letter is on the design and control of the latter module. The design comprises of alternating tendons and pneumatics in a radial arrangement, which enables elongation, contraction, and omnidirectional bending. Additionally, a synergetic coactivation of cables and tendons in a given configuration allows for stiffness modulation, which is necessary to facilitate washing and scrubbing. The novelty of the work is twofold: 1) Three base cases of antagonistic actuation are identified that enable stiffness variation. Each category is then experimentally characterized by the application of an external force that imposes a linear displacement at the tip in both axial and lateral directions. 2) The development of a novel algorithm based on cooperative multiagent reinforcement learning that simultaneously optimizes stiffness and position. The results highlight the effectiveness of the design and control to contribute toward the development of the assistive device.