Data-Driven Human-Robot Interaction Without Velocity Measurement Using Off-Policy Reinforcement Learning

In this paper, we present a novel data-driven design method for the human-robot interaction (HRI) system, where a given task is achieved by cooperation between the human and the robot. The presented HRI controller design is a two-level control design approach consisting of a task-oriented performance optimization design and a plant-oriented impedance controller design. The task-oriented design minimizes the human effort and guarantees the perfect task tracking in the outer-loop, while the plant-oriented achieves the desired impedance from the human to the robot manipulator end-effector in the inner-loop. Data-driven reinforcement learning techniques are used for performance optimization in the outer-loop to assign the optimal impedance parameters. In the inner-loop, a velocity-free filter is designed to avoid the requirement of end-effector velocity measurement. On this basis, an adaptive controller is designed to achieve the desired impedance of the robot manipulator in the task space. The simulation and experiment of a robot manipulator are conducted to verify the efficacy of the presented HRI design framework.

I. Introduction

Robotic manipulators have played an important role in engineering applications, such as master-slave teleoperation systems [1], construction automation [2], space engineering [3], to name a few. When the human is restricted by the physical limitation or when operating in a harsh environment is required, the robot manipulators can handle strenuous and dangerous work that is difficult or impossible for human operators. However, robot manipulators cannot completely replace the human because of robots' lack of high-level of learning and inference ability. Therefore, the interaction between the human and the robot could take the best of human and robot capabilities. Successful applications of human-robot interaction (HRI) system designs include physiotherapy [4], human amplifier [5], assistive haptic device [6]. In this paper, we employ the two-level design framework [7] for the HRI systems with novel outer-loop and inner-loop designs to obviate the requirement of velocity measurement and the complete knowledge of system dynamics.