Simultaneous estimation of joint angle and interaction force towards sEMG-driven human-robot interaction during constrained tasks

Abstract

Human has excellent motor capability and performance in conducting various manipulation tasks. During some tasks such as tightening/loosening a screw with a screwdriver, the motion is accompanied by force exertion to the environment (that is, constrained motion). To obtain natural human-robot interaction (HRI) as human interacts/collaborates with the environment, decoding the human’s movement intention in a way of motion and interaction force is meaningful for robots to carry out such constrained tasks. This paper proposes a long shortterm memory (LSTM) -based decoding method for the simultaneous estimation of human motion and interactive force from muscle activities represented by surface electromyography (sEMG) signals. The sEMG recorded from the muscles of forearm is used to decode human’s movement intention. In order to extract smooth features from non-stationary sEMG signals, Bayesian filter is applied instead of traditional time-domain feature extraction method. From the real-time experiments on eight subjects, the LSTM-based decoding method represents high accuracy of motion estimation (91.7%) and force estimation (96.1%) despite of the existence of muscle coupling and non-stationary mapping between muscle activities and motion/interaction force during such constrained tasks. It indicates that the estimated motion and interaction force can be further applied for HRI in accomplishing constrained tasks.