Adaptive Human-Robot Interaction Based on Lag-Lead Modelling for Home-Based Stroke Rehabilitation: Novel Mechanisms for Assessment and Performance Based Adaptation of Task Difficulty

Abstract

In this work we present three interaction algorithms developed under the EU project SCRIPT in order to evaluate stroke patients' capabilities, evaluate their performance during robot-assisted exercise and consequently adapt the difficulty of the exercise to each individual. The first procedure assesses movement amplitude and duration with the subject making only a few repetitions of the motion. The second algorithm, aimed at evaluation of subject performance, is based on whether that the subject is lagging or leading with respect to a target reference trajectory. Finally, the third procedure aims at modifying the task difficulty (time allowed to reach the target, in this case) based on a performance indicator. The proposed mechanisms are completely independent from each other and could thus be exploited as single units. Furthermore, all of them are generalizable to any movement. These components have been adopted in the SCRIPT system, which is currently being tested in patients' home.