Cooperative human-robot control based on Fitts' law

Many studies on human motor control have examined how humans move the arms. A well known phenomenon known as the Fitts' law describes the trade-off between the speed of motion and its accuracy. In robotics, many studies were performed, and different control methods were proposed, for robots working in well structured environments. Nevertheless, the cooperation between humans and robots remains a challenging task that is highly relevant for robots aiming to work together with humans in non-structured environments. In this paper we propose a novel method for on-line adaptation of robotic trajectories, where humans and robots are autonomous agents coupled through physical interaction, for example through manipulated object. Within the proposed framework, the robot adapts to the human motion through the sensory feedback by taking into account the Fitts' law where the user specific behavior is estimated using a recursive least square updates. The movement trajectories are represented by the Dynamic Movement Primitives, where the adaptation relies on the Iterative Learning Controller framework. The proposed approach was evaluated by a cooperative human robot arm-reaching task on a plane. We tested the accuracy and efficiency of the proposed method, showed its relevance and demonstrated that the proposed approach fully adapts to the human motor control and maintains the desired accuracy of the movement.