Including a Musculoskeletal Model in the Control Loop of an Assistive Robot for the Design of Optimal Target Forces

Assistive and rehabilitation robots are designed in the attempt to alleviate the work of the therapists and to accelerate the rehabilitation of the patients. Including accurate descriptions of the human body dynamics into the control loop of these robots can lead to the creation of smoother human-robot interfaces. In this paper we present: 1) a torque-driven musculoskeletal model of the sit-to-stand movement, 2) the optimal control (OC) solution of the corresponding predictive dynamics and 3) the model predictive control (MPC) solution that simulates how the human model interacts with a simple robot model. The model is a planar and symmetric representation of the major joints involved in the sit-to-stand movement: ankle, knee, hip, shoulder, elbow and neck. The seat has been modelled as a contact force, reacting like a spring-damper in the vertical direction and as a friction along the horizontal direction. Experimental data collected on a single subject provided the reference for qualitative movement comparison. The movement predicted by the OC exhibits the major characteristics of the real movement (e.g. preparation phase, joint torque and articular angle patterns). The MPC framework allowed us to simulate the reaction of the musculoskeletal model to an external force provided by a robot. This method could be used in the future in the design of specific target forces for assistive robot strategies and smooth human-robot interfaces.