A physics-based model for predicting user intent in shared-control pedestrian mobility aids

This paper presents a physics-based model approach to infer navigational intent of the user of a walker, based on measuring forces and moments applied to the walker´s handles. Our experiments use two 6-DOF force/moment sensors on the walker´s handles, a 2-D kinematic-dynamic model of the walker and a digital motion capture system to trace the path of the walker. The motion capture system records the path the walker follows while the 6 DOF sensors record the handle forces used to guide the walker along that path. A dynamic model of the walker that determines user navigational intent from force/moment data was developed and validated against the motion capture data streams. This paper describes the development and validation of the model as well as plans for using the model as a path predictor. The inferred user intent is incorporated into a passive shared steering control system for the walker.