PROJECT TITLE :

Development of an Environment-Aware Locomotion Mode Recognition System for Powered Lower Limb Prostheses

ABSTRACT:

This paper aimed to develop and evaluate an surroundings-aware locomotion mode recognition system for volitional management of powered artificial legs. A portable terrain recognition (TR) module, consisting of an inertia measurement unit and a laser distance meter, was engineered to spot the type of terrain in front of the wearer while walking. A call tree was used to classify the terrain types and provide either coarse or refined info regarding the walking atmosphere. Then, the obtained environmental information was modeled as a priori likelihood and was integrated with a neuromuscular-mechanical-fusion-based locomotion mode (LM) recognition system. The designed TR module and environmental-aware LM recognition system was evaluated separately on ready-bodied subjects and a transfemoral amputee on-line. The results showed that the TR module provided top quality environmental information: TR accuracy is on top of ninety eightpercent and terrain transitions are detected over five hundred ms before the time needed to change the prosthesis management mode. This enabled smooth locomotion mode transitions for the wearers. The obtained environmental data any improved the performance of LM recognition system, irrespective of whether coarse or refined data was used. In addition, the atmosphere-aware LM recognition system created reliable online performance when the TR output was relatively noisy, which indicated the potential of this method to work in unconstructed setting. This paper demonstrated that environmental information should be considered for operating wearable lower limb robotic devices, such as prosthetics and orthotics.