Environment recognition for context-dependent control of powered exoskeletons

The daily use of advanced wearable robotic devices for the assistance of people with locomotive disabilities is still facing clear limitations in usability and acceptance. In most devices, the correct selection and initiation of pre-defined functions and ac- tivities rely on the user's input and constant interpretation of the environment, which results in a substantial cognitive workload. In this study, a novel environment recog- nition and parameterization system that uses depth camera images is proposed as a potential assistant in the control of a powered lower-limb exoskeleton. The feasibil- ity of an on-line shared control approach between the user and the parameterization system was assessed in two specific use cases of lower-limb exoskeletons: Mode selec- tion assistance and dynamic step length adaptation. In a sequence of realistic daily life tasks, the assistance provided by the proposed system reduced the mean overall workload by 19% on a group of seven neurologically intact subjects. In conclusion, an assistive environment recognition and parameterization system to select and initiate appropriate activity modes, and to adjust control parameters such as step length shows the potential of reducing the cognitive workload on the user, and thereby positively influencing device usability.