3 accepted papers
Ankle exoskeletons have the potential to augment mobility, but control strategies have largely failed to seamlessly adapt to changes in the locomotion task. Here, we introduce a multi-headed network that predicts gait speed, ground incline, stance/swing transitions, and percent stance. These predict
Ankle exoskeletons have the potential to improve mobility, but common controllers are often inflexible to variations in tasks, such as changes in walking speed. To enable effective variable-speed exoboot control, we developed and validated a two-headed convolutional neural network trained to (1) cla
Modern passive ankle-foot prostheses do not exhibit appropriate biomechanics during walking, and are unable to adjust their mechanics for other mobility tasks, such as stair traversal or quiet standing. In this paper, we introduce a quasi-passive ankle-foot prosthesis that addresses these challenges…