Abstract: Recent advances in computer vision and deep learning are allowing researchers to develop automated environment recognition systems for robotic leg prostheses and exoskeletons. However, small-scale and private training datasets have impeded the widespread development and dissemination of image classification algorithms (e.g., convolutional neural networks) for recognizing the human walking environment.


*Details on the ExoNet database are provided in the references above. Please email Brokoslaw Laschowski (blaschow@uwaterloo.ca) for any additional questions and/or technical assistance. 


Previous studies of robotic leg prostheses and exoskeletons with regenerative actuators have focused almost exclusively on level-ground walking applications. Here we analyzed the lower-limb joint mechanical work and power during stand-to-sit movements using inverse dynamics to estimate the biomechanical energy theoretically available for electrical energy regeneration and storage. Nine subjects performed 20 sitting and standing movements while lower-limb kinematics and ground reaction forces were experimentally measured.