@inbook{06ca3ed43a3940aca6a833b5d14840cd,
title = "Understanding Human-Prosthesis Interaction via Reinforcement Learning-Based Echo Control: A Case Study",
abstract = "This case study aimed to understand human-prosthesis interaction while the impedance control of a robotic prosthesis was tuned in order to echo the knee kinematics on the intact joint. Echo control derives from a common belief that if the prosthesis joint mechanics meet those of the intact joint, more symmetrical and normal gait should be reached in the prosthesis user. In this study, our previous developed reinforcement learning (RL) control was used to tune impedance of a power knee prosthesis in walking to achieve echo control. It was tested on one able-bodied human subject walking with the robotic knee. The results showed that the prosthesis control parameter tuning was coupled with changes in intact knee mechanics. Nevertheless, regardless such neuromechanic coupling between the two lower limbs, RL was robust to tune prosthesis control and meet the intact knee kinematics. Finally, the RL echo control enabled us to examine gait symmetry. Additional research efforts are still needed to identify the influence of echo control of prosthetic knee on gait tempospatial symmetry.",
author = "Ruofan Wu and Minhan Li and Jennie Si and {(Helen) Huang}, He",
note = "Funding Information: This work was supported in part by National Science Foundation #1563454, #1563921, #1808752 and #1808898. Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.",
year = "2022",
doi = "10.1007/978-3-030-70316-5_112",
language = "English (US)",
series = "Biosystems and Biorobotics",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "697--701",
booktitle = "Biosystems and Biorobotics",
address = "Germany",
}