Works (5)
Updated: July 5th, 2023 14:44
2021 article
Reinforcement Learning Control of Robotic Knee With Human-in-the-Loop by Flexible Policy Iteration
Gao, X., Si, J., Wen, Y., Li, M., & Huang, H. (2021, May 6). IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, Vol. 5.
author keywords: Robots; Impedance; Tuning; Prosthetics; Knee; Erbium; Legged locomotion; Adaptive optimal control; data- and time-efficient learning; flexible policy iteration (FPI); human-in-the-loop; reinforcement learning (RL); robotic knee
MeSH headings : Humans; Computer Simulation; Neural Networks, Computer; Policy; Robotic Surgical Procedures; Robotics
TL;DR:
This study introduces flexible policy iteration (FPI), which can flexibly and organically integrate experience replay and supplemental values from prior experience into the RL controller, and shows system-level performances, including convergence of the approximate value function, (sub)optimality of the solution, and stability of the system.
(via Semantic Scholar)
arxiv.org (repository)
Sources: Web Of Science, ORCID, NC State University Libraries
Added: October 18, 2021
2021 article
Toward Expedited Impedance Tuning of a Robotic Prosthesis for Personalized Gait Assistance by Reinforcement Learning Control
Li, M., Wen, Y., Gao, X., Si, J., & Huang, H. (2021, May 26). IEEE TRANSACTIONS ON ROBOTICS, Vol. 5.
author keywords: Tuning; Impedance; Knee; Prosthetics; Legged locomotion; Robustness; Kinematics; Impedance control; knee prosthesis; policy iteration; rehabilitation robotics; reinforcement learning (RL)
TL;DR:
A policy iteration with constraint embedded (PICE) method as an innovative solution to the problem under the framework of reinforcement learning, using a projected Bellman equation with a constraint of assuring positive semidefiniteness of performance values during policy evaluation.
(via Semantic Scholar)
UN Sustainable Development Goal Categories
3. Good Health and Well-being
(Web of Science)
Sources: Web Of Science, ORCID, NC State University Libraries
Added: October 18, 2021
2020 journal article
Wearer-Prosthesis Interaction for Symmetrical Gait: A Study Enabled by Reinforcement Learning Prosthesis Control
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 28(4), 904–913.
author keywords: Prosthetics; Knee; Impedance; Legged locomotion; Robot kinematics; Tuning; Wearer-prosthesis interaction; robotic knee prosthesis; reinforcement learning; gait asymmetry; anteroposterior impulse
MeSH headings : Amputees; Artificial Limbs; Biomechanical Phenomena; Gait; Humans; Knee Joint; Prosthesis Design; Walking
TL;DR:
The results suggest that it is possible to personalize transfemoral prosthesis control for improved temporal-spatial gait symmetry, and indicated that the RL-based prosthesis tuning system was a potential tool for studying wearer-prosthesis interactions.
(via Semantic Scholar)
UN Sustainable Development Goal Categories
3. Good Health and Well-being
(Web of Science)
Sources: Web Of Science, NC State University Libraries, ORCID
Added: May 8, 2020
2017 journal article
A new powered lower limb prosthesis control framework based on adaptive dynamic programming
IEEE Transactions on Neural Networks and Learning Systems, 28(9), 2215–2220.
Source: NC State University Libraries
Added: August 6, 2018
2017 journal article
Interactions between transfemoral amputees and a powered knee prosthesis during load carriage
Scientific Reports, 7.
Source: NC State University Libraries
Added: August 6, 2018
Citation Index includes data from a number of different sources. If you have questions about the sources of data in the Citation Index or need a set of data which is free to re-distribute, please contact us.
Certain data included herein are derived from the Web of Science© and InCites© (2024) of Clarivate Analytics. All rights reserved. You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.