Drewing, Nadine ; Ahmadi, Arjang ; Xiong, Xiaofeng ; Sharbafi, Maziar Ahmad (2024)
Comparison of Empirical and Reinforcement Learning (RL)-Based Control Based on Proximal Policy Optimization (PPO) for Walking Assistance: Does AI Always Win?
In: Biomimetics, 2024, 9 (11)
doi: 10.26083/tuprints-00028848
Artikel, Zweitveröffentlichung, Verlagsversion
 | Es ist eine neuere Version dieses Eintrags verfügbar. |
Kurzbeschreibung (Abstract)
The use of wearable assistive devices is growing in both industrial and medical fields. Combining human expertise and artificial intelligence (AI), e.g., in human-in-the-loop-optimization, is gaining popularity for adapting assistance to individuals. Amidst prevailing assertions that AI could surpass human capabilities in customizing every facet of support for human needs, our study serves as an initial step towards such claims within the context of human walking assistance. We investigated the efficacy of the Biarticular Thigh Exosuit, a device designed to aid human locomotion by mimicking the action of the hamstrings and rectus femoris muscles using Serial Elastic Actuators. Two control strategies were tested: an empirical controller based on human gait knowledge and empirical data and a control optimized using Reinforcement Learning (RL) on a neuromuscular model. The performance results of these controllers were assessed by comparing muscle activation in two assisted and two unassisted walking modes. Results showed that both controllers reduced hamstring muscle activation and improved the preferred walking speed, with the empirical controller also decreasing gastrocnemius muscle activity. However, the RL-based controller increased muscle activity in the vastus and rectus femoris, indicating that RL-based enhancements may not always improve assistance without solid empirical support.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2024 |
| Autor(en): | Drewing, Nadine ; Ahmadi, Arjang ; Xiong, Xiaofeng ; Sharbafi, Maziar Ahmad |
| Art des Eintrags: | Zweitveröffentlichung |
| Titel: | Comparison of Empirical and Reinforcement Learning (RL)-Based Control Based on Proximal Policy Optimization (PPO) for Walking Assistance: Does AI Always Win? |
| Sprache: | Englisch |
| Publikationsjahr: | 10 Dezember 2024 |
| Ort: | Darmstadt |
| Publikationsdatum der Erstveröffentlichung: | November 2024 |
| Ort der Erstveröffentlichung: | Basel |
| Verlag: | MDPI |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | Biomimetics |
| Jahrgang/Volume einer Zeitschrift: | 9 |
| (Heft-)Nummer: | 11 |
| Kollation: | 19 Seiten |
| DOI: | 10.26083/tuprints-00028848 |
| URL / URN: | https://tuprints.ulb.tu-darmstadt.de/28848 |
| Zugehörige Links: | |
| Herkunft: | Zweitveröffentlichung DeepGreen |
| Kurzbeschreibung (Abstract): | The use of wearable assistive devices is growing in both industrial and medical fields. Combining human expertise and artificial intelligence (AI), e.g., in human-in-the-loop-optimization, is gaining popularity for adapting assistance to individuals. Amidst prevailing assertions that AI could surpass human capabilities in customizing every facet of support for human needs, our study serves as an initial step towards such claims within the context of human walking assistance. We investigated the efficacy of the Biarticular Thigh Exosuit, a device designed to aid human locomotion by mimicking the action of the hamstrings and rectus femoris muscles using Serial Elastic Actuators. Two control strategies were tested: an empirical controller based on human gait knowledge and empirical data and a control optimized using Reinforcement Learning (RL) on a neuromuscular model. The performance results of these controllers were assessed by comparing muscle activation in two assisted and two unassisted walking modes. Results showed that both controllers reduced hamstring muscle activation and improved the preferred walking speed, with the empirical controller also decreasing gastrocnemius muscle activity. However, the RL-based controller increased muscle activity in the vastus and rectus femoris, indicating that RL-based enhancements may not always improve assistance without solid empirical support. |
| Freie Schlagworte: | wearable assistive device, exosuit, exo control, reinforcement learning, PPO |
| ID-Nummer: | Artikel-ID: 665 |
| Status: | Verlagsversion |
| URN: | urn:nbn:de:tuda-tuprints-288488 |
| Zusätzliche Informationen: | This article belongs to the Special Issue: Biologically Inspired Design and Control of Robots: Second Edition |
| Sachgruppe der Dewey Dezimalklassifikatin (DDC): | 500 Naturwissenschaften und Mathematik > 570 Biowissenschaften, Biologie 600 Technik, Medizin, angewandte Wissenschaften > 620 Ingenieurwissenschaften und Maschinenbau 700 Künste und Unterhaltung > 796 Sport |
| Fachbereich(e)/-gebiet(e): | 03 Fachbereich Humanwissenschaften 03 Fachbereich Humanwissenschaften > Institut für Sportwissenschaft 03 Fachbereich Humanwissenschaften > Institut für Sportwissenschaft > Sportbiomechanik |
| Hinterlegungsdatum: | 10 Dez 2024 13:35 |
| Letzte Änderung: | 21 Dez 2024 18:19 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
Verfügbare Versionen dieses Eintrags
- Comparison of Empirical and Reinforcement Learning (RL)-Based Control Based on Proximal Policy Optimization (PPO) for Walking Assistance: Does AI Always Win? (deposited 10 Dez 2024 13:35) [Gegenwärtig angezeigt]
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum