Designing Personalised Rehabilitation Controllers using Offline Model-Based Optimisation

Andreas Christou; Daniel Gordon; Theodoros Stouraitis; Sethu Vijayakumar

doi:10.1109/ROBIO55434.2022.10011916

Designing Personalised Rehabilitation Controllers using Offline Model-Based Optimisation

Andreas Christou, Daniel Gordon, Theodoros Stouraitis, Sethu Vijayakumar

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

The use of robotic assistance in rehabilitation is becoming more popular, yet delivering optimal assistance remains an open challenge. In order to accelerate a patient’s recovery, assistance that is personalised to the needs of the patient is required. However, controllers of rehabilitation robots have traditionally been designed and tuned heuristically, through trial and error, with one set of parameters used across several patients. In this paper, we propose an offline model-based optimisation approach, which can be used to create personalised rehabilitation controllers. We formulate the process of designing and tuning a rehabilitation controller as a multi-objective optimisation problem, and we solve this problem using Bayesian optimisation. We evaluate our method with forward dynamics simulations and the results demonstrate that a set of controller parameters can be obtained that are both patient-specific and task-specific. Our approach could be used for the personalisation of controllers designed for rehabilitation, injury prevention and human augmentation.

Original language	English
Title of host publication	Proceedings of the 2022 IEEE International Conference on Robotics and Biomimetics (IEEE ROBIO 2022)
Publisher	Institute of Electrical and Electronics Engineers
Pages	148-155
Number of pages	8
ISBN (Electronic)	978-1-6654-8109-0
ISBN (Print)	978-1-6654-8110-6
DOIs	https://doi.org/10.1109/ROBIO55434.2022.10011916
Publication status	Published - 18 Jan 2023
Event	The 2022 IEEE International Conference on Robotics and Biomimetics - Xishuangbanna, China Duration: 5 Dec 2022 → 9 Dec 2022 http://robio2022.org/index.html

Conference

Conference	The 2022 IEEE International Conference on Robotics and Biomimetics
Abbreviated title	ROBIO 2022
Country/Territory	China
City	Xishuangbanna
Period	5/12/22 → 9/12/22
Internet address	http://robio2022.org/index.html

Access to Document

10.1109/ROBIO55434.2022.10011916Licence: All Rights Reserved

Designing Personalised_CHRISTOU_DOA15102022_AFVAccepted author manuscript, 7.1 MBLicence: Creative Commons: Attribution (CC-BY)

https://ieeexplore.ieee.org/document/10011916Licence: All Rights Reserved

Co-bots and Exoskeletons for Assisted Living with Ergonomic Measures
Vijayakumar, S.
EU other
1/02/21 → 31/12/22
Project: Research
Turing AI research Programme
Vijayakumar, S.
UK-based charities
1/09/18 → 31/08/23
Project: Research

Cite this

Christou, A., Gordon, D., Stouraitis, T., & Vijayakumar, S. (2023). Designing Personalised Rehabilitation Controllers using Offline Model-Based Optimisation. In Proceedings of the 2022 IEEE International Conference on Robotics and Biomimetics (IEEE ROBIO 2022) (pp. 148-155). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ROBIO55434.2022.10011916

@inproceedings{7d00fa8c8601436bb9865ca4c6f0a83c,

title = "Designing Personalised Rehabilitation Controllers using Offline Model-Based Optimisation",

abstract = "The use of robotic assistance in rehabilitation is becoming more popular, yet delivering optimal assistance remains an open challenge. In order to accelerate a patient{\textquoteright}s recovery, assistance that is personalised to the needs of the patient is required. However, controllers of rehabilitation robots have traditionally been designed and tuned heuristically, through trial and error, with one set of parameters used across several patients. In this paper, we propose an offline model-based optimisation approach, which can be used to create personalised rehabilitation controllers. We formulate the process of designing and tuning a rehabilitation controller as a multi-objective optimisation problem, and we solve this problem using Bayesian optimisation. We evaluate our method with forward dynamics simulations and the results demonstrate that a set of controller parameters can be obtained that are both patient-specific and task-specific. Our approach could be used for the personalisation of controllers designed for rehabilitation, injury prevention and human augmentation.",

author = "Andreas Christou and Daniel Gordon and Theodoros Stouraitis and Sethu Vijayakumar",

note = "Funding Information: *This research was supported in part by the Engineering and Physical Sciences Research Council (EPSRC, grant reference EP/L016834/1) as part of the Centre for Doctoral Training in Robotics and Autonomous Systems at Heriot-Watt University and The University of Edinburgh, in part by the Alan Turing Institute, U.K., and in part by the Honda Research Institute Europe, Germany. Publisher Copyright: {\textcopyright} 2022 IEEE.; The 2022 IEEE International Conference on Robotics and Biomimetics , ROBIO 2022 ; Conference date: 05-12-2022 Through 09-12-2022",

year = "2023",

month = jan,

day = "18",

doi = "10.1109/ROBIO55434.2022.10011916",

language = "English",

isbn = "978-1-6654-8110-6",

pages = "148--155",

booktitle = "Proceedings of the 2022 IEEE International Conference on Robotics and Biomimetics (IEEE ROBIO 2022)",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

url = "http://robio2022.org/index.html",

}

Christou, A, Gordon, D, Stouraitis, T & Vijayakumar, S 2023, Designing Personalised Rehabilitation Controllers using Offline Model-Based Optimisation. in Proceedings of the 2022 IEEE International Conference on Robotics and Biomimetics (IEEE ROBIO 2022). Institute of Electrical and Electronics Engineers, pp. 148-155, The 2022 IEEE International Conference on Robotics and Biomimetics , Xishuangbanna, China, 5/12/22. https://doi.org/10.1109/ROBIO55434.2022.10011916

Designing Personalised Rehabilitation Controllers using Offline Model-Based Optimisation. / Christou, Andreas; Gordon, Daniel; Stouraitis, Theodoros et al.
Proceedings of the 2022 IEEE International Conference on Robotics and Biomimetics (IEEE ROBIO 2022). Institute of Electrical and Electronics Engineers, 2023. p. 148-155.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Designing Personalised Rehabilitation Controllers using Offline Model-Based Optimisation

AU - Christou, Andreas

AU - Gordon, Daniel

AU - Stouraitis, Theodoros

AU - Vijayakumar, Sethu

N1 - Funding Information: *This research was supported in part by the Engineering and Physical Sciences Research Council (EPSRC, grant reference EP/L016834/1) as part of the Centre for Doctoral Training in Robotics and Autonomous Systems at Heriot-Watt University and The University of Edinburgh, in part by the Alan Turing Institute, U.K., and in part by the Honda Research Institute Europe, Germany. Publisher Copyright: © 2022 IEEE.

PY - 2023/1/18

Y1 - 2023/1/18

N2 - The use of robotic assistance in rehabilitation is becoming more popular, yet delivering optimal assistance remains an open challenge. In order to accelerate a patient’s recovery, assistance that is personalised to the needs of the patient is required. However, controllers of rehabilitation robots have traditionally been designed and tuned heuristically, through trial and error, with one set of parameters used across several patients. In this paper, we propose an offline model-based optimisation approach, which can be used to create personalised rehabilitation controllers. We formulate the process of designing and tuning a rehabilitation controller as a multi-objective optimisation problem, and we solve this problem using Bayesian optimisation. We evaluate our method with forward dynamics simulations and the results demonstrate that a set of controller parameters can be obtained that are both patient-specific and task-specific. Our approach could be used for the personalisation of controllers designed for rehabilitation, injury prevention and human augmentation.

AB - The use of robotic assistance in rehabilitation is becoming more popular, yet delivering optimal assistance remains an open challenge. In order to accelerate a patient’s recovery, assistance that is personalised to the needs of the patient is required. However, controllers of rehabilitation robots have traditionally been designed and tuned heuristically, through trial and error, with one set of parameters used across several patients. In this paper, we propose an offline model-based optimisation approach, which can be used to create personalised rehabilitation controllers. We formulate the process of designing and tuning a rehabilitation controller as a multi-objective optimisation problem, and we solve this problem using Bayesian optimisation. We evaluate our method with forward dynamics simulations and the results demonstrate that a set of controller parameters can be obtained that are both patient-specific and task-specific. Our approach could be used for the personalisation of controllers designed for rehabilitation, injury prevention and human augmentation.

U2 - 10.1109/ROBIO55434.2022.10011916

DO - 10.1109/ROBIO55434.2022.10011916

M3 - Conference contribution

SN - 978-1-6654-8110-6

SP - 148

EP - 155

BT - Proceedings of the 2022 IEEE International Conference on Robotics and Biomimetics (IEEE ROBIO 2022)

PB - Institute of Electrical and Electronics Engineers

T2 - The 2022 IEEE International Conference on Robotics and Biomimetics

Y2 - 5 December 2022 through 9 December 2022

ER -

Designing Personalised Rehabilitation Controllers using Offline Model-Based Optimisation

Abstract / Description of output

Conference

Access to Document

Fingerprint

Projects

Co-bots and Exoskeletons for Assisted Living with Ergonomic Measures

Turing AI research Programme

Cite this