Learning Shared Control by Demonstration for Personalized Wheelchair Assistance
- Submitting institution
-
University of Nottingham, The
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 5225278
- Type
- D - Journal article
- DOI
-
10.1109/TOH.2018.2804911
- Title of journal
- IEEE Transactions on Haptics
- Article number
- -
- First page
- 431
- Volume
- 11
- Issue
- 3
- ISSN
- 1939-1412
- Open access status
- Compliant
- Month of publication
- February
- Year of publication
- 2018
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
1
- Research group(s)
-
-
- Citation count
- 8
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper presents a user modelling technique for assistance generation, based on the learning-by-demonstration (LbD) paradigm, and tests the concept with a robotic wheelchair. The study is important in extending LbD to teach a robot to interact with a human, rather than teaching it to perform a task alone. The concept was nominated by the IEEE ROMAN’15 program committee for the RSJ/KROS Distinguished Interdisciplinary Research Award. The paper demonstrates the concept in a user study, where machine-learned assistance is compared to human assistance, akin to a Turing test, where comparable performance is observed for several dependent variables.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
