Neural Network-Based Motion Control of an Underactuated Wheeled Inverted Pendulum Model
- Submitting institution
-
University of Plymouth
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 908
- Type
- D - Journal article
- DOI
-
10.1109/tnnls.2014.2302475
- Title of journal
- IEEE Transactions on Neural Networks and Learning Systems
- Article number
- -
- First page
- 2004
- Volume
- 25
- Issue
- 11
- ISSN
- 2162-237X
- Open access status
- Out of scope for open access requirements
- Month of publication
- March
- Year of publication
- 2014
- 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
-
3
- Research group(s)
-
-
- Citation count
- 164
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper exhibits an efficient motion controller for a wheeled underactuated inverted pendulum (WIP). This is important because WIPs are widely applicable models of (at best partially controlled humans) on two-wheeled autonomous vehicles. The paper presents a breakthrough in solving this difficult control problem by combining state-of-the-art techniques with a novel model-splitting method and the use of neural networks. A rigorous analysis guarantees that tilt angles stay in acceptable bounds, providing safety margins for human drivers. Altmetrics lists 26 international patent applications that cite this paper.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -