Artificial co-drivers as a universal enabling technology for future intelligent vehicles and transportation systems
- Submitting institution
-
Middlesex University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 343
- Type
- D - Journal article
- DOI
-
10.1109/TITS.2014.2330199
- Title of journal
- IEEE Transactions on Intelligent Transportation Systems
- Article number
- -
- First page
- 244
- Volume
- 16
- Issue
- 1
- ISSN
- 1524-9050
- Open access status
- Out of scope for open access requirements
- Month of publication
- July
- Year of publication
- 2014
- URL
-
http://eprints.mdx.ac.uk/19480/
- 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
-
7
- Research group(s)
-
-
- Citation count
- 38
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper is significant in setting-out the conceptual underpinnings of the H2020 DREAMS4CARS project and providing a novel conception of human-machine interaction. It proposes an extension of perception-action learning capable of explaining driving in terms of a hierarchy of concurrent subsumptive control loops executing at progressively decreasing time scales. Critically, this control subsumption is mirrored via a representational/perceptual subsumption common to both humans and machines, allowing human driving intentions to be transparently interpretable to machine learning processes. This system was successfully implemented within a FIAT test vehicle, and remains the subject of active ongoing research.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -