Mixed Logical Inference and Probabilistic Planning for Robots in Unreliable Worlds
- Submitting institution
-
The University of Birmingham
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 42336624
- Type
- D - Journal article
- DOI
-
10.1109/TRO.2015.2422531
- Title of journal
- IEEE Transactions on Robotics
- Article number
- -
- First page
- 699
- Volume
- 31
- Issue
- 3
- ISSN
- 1552-3098
- Open access status
- Out of scope for open access requirements
- Month of publication
- May
- Year of publication
- 2015
- 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
-
2
- Research group(s)
-
-
- Citation count
- 24
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The architecture described in this paper is a step towards addressing the fundamental open problem of combining non-monotonic logical inference and probabilistic planning in the context of mobile robots in dynamic, complex environments. Unlike architectures that switch between logical and probabilistic reasoning, this architecture supports smooth transfer of knowledge and control between the two reasoning components, significantly improving the reliability of the robots' operation. This article in a high-impact journal extends initial work that won a Paper of Excellence Award at ICDL-2012 conference, and was the basis of a grant (as PI) from the US Office of Naval Research (US$977K).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -