Robot Multi-Modal Object Perception and Recognition: Synthetic Maturation of Sensorimotor Learning in Embodied Systems
- Submitting institution
-
Aston University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 37467405
- Type
- D - Journal article
- DOI
-
10.1109/TCDS.2020.2965985
- Title of journal
- IEEE Transactions on Cognitive and Developmental Systems
- Article number
- 0
- First page
- -
- Volume
- 0
- Issue
- 0
- ISSN
- 2379-8920
- Open access status
- Compliant
- Month of publication
- January
- Year of publication
- 2020
- 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
-
4
- Research group(s)
-
A - Aston Institute of Urban Technology and the Environment (ASTUTE)
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- We propose a holistic architecture for developmentally plausible robotic learning and acting. The work takes a longitudinal approach where a humanoid scaffolds its knowledge as its subsystems gradually mature equivalently to human development. The results not only demonstrate the ability to recognise objects, including own hand but the impact of uncertainty due to underdeveloped modalities to object recognition. The contribution is of importance to roboticists and child psychologists as it provides practical illustrations of the complexity in the modelling of human infants.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
