Map learning with uninterpreted sensors and effectors
Artificial Intelligence
Predictive state representations: a new theory for modeling dynamical systems
UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence
ICML '05 Proceedings of the 22nd international conference on Machine learning
Learning predictive state representations in dynamical systems without reset
ICML '05 Proceedings of the 22nd international conference on Machine learning
Learning subjective representations for planning
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Unsupervised learning of image manifolds by semidefinite programming
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance
International Journal of Robotics Research
Hi-index | 0.00 |
Extracting a map from a stream of experience is a key problem in robotics and artificial intelligence in general. We propose a technique, called subjective mapping, that seeks to learn a fully specified predictive model, or map, without the need for expert provided models of the robot's motion and sensor apparatus. We briefly overview the recent advancements presented elsewhere (ICML, IJCAI, and ISRR) that make this possible, examine its significance in relationship to other developments in the field. and outline open issues that remain to be addressed.