Intelligence without representation
Artificial Intelligence
Learning concepts from sensor data of a mobile robot
Machine Learning - Special issue on robot learning
Using Abstrips Abstractions -- Where do WeStand?
Artificial Intelligence Review
Integrated Region-Based Image Retrieval
Integrated Region-Based Image Retrieval
Phase Transitions in Relational Learning
Machine Learning
A Framework for Learning Rules from Multiple Instance Data
EMCL '01 Proceedings of the 12th European Conference on Machine Learning
Anchoring Symbols to Sensor Data: Preliminary Report
Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence
Fast and Robust Segmentation of Natural Color Scenes
ACCV '98 Proceedings of the Third Asian Conference on Computer Vision-Volume I - Volume I
The Capacity and the Sensitivity of Color Histogram Indexing
The Capacity and the Sensitivity of Color Histogram Indexing
The origins of syntax in visually grounded robotic agents
IJCAI'97 Proceedings of the Fifteenth international joint conference on Artifical intelligence - Volume 2
Multistrategy Operators for Relational Learning and Their Cooperation
Fundamenta Informaticae
Multistrategy Operators for Relational Learning and Their Cooperation
Fundamenta Informaticae
| Hi-index | 0.00 |
To efficiently identify properties from its environment is an essential ability of a mobile robot who needs to interact with humans. Successful approaches to provide robots with such ability are based on ad-hoc perceptual representation provided by AI designers. Instead, our goal is to endow autonomous mobile robots (in our experiments a Pioneer 2DX) with a perceptual system that can efficiently adapt itself to ease the learning task required to anchor symbols. Our approach is in the line of meta-learning algorithms that iteratively change representations so as to discover one that is well fitted for the task. The architecture we propose may be seen as a combination of the two widely used approach in feature selection: the Wrapper-model and the Filter-model. Experiments using the PLIC system to identify the presence of Humans and Fire Extinguishers show the interest of such an approach, which dynamically abstracts a well fitted image description depending on the concept to learn.