Name
Title | ||
|---|---|---|
Learning Bayesian models of sensorimotor interaction: from random exploration toward the discovery of new behaviors |
Abstract | ||
|---|---|---|
We are interested in probabilistic models of space and navigation. We describe an experiment where a Koala robot uses experimental data, gathered by randomly exploring the sensorimotor space, so as to learn a model of its interaction with the environment. This model is then used to generate a variety of new behaviors, from obstacle avoidance to wall following to ball pushing, which were previously unknown by the robot. The learned model can be seen as a building block for a hierarchical control architecture based on the Bayesian Map formalism. Index Terms—Navigation, space representation, learning, be- havior, bayesian model. |
Year | DOI | Venue |
|---|---|---|
2005 | 10.1109/IROS.2005.1545147 | IROS |
Keywords | Field | DocType |
Bayes methods,collision avoidance,learning (artificial intelligence),mobile robots,navigation,probability,sensors,Bayesian map formalism,Bayesian model,Koala robot,hierarchical control architecture,obstacle avoidance,probabilistic model,sensorimotor interaction,Navigation,bayesian model,behavior,learning,space representation | Obstacle avoidance,Computer vision,Architecture,Experimental data,Computer science,Artificial intelligence,Probabilistic logic,Formalism (philosophy),Robot,Mobile robot,Machine learning,Bayesian probability | Conference |
Citations | PageRank | References |
2 | 0.46 | 7 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Éva Simonin | 1 | 2 | 0.46 |
| Julien Diard | 2 | 62 | 10.72 |
| Pierre Bessière | 3 | 425 | 86.40 |