Coevolution of active vision and feature selection
| Autor: | Dario Floreano, Davide Marocco, Toshifumi Kato, Eric L. Sauser |
|---|---|
| Přispěvatelé: | Floreano, Dario, Kato, Toshifumi, Marocco, Davide, Sauser, Eric |
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
Engineering
Automobile Driving Visual perception Neural Networks General Computer Science Machine vision Models Neurological Active Vision Biophysics Evolutionary robotics Poison control Feature selection Mobile Robots Discrimination Psychological Animals Humans Computer vision Visual Pathways Visual Pathway Feature Selection Active vision Vision Ocular Discrimination (Psychology) Neurons Animal business.industry Mobile robot Robotics Artificial Evolution Neural Networks (Computer) Neuron Biological Evolution Robotic Algorithm Visual Perception Robot Artificial intelligence Neural Networks Computer Evolutionary Robotics business Algorithms Photic Stimulation Human Biotechnology |
| Popis: | We show that complex visual tasks, such as position- and size-invariant shape recognition and navigation in the environment, can be tackled with simple architectures generated by a coevolutionary process of active vision and feature selection. Behavioral machines equipped with primitive vision systems and direct pathways between visual and motor neurons are evolved while they freely interact with their environments. We describe the application of this methodology in three sets of experiments, namely, shape discrimination, car driving, and robot navigation. We show that these systems develop sensitivity to a number of oriented, retinotopic, visual-feature-oriented edges, corners, height, and a behavioral repertoire to locate, bring, and keep these features in sensitive regions of the vision system, resembling strategies observed in simple insects |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|