A massively parallel architecture for a self-organizing neural pattern recognition machine
Computer Vision, Graphics, and Image Processing
CNLS '89 Proceedings of the ninth annual international conference of the Center for Nonlinear Studies on Self-organizing, Collective, and Cooperative Phenomena in Natural and Artificial Computing Networks on Emergent computation
Simulation of adaptive behavior in animats: review and prospect
Proceedings of the first international conference on simulation of adaptive behavior on From animals to animats
Mapbuilding using self-organising networks in “really useful robots”
Proceedings of the first international conference on simulation of adaptive behavior on From animals to animats
An adaptive neural network: the cerebral cortex
An adaptive neural network: the cerebral cortex
Neural Networks - Special issue: models of neurodynamics and behavior
Memoryless policies: theoretical limitations and practical results
SAB94 Proceedings of the third international conference on Simulation of adaptive behavior : from animals to animats 3: from animals to animats 3
SAB94 Proceedings of the third international conference on Simulation of adaptive behavior : from animals to animats 3: from animals to animats 3
Reinforcement learning: a survey
Journal of Artificial Intelligence Research
Learning reactive and planning rules in a motivationally autonomousanimat
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Hi-index | 0.00 |
In this chapter, we intend to present a way to design Neural Network architectures to control an autonomous mobile robot using vision as the main sensor. We start discussing the notion of autonomy. In particular we show how it constrains the learning and the architecture of the control system. We propose a set of neural tools developed to solve problems linked with autonomous learning: the Perception-Action (PerAc) architecture, the Probabilistic Conditioning Rule (PCR) and a system allowing to plan actions (integrating a system for transition learning and prediction). Illustrations on different examples (visual homing, maze problem and planning) of how the tools that has been elaborated can be assembled to form a generic control system reusable for several tasks are presented along the description of the tools. Finally, future developments and the way to integrate these works in a general cognitive science framework will be discussed.