Minimalist mobile robotics: a colony-style architecture for an artificial creature
Minimalist mobile robotics: a colony-style architecture for an artificial creature
ALVINN: an autonomous land vehicle in a neural network
Advances in neural information processing systems 1
Introduction to the theory of neural computation
Introduction to the theory of neural computation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Advances in neural information processing systems 2
Maximum likelihood competitive learning
Advances in neural information processing systems 2
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
Learning hill-climbing functions as a strategy for generating behaviors in a mobile robot
Proceedings of the first international conference on simulation of adaptive behavior on From animals to animats
Learning to Perceive and Act by Trial and Error
Machine Learning
Learning in embedded systems
Evolving visually guided robots
Proceedings of the second international conference on From animals to animats 2 : simulation of adaptive behavior: simulation of adaptive behavior
Evolving dynamical neural networks for adaptive behavior
Adaptive Behavior
Sparse distributed memory and related models
Associative neural memories
An active vision architecture based on iconic representations
Artificial Intelligence - Special volume on computer vision
Using emergent modularity to develop control systems for mobile robots
Adaptive Behavior - Special issue on environment structure and behavior
Sparse Distributed Memory
Advances in Neural Information Processing Systems 5, [NIPS Conference]
Object indexing using an iconic sparse distributed memory
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Reinforcement learning: a survey
Journal of Artificial Intelligence Research
Natural basis functions and topographic memory for face recognition
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 1
Hidden state and reinforcement learning with instance-based stateidentification
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
| Hi-index | 0.00 |
We describe a general framework for learningperception-based navigational behaviors in autonomous mobilerobots. A hierarchical behavior-based decomposition of thecontrol architecture is used to facilitate efficient modularlearning. Lower level reactive behaviors such as collisiondetection and obstacle avoidance are learned using a stochastichill-climbing method while higher level goal-directed navigationis achieved using a self-organizing sparse distributed memory.The memory is initially trained by teleoperating the robot on asmall number of paths within a given domain of interest. Duringtraining, the vectors in the sensory space as well as the motorspace are continually adapted using a form of competitivelearning to yield basis vectors that efficiently span thesensorimotor space. After training, the robot navigates fromarbitrary locations to a desired goal location using motoroutput vectors computed by a saliency-based weighted averagingscheme. The pervasive problem of perceptual aliasing infinite-order Markovian environments is handled by allowing bothcurrent as well as the set of immediately preceding perceptualinputs to predict the motor output vector for the current timeinstant. We describe experimental and simulation resultsobtained using a mobile robot equipped with bump sensors,photosensors and infrared receivers, navigating within anenclosed obstacle-ridden arena. The results indicate that themethod performs successfully in a number of navigational tasksexhibiting varying degrees of perceptual aliasing.