Proceedings of the fifth international conference on simulation of adaptive behavior on From animals to animats 5
A Study of Index Structures for Main Memory Database Management Systems
VLDB '86 Proceedings of the 12th International Conference on Very Large Data Bases
Reinforcement learning with selective perception and hidden state
Reinforcement learning with selective perception and hidden state
From Wheels to Wings with Evolutionary Spiking Circuits
Artificial Life
A Machine Learning Evaluation of an Artificial Immune System
Evolutionary Computation
A Simple Aplysia-Like Spiking Neural Network to Generate Adaptive Behavior in Autonomous Robots
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies
Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies
Context-awareness in user modelling: requirements analysis for a case-based reasoning application
ICCBR'03 Proceedings of the 5th international conference on Case-based reasoning: Research and Development
Self-adaptation and dynamic environment experiments with evolvable virtual machines
ESOA'05 Proceedings of the Third international conference on Engineering Self-Organising Systems
Adaptive evolutionary planner/navigator for mobile robots
IEEE Transactions on Evolutionary Computation
Vision-Motor Abstraction toward Robot Cognition
ICONIP '09 Proceedings of the 16th International Conference on Neural Information Processing: Part II
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Hi-index | 0.00 |
This work concerns practical issues surrounding the application of learning and memory in a real mobile robot with the goal of optimal navigation in dynamic environments. A novel hierarchical adaptive controller that contains two-level units was developed and trained in a physical mobile robot "e-Puck." In the low-level unit, the robot holds a number of biologically inspired Aplysia -like spiking neural networks that have the property of spike time-dependent plasticity. Each of these networks is trained to become an expert in a particular local environment(s). All the trained networks are stored in a tree-type memory structure that is located in the high-level unit. These stored networks are used as experiences for the robot to enhance its navigation ability in both new and previously trained environments. The robot's memory is designed to hold memories of various lengths and has a simple searching mechanism. Forgetting and dynamic clustering techniques are used to control the memory size. Experimental results show that the proposed model can produce a robot with learning and memorizing capabilities that enable it to survive in complex and highly dynamic environments.