An Ensemble of Cooperative Extended Kohonen Maps for Complex Robot Motion Tasks

Authors:
Kian Hsiang Low;Wee Kheng Leow;Marcelo H. Ang, Jr.
Affiliations:
Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213-3890, U. S. A.;Department of Computer Science, National University of Singapore, Singapore 117543, Singapore;Department of Mechanical Engineering, National University of Singapore, Singapore 119260, Singapore
Venue:
Neural Computation
Year:
2005

Citing 49
Cited 2

Adaptive filter theory

Adaptive filter theory
Topology conserving mappings for learning motor tasks

AIP Conference Proceedings 151 on Neural Networks for Computing
INFANT neural controller for adaptive sensory-motor coordination

Neural Networks
A resource-allocating network for function interpolation

Neural Computation
Automatic programming of behavior-based robots using reinforcement learning

Artificial Intelligence
First- and second-order methods for learning: between steepest descent and Newton's method

Neural Computation
Democracy in neural nets: voting schemes for classification

Neural Networks
Learning goal-directed sensory-based navigation of a mobile robot

Neural Networks
Artificial intelligence: a modern approach

Artificial intelligence: a modern approach
A dynamical systems perspective on agent-environment interaction

Artificial Intelligence - Special volume on computational research on interaction and agency, part 1
A real-time, unsupervised neural network for the low-level control of a mobile robot in a nonstationary environment

Neural Networks
Dynamic cell structure learns perfectly topology preserving map

Neural Computation
Methods for combining experts' probability assessments

Neural Computation
Mind as motion: explorations in the dynamics of cognition

Mind as motion: explorations in the dynamics of cognition
Locally Weighted Learning

Artificial Intelligence Review - Special issue on lazy learning
Optimal linear combinations of neural networks

Neural Networks
On Combining Classifiers

IEEE Transactions on Pattern Analysis and Machine Intelligence
Experiments with reinforcement learning in problems with continuous state and action spaces

Adaptive Behavior
Action selection in an autonomous agent with a hierarchical distributed reactive planning architecture

AGENTS '98 Proceedings of the second international conference on Autonomous agents
A self-organizing neural network architecture for navigation using optic flow

Neural Computation
Hierarchical Learning of Navigational Behaviors in anAutonomous Robot using a Predictive Sparse DistributedMemory

Machine Learning - Special issue on learning in autonomous robots
Learning from Innate Behaviors: A Quantitative Evaluation of Neural Network Controllers

Machine Learning - Special issue on learning in autonomous robots
Sewer robotics

Proceedings of the fifth international conference on simulation of adaptive behavior on From animals to animats 5
BISMARC: a biologically inspired system for map-based autonomous rover control

Neural Networks - Special issue on neural control and robotics: biology and technology
Robot navigation with a polar neural map

AAAI '99/IAAI '99 Proceedings of the sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence
Experiences with an interactive museum tour-guide robot

Artificial Intelligence - Special issue on applications of artificial intelligence
An overview of radial basis function networks

Radial basis function networks 2
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
An Behavior-based Robotics

An Behavior-based Robotics
A hybrid mobile robot architecture with integrated planning and control

Proceedings of the first international joint conference on Autonomous agents and multiagent systems: part 1
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Self-Organizing Maps

Self-Organizing Maps
Scalable Techniques from Nonparametric Statistics for Real Time Robot Learning

Applied Intelligence
Collaboration Through the Exploitation of Local Interactions in Autonomous Collective Robotics: The Stick Pulling Experiment

Autonomous Robots
Continuous-Action Q-Learning

Machine Learning
Neural Network Ensembles

IEEE Transactions on Pattern Analysis and Machine Intelligence
Urban Search and Rescue Robots: From Tragedy to Technology

IEEE Intelligent Systems
Practical Reinforcement Learning in Continuous Spaces

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Learning the Visuomotor Coordination of a Mobile Robot by Using the Invertible Kohonen Map

IWANN '96 Proceedings of the International Workshop on Artificial Neural Networks: From Natural to Artificial Neural Computation
Applications of the self-organising map to reinforcement learning

Neural Networks - New developments in self-organizing maps
Combining diverse neural nets

The Knowledge Engineering Review
Constructive Incremental Learning from Only Local Information

Neural Computation
Learning and generalization in cascade network architectures

Neural Computation
Task allocation via self-organizing swarm coalitions in distributed mobile sensor network

AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Hierarchical reinforcement learning with the MAXQ value function decomposition

Journal of Artificial Intelligence Research
Reinforcement learning: a survey

Journal of Artificial Intelligence Research
Action selection for single- and multi-robot tasks using cooperative extended Kohonen maps

IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
Growing radial basis neural networks: merging supervised and unsupervised learning with network growth techniques

IEEE Transactions on Neural Networks
Reformulated radial basis neural networks trained by gradient descent

IEEE Transactions on Neural Networks

Real-time robot path planning based on a modified pulse-coupled neural network model

IEEE Transactions on Neural Networks
Multi-dimensional representations of laparoscopic simulations for SANETs

EUROCAST'11 Proceedings of the 13th international conference on Computer Aided Systems Theory - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

Self-organizing feature maps such as extended Kohonen maps (EKMs) have been very successful at learning sensorimotor control for mobile robot tasks. This letter presents a new ensemble approach, cooperative EKMs with indirect mapping, to achieve complex robot motion. An indirect-mapping EKM self-organizes to map from the sensory input space to the motor control space indirectly via a control parameter space. Quantitative evaluation reveals that indirect mapping can provide finer, smoother, and more efficient motion control than does direct mapping by operating in a continuous, rather than discrete, motor control space. It is also shown to outperform basis function neural networks. Furthermore, training its control parameters with recursive least squares enables faster convergence and better performance compared to gradient descent. The cooperation and competition of multiple self-organized EKMs allow a nonholonomic mobile robot to negotiate unforeseen, concave, closely spaced, and dynamic obstacles. Qualitative and quantitative comparisons with neural network ensembles employing weighted sum reveal that our method can achieve more sophisticated motion tasks even though the weighted-sum ensemble approach also operates in continuous motor control space.