Learning Multiple Goal-Directed Actions Through Self-Organization of a Dynamic Neural Network Model: A Humanoid Robot Experiment

Authors:
Ryunosuke Nishimoto;Jun Namikawa;Jun Tani
Affiliations:
Brain Science Institute, RIKEN, Saitama, Japan;Brain Science Institute, RIKEN, Saitama, Japan;Brain Science Institute, RIKEN, Saitama, Japan
Venue:
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Year:
2008

Citing 13
Cited 3

Real-time obstacle avoidance for manipulators and mobile robots

International Journal of Robotics Research
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Learning goal-directed sensory-based navigation of a mobile robot

Neural Networks
A dynamical systems perspective on agent-environment interaction

Artificial Intelligence - Special volume on computational research on interaction and agency, part 1
Multiple paired forward and inverse models for motor control

Neural Networks - Special issue on neural control and robotics: biology and technology
Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems

Neural Networks - Special issue on organisation of computation in brain-like systems
Imitation as a dual-route process featuring predictive and learning components: a biologically plausible computational model

Imitation in animals and artifacts
Learning to generate articulated behavior through the bottom-up and the top-down interaction processes

Neural Networks
Learning to generate combinatorial action sequences utilizing the initial sensitivity of deterministic dynamical systems

Neural Networks
Self-organization of distributedly represented multiple behavior schemata in a mirror system: reviews of robot experiments using RNNPB

Neural Networks - 2004 Special issue: New developments in self-organizing systems
A learning algorithm for continually running fully recurrent neural networks

Neural Computation
Model-based learning for mobile robot navigation from the dynamicalsystems perspective

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Self-organization of behavioral primitives as multiple attractor dynamics: A robot experiment

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans

2008 Special Issue: Achieving "organic compositionality" through self-organization: Reviews on brain-inspired robotics experiments

Neural Networks
Integrative learning between language and action: a neuro-robotics experiment

ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part II
Imitating others by composition of primitive actions: A neuro-dynamic model

Robotics and Autonomous Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

We introduce a model that accounts for cognitive mechanisms oflearning and generating multiple goal-directed actions. The modelemploys the novel idea of the so-called "sensory forward model,"which is assumed to function in inferior parietal cortex for thegeneration of skilled behaviors in humans and monkeys. A set ofdifferent goal-directed actions can be generated by the sensoryforward model by utilizing the initial sensitivity characteristicsof its acquired forward dynamics. The analyses on our roboticsexperiments show qualitatively how generalization in learning canbe achieved for situational variances, and how the top-downintention toward a specific goal state can reconcile with thebottom-up sensation from reality.