Learning to generate articulated behavior through the bottom-up and the top-down interaction processes

Authors:
Jun Tani
Affiliations:
Brain Science Institute, RIKEN, 2-1 Hirosawa, Wako-shi, Saitama 351-0198, Japan
Venue:
Neural Networks
Year:
2003

Citing 8
Cited 25

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Original Contribution: Recognition of manipulated objects by motor learning with modular architecture networks

Neural Networks
Long short-term memory

Neural Computation
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
MOSAIC Model for Sensorimotor Learning and Control

Neural Computation
Annealed competition of experts for a segmentation and classification of switching dynamics

Neural Computation
Incremental learning of complex temporal patterns

IEEE Transactions on Neural Networks

Learning Semantic Combinatoriality from the Interaction between Linguistic and Behavioral Processes

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
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
Motor primitive and sequence self-organization in a hierarchical recurrent neural network

Neural Networks - 2004 Special issue: New developments in self-organizing systems
2006 Special issue: Dynamic and interactive generation of object handling behaviors by a small humanoid robot using a dynamic neural network model

Neural Networks - 2006 Special issue: The brain mechanisms of imitation learning
On Cognition as Dynamical Coupling: An Analysis of Behavioral Attractor Dynamics

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Learning Multiple Goal-Directed Actions Through Self-Organization of a Dynamic Neural Network Model: A Humanoid Robot Experiment

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Coordinating with the Future: The Anticipatory Nature of Representation

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

Neural Networks
Schema-Based Design and the AKIRA Schema Language: An Overview

Anticipatory Behavior in Adaptive Learning Systems
An Intrinsic Neuromodulation Model for Realizing Anticipatory Behavior in Reaching Movement under Unexperienced Force Fields

Anticipatory Behavior in Adaptive Learning Systems
Building recurrent neural networks to implement multiple attractor dynamics using the gradient descent method

Advances in Artificial Neural Systems
The Cognitive Body: From Dynamic Modulation to Anticipation

Anticipatory Behavior in Adaptive Learning Systems
Autonomy of Self at Criticality: The Perspective from Synthetic Neuro-Robotics

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Intelligence Dynamics: a concept and preliminary experiments for open-ended learning agents

Autonomous Agents and Multi-Agent Systems
Spatio-temporal memories for machine learning: a long-term memory organization

IEEE Transactions on Neural Networks
Input space bifurcation manifolds of recurrent neural networks

Neurocomputing
An analysis of behavioral attractor dynamics

ECAL'07 Proceedings of the 9th European conference on Advances in artificial life
Anticipation and future-oriented capabilities in natural and artificial cognition

50 years of artificial intelligence
Taming the beast: guided self-organization of behavior in autonomous robots

SAB'10 Proceedings of the 11th international conference on Simulation of adaptive behavior: from animals to animats
Hierarchical behavior categorization using correlation based adaptive resonance theory

Neurocomputing
Dynamic generation and switching of object handling behaviors by a humanoid robot using a recurrent neural network model

SAB'06 Proceedings of the 9th international conference on From Animals to Animats: simulation of Adaptive Behavior
Imitating others by composition of primitive actions: A neuro-dynamic model

Robotics and Autonomous Systems
Simple and complex behavior learning using behavior hidden Markov model and CobART

Neurocomputing
On the Development of an Ants-Inspired Navigational Network for Autonomous Robots

International Journal of Intelligent Mechatronics and Robotics
Toward metabolic robotics: Insights from modeling embodied cognition in a biomechatronic symbiont1

Artificial Life

Quantified Score

Hi-index	0.00

Visualization

Abstract

A novel hierarchical neural network architecture for sensory-motor learning and behavior generation is proposed. Two levels of forward model neural networks are operated on different time scales while parametric interactions are allowed between the two network levels in the bottom-up and top-down directions. The models are examined through experiments of behavior learning and generation using a real robot arm equipped with a vision system. The results of the learning experiments showed that the behavioral patterns are learned by self-organizing the behavioral primitives in the lower level and combining the primitives sequentially in the higher level. The results contrast with prior work by Pawelzik et al. [Neural Comput. 8 (1996) 340], Tani and Nolfi [From animals to animats, 1998], and Wolpert and Kawato [Neural Networks 11 (1998) 1317] in that the primitives are represented in a distributed manner in the network in the present scheme whereas, in the prior work, the primitives were localized in specific modules in the network. Further experiments of on-line planning showed that the behavior could be generated robustly against a background of real world noise while the behavior plans could be modified flexibly in response to changes in the environment. It is concluded that the interaction between the bottom-up process of recalling the past and the top-down process of predicting the future enables both robust and flexible situated behavior.