Multi-method learning and assimilation

Authors:
Shinya Takamuku;Ronald C. Arkin
Affiliations:
Department of Adaptive Machine Systems, Graduate School of Engineering, Osaka University, 2-1 Yamadaoka, Suita, Osaka, 565-0871, Japan;Mobile Robot Laboratory and GVU Center, College of Computing, Georgia Institute of Technology, Atlanta, GA, USA
Venue:
Robotics and Autonomous Systems
Year:
2007

Citing 6
Cited 1

Multitask Learning

Machine Learning - Special issue on inductive transfer
An open architecture for robot entertainment

AGENTS '97 Proceedings of the first international conference on Autonomous agents
An Behavior-based Robotics

An Behavior-based Robotics
Reinforcement Learning

Reinforcement Learning
Development of an Autonomous Quadruped Robot for Robot Entertainment

Autonomous Robots - Special issue on autonomous agents
No free lunch theorems for optimization

IEEE Transactions on Evolutionary Computation

Validation of an algorithm for dynamically diagnosing learning progress and innovation performance at real-time base

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

Considering the wide range of possible behaviours to be acquired for domestic robots, applying a single learning method is clearly insufficient. In this paper, we propose a new strategy for behaviour acquisition for domestic robots where the behaviours are acquired using multiple differing learning methods that are subsequently incorporated into a common behaviour selection system, enabling them to be performed in appropriate situations. An example of the implementation of this strategy applied to the entertainment humanoid robot QRIO is introduced and the results are discussed.