Developmental learning of internal models for robotics
Author(s)
Dearden, Anthony
Type
Thesis
Abstract
Abstract: Robots that operate in human environments can learn motor skills asocially, from selfexploration, or socially, from imitating their peers. A robot capable of doing both can be more ~daptiveand autonomous. Learning by imitation, however, requires the ability to understand the actions ofothers in terms ofyour own motor system: this information can come from a robot's own exploration. This thesis investigates the minimal requirements for a robotic system than learns from both self-exploration and imitation of others. .Through self.exploration and computer vision techniques, a robot can develop forward 'models: internal mo'dels of its own motor system that enable it to predict the consequences of its actions. Multiple forward models are learnt that give the robot a distributed, causal representation of its motor system. It is demon~trated how a controlled increase in the complexity of these forward models speeds up the robot's learning. The robot can determine the uncertainty of its forward models, enabling it to explore so as to improve the accuracy of its???????predictions. Paying attention fO the forward models according to how their uncertainty is changing leads to a development in the robot's exploration: its interventions focus on increasingly difficult situations, adapting to the complexity of its motor system. A robot can invert forward models, creating inverse models, in order to estimate the actions that will achieve a desired goal. Switching to socialleaming. the robot uses these inverse model~ to imitate both a demonstrator's gestures and the underlying goals of their movement.
Date Issued
2008-01
Copyright Statement
Attribution NoDerivatives 4.0 International Licence (CC BY-ND)
Creator
Dearden, Anthony
Publisher Institution
Imperial College London (University of London)
Qualification Level
Doctoral
Qualification Name
Doctor of Philosophy (PhD)