Biomimetic Neural Learning for Intelligent Robots: Intelligent Systems, Cognitive Robotics, and NeuroscienceStefan Wermter, Günther Palm, Mark Elshaw This book presents research performed as part of the EU project on biomimetic multimodal learning in a mirror neuron-based robot (MirrorBot) and contri- tions presented at the International AI-Workshop on NeuroBotics. The ov- all aim of the book is to present a broad spectrum of current research into biomimetic neural learning for intelligent autonomous robots. There is a need for a new type of robot which is inspired by nature and so performs in a more ?exible learned manner than current robots. This new type of robot is driven by recent new theories and experiments in neuroscience indicating that a biological and neuroscience-oriented approach could lead to new life-like robotic systems. The book focuses on some of the research progress made in the MirrorBot project which uses concepts from mirror neurons as a basis for the integration of vision, language and action. In this book we show the development of new techniques using cell assemblies, associative neural networks, and Hebbian-type learning in order to associate vision, language and motor concepts. We have developed biomimetic multimodal learning and language instruction in a robot to investigate the task ofsearching for objects. As well as the researchperformed in this area for the MirrorBot project, the second part of this book incorporates signi?cant contributions from other research in the ?eld of biomimetic robotics. This second part of the book concentrates on the progress made in neuroscience inspired robotic learning approaches (in short: NeuroBotics). |
Contents
Towards Biomimetic Neural Learning for Intelligent Robots | 1 |
The Intentional Attunement Hypothesis The Mirror Neuron System | 16 |
Sequence Detector Networks and Associative Learning of Grammatical | 31 |
A Distributed Model of Spatial Visual Attention | 54 |
A Hybrid Architecture Using CrossCorrelation and Recurrent Neural | 73 |
Image Invariant Robot Navigation Based on Self Organising Neural | 88 |
Detecting Sequences and Understanding Language with Neural | 107 |
Towards Word Semantics from Multimodal AcousticoMotor | 144 |
Biomimetic Cognitive Behaviour in Robots | 211 |
Experiments with FourLegged | 225 |
Spatial Representation and Navigation in a Bioinspired Robot | 245 |
Combining Distributed | 265 |
An Anthropomorphic Arm with Bioinspired Control | 281 |
LARP Biped Robotics Conceived as Human Modelling | 299 |
The Driving Force in Early Stage Learning | 315 |
Modular Learning Schemes for Visual Robot Control | 333 |
Grounding Neural Robot Language in Action | 162 |
A Spiking Neural Network Model of Multimodal Language Processing | 182 |
A Scale Invariant Local Image Descriptor for Visual Homing | 362 |
Other editions - View all
Biomimetic Neural Learning for Intelligent Robots: Intelligent Systems ... Stefan Wermter,Günther Palm,Mark Elshaw No preview available - 2005 |
Biomimetic Neural Learning for Intelligent Robots: Intelligent Systems ... Stefan Wermter,Günther Palm,Mark Elshaw No preview available - 2005 |
Common terms and phrases
action activation actuator agent algorithm allows angle approach architecture areas artificial assemblies associative attention behaviour biological brain cells cluster cognitive color complex computational connections consists corresponding cortex cortical described different direction distributed environment error estimation example experiments field figure first function given goal hierarchical human implemented input instruction interest internal joint landmarks language layer learning means mechanism memory method mirror neurons module motor movement navigation neural networks nodes object observed output pattern performed place cells population position possible presented Press problem processing receives recognition regions represent representation respectively response robot Science sensory sequence shows signals similar simple simulation single sound space step structure studies task units vector vision visual weights