Multiple abstraction hierarchies for mobile robot operation in large environments / Cipriano Galindo, Juan-Antonio Fernández-Madrigal, Javier González.

Format:

Book

Author/Creator:

Galindo, Cipriano, 1977-

Contributor:

Fernández-Madrigal, Juan-Antonio, 1970-

González, Javier (González Jiménez)

Series:

Studies in computational intelligence ; 68.

Studies in computational intelligence ; 68

Language:

English

Subjects (All):

Mobile robots.

Physical Description:

xv, 178 pages : illustrations ; 24 cm.

Place of Publication:

Berlin ; New York : Springer, [2007]

Summary:

This book focuses on the efficient performance of mobile robots through the use of multi-hierarchical symbolic representations of the environment. A mobile robot intended to perform deliberative actions must possess some symbolic representation of its workspace, but such representations of real environments usually become so large that should be conveniently arranged in order to facilitate and, in some cases, make possible their use.

Apart from the drawback of dealing with large amounts of information, other problems stand out when using symbolic representations. One is keeping the model properly optimized with respect to the robot tasks while maintaining it coherent with reality. Another one is the creation (or modification) of symbols from sensorial data. This book addresses all these issues considering symbolic multi-hierarchical structures. Such structures, based on the concept of abstraction, allow a robot to speed up its operation in large environments. Practical solutions tested on real robots (for instance, a robotic wheelchair for elder people) are provided. The book is intended for PhD students and in general for robotics, computer science, and artificial intelligence researchers.

Contents:

1 A Robotic Future 1

1.1 Why is it Not Real? 2

1.2 Making it Possible 5

2 Multi-Hierarchical, Symbolic Representation of the Environment 9

2.2 Informal Description of a Multi-Hierarchical Model Based on Graphs 13

2.2.1 What is an AH-Graph? 13

2.2.2 What is a Multi-AH-Graph? 14

2.3 Formalization of Graphs 15

2.4 Formalization of Graph Abstraction 18

2.5 Category Theory for Abstraction and Refinement of Graphs 20

2.5.1 The Category of Graphs with Abstraction 20

2.5.2 The Category of Graphs with Refinements 25

3 Application of Hierarchical Models to Mobile Robot Task Planning 29

3.2 Formalization of Classical Planning in Category Theory 33

3.2.1 Planning Basics 34

3.2.2 The Category of Planning States with Abstraction 35

3.2.3 Functors Between the AGraph and the AState Categories 37

3.2.4 Hierarchical Planning with CV AGraph and AState 42

3.3 Hierarchical Planning Through Plan Guidance 47

3.4 Hierarchical Planning Through Action Guidance 54

3.5 Anomalies in Hierarchical Planning 57

3.6 Experimental Results 58

4 Mobile Robot Operation with Multi-Hierarchies 65

4.2 A Multi-Hierarchical World Model for a Mobile Robot 68

4.2.1 Task-Planning Hierarchies 68

4.2.2 Localization Hierarchy 69

4.2.3 Cognitive Hierarchy 71

4.3 The Utility of the Multi-Hierarchical Model for Human-Robot Interaction 73

4.3.1 The Inter-Hierarchy Translation Process 75

4.3.2 Interactive Task-Planning 77

5 Automatic Learning of Hierarchical Models 85

5.2 The ELVIRA Framework 88

5.3 Model Creation/Maintenance 89

5.3.1 Human-Assisted Symbolic Modeling 90

5.3.2 Perceptual Anchoring 91

5.4 Model Optimization 95

5.4.1 Evolutionary Hierarchy Optimizer 96

5.4.2 Population 97

5.4.3 Individual Recombination 99

5.4.4 Individual Mutation 101

5.4.5 Individual Evaluation 104

5.4.6 Memory and Time Consumption 105

5.5 Experimental Results 107

5.5.1 Real Evaluation 107

5.5.2 Simulated Experiments 111

5.5.3 Considerations for Outdoor or Dynamic Environments 113

6 Implementation and Experiences on a Real Robot 115

6.2 Related Works on Human-Robot Interaction 119

6.3 Overview of the ACRHIN Architecture 120

6.4 The Deliberative Level 123

6.4.1 Symbolic Management 123

6.4.2 Task Manager 126

6.5 The Executive Level 126

6.5.1 Alert System 127

6.5.2 Plan Executor and Alert Manager (PLEXAM) 129

6.6 The Functional Level 129

6.7 Experiences on the SENA Robotic Wheelchair 131

6.7.1 The SENA Robotic Wheelchair 131

6.7.2 Software Details 134

6.7.3 Experiences on SENA 135

A Mathematical Demonstrations for the Formalization of the Graph Category 145

A.1 Composition of Abstractions in AGraph is an Abstraction 145

A.2 Composition of Abstractions in AGraph is Associative 148

A.3 Composition and Identity of Abstractions in AGraph 149

A.4 Composition of Refinements in RGraph is a Refinement 150

A.5 Composition of Refinements in RGraph is Associative 153

A.6 Composition and Identity of Refinements in RGraph 154

B Demonstration that [Psi] is a Functor from CAVGraph to AState 157

B.1 [Psi] Preserves Identity 157

B.2 [Psi] Preserves Composition of Arrows 158

C Planning Domain 161.

Notes:

Includes bibliographical references (pages [167]-175) and index.

ISBN:

3540726888

9783540726883

OCLC:

164688620