Minimalist Mobile Robotics

Rather than using traditional artificial intelligence techniques, which are ineffective when applied to the complexities of real-world robot navigaiton, Connell describes a methodology of reconstructing intelligent robots with distributed, multiagent control systems. After presenting this methodology, hte author describes a complex, robust, and successful application-a mobile robot "can collection machine" which operates in an unmodified offifce environment occupied by moving people.

Foreword

Preface

1. Introduction

1.1 The Task

1.2 Animal Stories

1.3 Design Principles

1.4 Contributions

1.5 Roadmap

2. Architecture

2.1 What we Use

2.2 The Subsumption Architecture

2.3 The Multiprocessor Implementation

2.4 Related Architectures

3. Manipulation

3.1 Hardware

3.2 Sensors

3.3 Controlling the Hand

3.4 Controlling the Arm Locally

3.5 Controlling the Arm Globally

3.6 Controlling the Base

3.7 Experiments

4. Vision

4.1 Hardware

4.2 Image Processing

4.3 Visual Guidance

4.4 Experiments

5. Navigation

5.1 Sensors

5.2 Tactical Navigation

5.3 Strategic Navigation

5.4 Experiments

6. Discussion

6.1 Spatial Representation

6.2 Distributed Systems

6.3 Limitations

6.4 Extending Arbitration

6.5 Learning

6.6 Conclusion

Bibliography

Index