Neural Systems for Robotics

by Omidvar; Smagt

• ISBN13: 9780125262804
• ISBN10: 0125262809
• Format: Hardcover
• Copyright: 1997-04-10
• Publisher: Elsevier Science

Summary

Neural Systems for Robotics represents the most up-to-date developments in the rapidly growing aplication area of neural networks, which is one of the hottest application areas for neural networks technology. The book not only contains a comprehensive study of neurocontrollers in complex Robotics systems, written by highly respected researchers in the field but outlines a novel approach to solving Robotics problems. The importance of neural networks in all aspects of Robot arm manipulators, neurocontrol, and Robotic systems is also given thorough and in-depth coverage. All researchers and students dealing with Robotics will find Neural Systems for Robotics of immense interest and assistance. Key Features * Focuses on the use of neural networks in robotics-one of the hottest application areas for neural networks technology * Represents the most up-to-date developments in this rapidly growing application area of neural networks * Contains a new and novel approach to solving Robotics problems

Table of Contents

Contributors	ix	(6)
Preface	xv
1 Neural Network Sonar as a Perceptual Modality for Robotics	1	(16)
Itiel E. Dror
Mark Zagaeski
Damien Rios
Cynthia F. Moss
1.1 Use of Sonar in Robotics	1	(1)
1.2 Echolocating Bats	2	(1)
1.3 Neural Network Models of Biosonar	3	(3)
1.4 A Neural Network That Recognizes Speed of Movement	6	(5)
1.5 Conclusion	11	(6)
2 Dynamic Balance of a Biped Walking Robot	17	(20)
W. Thomas Miller III
Andrew L. Kun
2.1 Introduction	17	(2)
2.2 Background	19	(2)
2.3 Methods	21	(7)
2.4 Results	28	(3)
2.5 Conclusion	31	(6)
3 Visual Feedback in Motion	37	(38)
Patrick van der Smagt
Frans Groen
3.1 Introduction	37	(2)
3.2 The Trajectory of an Eye-in-Hand System	39	(4)
3.3 The Time-Independent Constraints	43	(3)
3.4 The Time-Dependent Constraints	46	(7)
3.5 Visual Measurement of the Stopping Criteria	53	(3)
3.6 Controlling the Manipulator	56	(6)
3.7 Results	62	(4)
3.8 Discussion	66	(2)
3.A Derivation of the Stopping Criteria	68	(2)
3.B Proof of Theorem 3.2	70	(1)
3.C Nonlinear Transform of a Noisy Signal	71	(4)
4 Inverse Kinematics of Dextrous Manipulators	75	(42)
David DeMers
Kenneth Kreutz-Delgado
4.1 Introduction	75	(2)
4.2 Kinematics	77	(18)
4.3 Solving the Inverse Kinematics Problem--A Survey	95	(9)
4.4 Exploiting Global Topological Knowledge to Solve the Inverse Kinematics Problem	104	(5)
4.5 Future Research Directions	109	(1)
4.6 Conclusion	110	(7)
5 Stable Manipulator Trajectory Control Using Neural Networks	117	(36)
Yichuang Jin
Tony Pipe
Alan Winfield
5.1 Introduction	117	(3)
5.2 Neural Networks	120	(1)
5.3 Methodology	121	(2)
5.4 Neural Network Offline Learning	123	(1)
5.5 Control Structure and Neural Network Online Learning Algorithm--Method 1	124	(9)
5.6 Control Structure and Neural Network Online Learning Algorithm--Method 2	133	(3)
5.7 Discussions of Online and Offline Learning	136	(4)
5.8 Applications in a PUMA Robot	140	(4)
5.9 Conclusion	144	(1)
5.A Proof of Theorem 5.4	145	(1)
5.B Proof of Theorem 5.5	146	(1)
5.C Proof of Theorem 5.6	147	(1)
5.D Proof of Theorem 5.7	148	(5)
6 The Neural Dynamics Approach to Sensory-Motor Control	153	(42)
Paolo Gaudiano
Frank H. Guenther
Eduardo Zalama
6.1 Introduction	154	(1)
6.2 Neural Models of Biological Motor Control	155	(15)
6.3 Unsupervised Control of a Mobile Robot	170	(11)
6.4 The DIVA Model of Speech Production	181	(7)
6.5 Conclusion	188	(7)
7 Operant Conditioning in Robots	195	(32)
Andreas Biihlmeier
Gerhard Manteuffel
7.1 Introduction	195	(2)
7.2 Mobile Robots, AI, and Conditioning	197	(1)
7.3 Neural Models of Conditioning	198	(6)
7.4 Conditioning Models and Robot Control	204	(2)
7.5 Implemetation in Robots	206	(14)
7.6 Discussion	220	(7)
8 A Dynamic Net for Robot Control	227	(44)
Bridget Hallam
John Hallam
Gillian Hayes
8.1 Introduction	227	(1)
8.2 Background	228	(3)
8.3 The Neuro-Connector Model of Learning and Motivation	231	(11)
8.4 The Net in Operation	242	(6)
8.5 Implementation on a Mobile Robot	248	(5)
8.6 Simulation Experiments	253	(6)
8.7 The Appropriateness of Using the Neuro-Connector Model as a Robot Controller	259	(4)
8.8 Conclusion	263	(2)
8.A Sensory Conditions	265	(1)
8.B Behaviors	265	(1)
8.C Sensory Neuron Parameters	266	(1)
8.D Releaser Neuron Parameters	266	(1)
8.E Behavior Neuron Parameters	266	(1)
8.F Synaptic Parameters	267	(4)
9 Neural Vehicles	271	(26)
Ben Krose
Joris van Dam
9.1 Introduction	271	(1)
9.2 Reactive Navigation	272	(9)
9.3 Planned Navigation in Known Environments	281	(7)
9.4 Map Building	288	(4)
9.5 Conclusion	292	(5)
10 Self-Organization and Autonomous Robots	297	(42)
Jukka Heikkonen
Pasi Koikkalainen
10.1 Introduction	297	(1)
10.2 Hypothesis	298	(2)
10.3 AI and Autonomous Robots	300	(2)
10.4 Realizations of Action-Oriented Systems	302	(2)
10.5 Learning Robots and Neural Networks	304	(2)
10.6 The Role of Self-Organization	306	(1)
10.7 From Situations to Actions: A General Concept	307	(1)
10.8 The Self-Organizing Map	307	(4)
10.9 The Simulated Robot	311	(1)
10.10 Case 1: Separate Training Environment	312	(6)
10.11 Case 2: Self-Exploring Robot	318	(4)
10.12 Case 3: Visually Guided Robot	322	(7)
10.13 Related Work	329	(2)
10.14 Conclusion	331	(8)
Index	339