Cover image for Spatial temporal patterns for action-oriented perception in roving robots
Title:
Spatial temporal patterns for action-oriented perception in roving robots
Series:
Cognitive systems monographs ; 1
Publication Information:
Berlin : Springer, 2009
Physical Description:
xx, 424 p. : ill. (some col.) ; 25 cm.
ISBN:
9783540884637

Available:*

Library
Item Barcode
Call Number
Material Type
Item Category 1
Status
Searching...
30000010193938 TJ211.3 S62 2009 Open Access Book Book
Searching...

On Order

Summary

Summary

The basic principles guiding sensing, perception and action in bio systems seem to rely on highly organised spatial-temporal dynamics. In fact, all biological senses, (visual, hearing, tactile, etc.) process signals coming from different parts distributed in space and also show a complex time evolution. As an example, mammalian retina performs a parallel representation of the visual world embodied into layers, each of which r- resents a particular detail of the scene. These results clearly state that visual perception starts at the level of the retina, and is not related uniquely to the higher brain centres. Although vision remains the most useful sense guiding usual actions, the other senses, ?rst of all hearing but also touch, become essential particularly in cluttered conditions, where visual percepts are somehow obscured by environment conditions. Ef?cient use of hearing can be learnt from acoustic perception in animals/insects, like crickets, that use this ancient sense more than all the others, to perform a vital function, like mating.


Table of Contents

B. Webb and J. WessnitzerH. Cruse and V. Dürr and M. Schilling and J. SchmitzB. Webb and J. Wessnitzer and H. Rosano and M. Szenher and M. Zampoglou and T. Haferlach and P. RussoH. Cruse and V. Dürr and M. Schilling and J. SchmitzM. G. Velarde and V. A. Makarov and N.P. Castellanos and Y.L. Song and D. LombardoP. Arena and S. De Fiore and M. Frasca and D. Lombardo and L. PatanéP. Arena and D. Lombardo and L. PatanéL. Alba and R. Domínguez Castro and F. Jiménez-Garrido and S. Espejo and S. Morillas and J. Listán and C. Utrera and A. García and Ma.D. Pardo and R. Romay and C. Mendoza and A. Jiménez and Á. Rodríguez-VázquezÁ. Zarándy and Cs. RekeczkyL. Alba and P. Arena and S. De Fiore and L. PatanéP. Arena and S. De Fiore and D. Lombardo and L. Patané
Part I Systems
1 Perception for Action in Insectsp. 3
1.1 Introductionp. 3
1.2 The Traditional Viewp. 3
1.3 Perception as Transformationp. 6
1.4 Closing the Loopp. 8
1.4.1 Active Perceptionp. 8
1.4.2 Dynamical Systems Theory and Perceptionp. 10
1.4.3 Dynamics and Networksp. 11
1.4.4 Further Bio-inspired Architectures for Perception-Actionp. 14
1.5 Predictive Loopsp. 16
1.6 Perception for Action in Insectsp. 17
1.7 Basic Physiology and the Central Nervous Systemp. 19
1.8 Higher Brain Centres in Insectsp. 21
1.8.1 The Mushroom Bodies (Corpora Pedunculata)p. 21
1.8.2 The Central Complexp. 27
1.9 Towards 'Insect Brain' Control Architecturesp. 30
1.10 Conclusionp. 33
Referencesp. 35
2 Principles of Insect Locomotionp. 43
2.1 Introductionp. 43
2.2 Biological Systemsp. 44
2.3 Sensorsp. 48
2.3.1 Mechanosensorsp. 49
2.3.2 Environmental Sensorsp. 51
2.4 Leg Controllerp. 52
2.4.1 Swing Movementp. 52
2.4.2 Stance Movementp. 57
2.5 Coordination of Different Legsp. 65
2.6 Insect Antennae as Models for Active Tactile Sensors in Legged Locomotionp. 75
2.7 Central Oscillatorsp. 78
2.8 Actuatorsp. 83
2.9 Conclusionp. 85
Referencesp. 86
3 Low Level Approaches to Cognitive Controlp. 97
3.1 Introductionp. 97
3.2 Sensory Systems and Simple Behavioursp. 98
3.2.1 Mechanosensory Systemsp. 98
3.2.2 Olfactory Systemsp. 100
3.2.3 Visual Systemsp. 102
3.2.4 Auditionp. 115
3.2.5 Audition and Visionp. 123
3.3 Navigationp. 129
3.3.1 Path Integrationp. 129
3.3.2 Visual Homingp. 137
3.3.3 Robot Implementation and Resultsp. 143
3.4 Learningp. 156
3.4.1 Neural Model and STDPp. 157
3.4.2 Non-elemental Associationsp. 158
3.4.3 Associating Auditory and Visual Cuesp. 163
3.5 Conclusionp. 166
Referencesp. 167
Part II Cognitive Models
4 A Bottom-Up Approach for Cognitive Controlp. 179
4.1 Introductionp. 180
4.2 Behavior-Based Approachesp. 181
4.3 A Bottom-Up Approach for Cognitive Controlp. 185
4.4 Representation by Situation Modelsp. 188
4.4.1 Basic Principles of Brain Functionp. 190
4.4.2 Recurrent Neural Networksp. 192
4.4.3 Memory Systemsp. 192
4.4.4 Recurrent Neural Networksp. 195
4.4.5 Applicationsp. 199
4.4.6 Learningp. 203
4.5 Towards Cognition, an Extension of Walknetp. 207
4.5.1 The Reactive and Adaptive Layerp. 208
4.5.2 Cognitive Levelp. 209
4.6 Conclusionsp. 215
Referencesp. 216
5 Mathematical Approach to Sensory Motor Control and Memoryp. 219
5.1 Theory of Recurrent Neural Networks Used to Form Situation Modelsp. 219
5.1.1 RNNs as a Part of a General Memory Structurep. 219
5.1.2 Input Compensation (IC) Units and RNNsp. 220
5.1.3 Learning Static Situationsp. 223
5.1.4 Dynamic Situations: Convergence of the Network Training Procedurep. 229
5.1.5 Dynamic Situations: Response of Trained IC-Unit Networks to a Novel External Stimulusp. 236
5.1.6 IC-Networks with Nonlinear Recurrent Couplingp. 242
5.1.7 Discussionp. 246
5.2 Probabilistic Target Searchingp. 249
5.2.1 Introductionp. 249
5.2.2 The Robot Probabilistic Sensory - Motor Layersp. 250
5.2.3 Obstacles, Path Complexity and the Robot IQ Testp. 253
5.2.4 First Neuron: Memory Skillp. 254
5.2.5 Second Neuron: Action Planningp. 257
5.2.6 Conclusionsp. 259
5.3 Memotaxis Versus Chemotaxisp. 260
5.3.1 Introductionp. 260
5.3.2 Robot Modelp. 261
5.3.3 Conclusionsp. 265
Referencesp. 266
6 From Low to High Level Approach to Cognitive Controlp. 269
6.1 Introductionp. 269
6.2 Weak Chaos Control for the Generation of Reflexive Behavioursp. 270
6.2.1 The Chaotic Multiscroll Systemp. 272
6.2.2 Control of the Multiscroll Systemp. 272
6.2.3 Multiscroll Control for Robot Navigation Controlp. 275
6.2.4 Robot Navigationp. 276
6.2.5 Simulation Resultsp. 278
6.3 Learning Anticipation in Spiking Networksp. 279
6.3.1 The Spiking Network Modelp. 281
6.3.2 Robot Simulation and Controller Structurep. 284
6.3.3 Spiking Network for Obstacle Avoidancep. 286
6.3.4 Spiking Network for Target Approachingp. 289
6.3.5 Navigation with Visual Cuesp. 293
6.4 Application to Landmark Navigationp. 295
6.4.1 The Spiking Network for Landmark Identificationp. 297
6.4.2 The Recurrent Neural Network for Landmark Navigationp. 298
6.4.3 Simulation Resultsp. 301
6.5 Conclusionsp. 305
Referencesp. 306
7 Complex Systems and Perceptionp. 309
7.1 Introductionp. 309
7.2 Reaction-Diffusion Cellular Nonlinear Networks and Perceptual Statesp. 311
7.3 The Representation Layerp. 312
7.3.1 The Preprocessing Blockp. 313
7.3.2 The Perception Blockp. 313
7.3.3 The Action Selection Network and the DRF Blockp. 320
7.3.4 Unsupervised Learning in the Preprocessing Blockp. 321
7.3.5 The Memory Blockp. 323
7.4 Strategy Implementation and Resultsp. 325
7.5 SPARK Cognitive Architecturep. 330
7.6 Behaviour Modulationp. 333
7.6.1 Basic Behaviorsp. 333
7.6.2 Representation Layerp. 334
7.7 Behaviour Modulation: Simulation Resultsp. 334
7.7.1 Simulation Setupp. 334
7.7.2 Learning Phasep. 336
7.7.3 Testing Phasep. 336
7.8 Conclusionsp. 337
Referencesp. 338
Appendix I CNNs and Turing patternsp. 340
Appendix II From Motor Maps to the Action Selection Networkp. 344
Part III Software/Hardware Cognitive Architecture and Experiments
8 New Visual Sensors and Processorsp. 351
8.1 Introductionp. 351
8.2 The Eye-RIS Vision System Conceptp. 353
8.3 The Retina-Like Front-End: From ACE Chips to Q-Eyep. 356
8.4 The Q-Eye Chipp. 358
8.5 Eye-RIS v1.1 Description (ACE16K Based)p. 362
8.5.1 Interruptsp. 364
8.6 Eye-RIS v1.2 Description (Q-Eye Based)p. 364
8.6.1 Digital Input/Output Portsp. 366
8.7 NIOS II Processorp. 367
8.7.1 NIOS II Processor Basicsp. 368
8.8 Conclusionp. 368
Referencesp. 368
9 Visual Algorithms for Cognitionp. 371
9.1 Global Displacement Calculationp. 371
9.2 Foreground-Background Separation Based Segmentationp. 374
9.2.1 Temporal Foreground-Background Separationp. 375
9.2.2 Spatial-Temporal Foreground-Background Separationp. 376
9.3 Active Contour Algorithmp. 377
9.4 Multi-target Trackingp. 380
9.5 Conclusionsp. 383
Referencesp. 383
10 SPARK Hardwarep. 385
10.1 Introductionp. 385
10.2 Multi-sensory Architecturep. 386
10.2.1 Spark Main Boardp. 387
10.2.2 Analog Sensory Boardp. 388
10.3 Sensory Systemp. 391
10.4 Conclusionp. 396
Referencesp. 397
11 Robotic Platforms and Experimentsp. 399
11.1 Introductionp. 399
11.2 Robotic Test Beds: Roving Robotsp. 400
11.2.1 Rover Ip. 400
11.2.2 Rover IIp. 402
11.3 Robotic Test Beds: Legged Robotsp. 402
11.3.1 MiniHexp. 402
11.3.2 Gregor IIIp. 404
11.4 Experiments and Resultsp. 405
11.4.1 Visual Homing and Hearing Targetingp. 405
11.4.2 Reflex-Based Locomotion Control with Sensory Fusionp. 408
11.4.3 Visual Perception and Target Followingp. 409
11.4.4 Reflex-Based Navigation Based on WCCp. 411
11.4.5 Learning Anticipation via Spiking Networksp. 413
11.4.6 Landmark Navigationp. 415
11.4.7 Turing Pattern Approach to Perceptionp. 416
11.4.8 Representation Layer for Behaviour Modulationp. 420
11.5 Conclusionp. 422
Referencesp. 422
Indexp. 423
Author Indexp. 425