Muutke küpsiste eelistusi

E-raamat: Visual Neuroscience of Robotic Grasping: Achieving Sensorimotor Skills through Dorsal-Ventral Stream Integration

  • Formaat: PDF+DRM
  • Sari: Cognitive Systems Monographs 28
  • Ilmumisaeg: 19-Jun-2015
  • Kirjastus: Springer International Publishing AG
  • Keel: eng
  • ISBN-13: 9783319203034
  • Formaat - PDF+DRM
  • Hind: 110,53 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
  • Formaat: PDF+DRM
  • Sari: Cognitive Systems Monographs 28
  • Ilmumisaeg: 19-Jun-2015
  • Kirjastus: Springer International Publishing AG
  • Keel: eng
  • ISBN-13: 9783319203034

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

This book presents interdisciplinary research that pursues the mutual enrichment of neuroscience and robotics. Building on experimental work, and on the wealth of literature regarding the two cortical pathways of visual processing - the dorsal and ventral streams - we define and implement, computationally and on a real robot, a functional model of the brain areas involved in vision-based grasping actions.
Grasping in robotics is largely an unsolved problem, and we show how the bio-inspired approach is successful in dealing with some fundamental issues of the task. Our robotic system can safely perform grasping actions on different unmodeled objects, denoting especially reliable visual and visuomotor skills.
The computational model and the robotic experiments help in validating theories on the mechanisms employed by the brain areas more directly involved in grasping actions. This book offers new insights and research hypotheses regarding such mechanisms, especially for what concerns the interaction between the dorsal and ventral streams. Moreover, it helps in establishing a common research framework for neuroscientists and roboticists regarding research on brain functions.
1 Introduction
1(6)
Reference
5(2)
2 The Neuroscience of Action and Perception
7(32)
2.1 The Two Cortical Streams of Visual Elaboration, Fundamental Roles and Proofs of Dissociation
7(5)
2.1.1 A Dual Mechanism for Vision
9(2)
2.1.2 Brain Pathways for Vision-Based Grasping
11(1)
2.2 Visual Areas and Stream Separation
12(2)
2.3 The Action-Oriented Dorsal Stream
14(10)
2.3.1 Posterior Intraparietal Sulcus
15(3)
2.3.2 Anterior Intraparietal Sulcus
18(3)
2.3.3 Ventral Premotor Cortex (PMv) and Other Motor Areas
21(1)
2.3.4 Other Dorsal Stream Areas
22(2)
2.4 Object Recognition and Stream Integration
24(3)
2.4.1 The Lateral Occipital Complex
24(1)
2.4.2 Other Brain Areas Involved in Grasping
25(1)
2.4.3 The Visual Streams in Action
26(1)
2.5 The Third Stream of Visual Processing
27(12)
References
28(11)
3 Intelligent Robotic Grasping?
39(18)
3.1 Vision-Based Robotic Grasping, A Brief Outline
39(3)
3.2 Biological Inspiration for Robot Grasping and Manipulation
42(2)
3.3 Symbol Grounding Through Robotic Manipulation
44(7)
3.3.1 Symbol Grounding and Neuroscience
44(1)
3.3.2 An Emerging Categorization of Synthesized Robot Grips
45(2)
3.3.3 Extracting Symbolic Meanings from Physical Interactions
47(3)
3.3.4 Symbolic Value of Hand-Object Interactions
50(1)
3.4 Toward Intelligent Robotic Grasping
51(6)
References
52(5)
4 Vision-Based Grasping, Where Robotics Meets Neuroscience
57(26)
4.1 Previous Models and Related Approaches
57(5)
4.2 Basic Modeling Concepts
62(6)
4.2.1 Methodological Issues
62(1)
4.2.2 Object, Hand, Task
63(4)
4.2.3 Role of the Dorsal and Ventral Streams and Possible Interactions
67(1)
4.3 Model Framework
68(8)
4.3.1 Processing of Basic Visual Information
70(1)
4.3.2 Extraction of Visual Features Suitable for Grasping
70(2)
4.3.3 Transformation of Visual Features into Hand Shapes
72(3)
4.3.4 Grasp Execution
75(1)
4.4 Conclusions
76(7)
References
77(6)
5 Extraction of Grasp-Related Visual Features
83(36)
5.1 Extraction and Integration of Object-Related Visual Cues in the Primate Cortex and in Robotics
84(5)
5.1.1 Feature Extraction
85(1)
5.1.2 Cue Integration
86(1)
5.1.3 Object Recognition in the Ventral Stream
87(1)
5.1.4 Orientation Estimation in Artificial Vision and Robotics
88(1)
5.2 A Model of Distance and Orientation Estimation of Graspable Objects
89(7)
5.2.1 Distance Estimation Through Proprioceptive Data
89(1)
5.2.2 Object Orientation Estimation Through Retinal Data
90(5)
5.2.3 Hierarchical Object Classification
95(1)
5.3 Neural Network Implementation of a Multiple Cue Slant Estimator
96(3)
5.3.1 Neural Network Estimators
96(1)
5.3.2 Merging the Estimators
96(1)
5.3.3 Results of the ANN Simulation
97(2)
5.4 Robotic Validation
99(15)
5.4.1 Robotic Setup
101(2)
5.4.2 Object Classification Experiments
103(2)
5.4.3 Object Pose and Distance Estimation
105(5)
5.4.4 Experimental Results
110(4)
5.5 Conclusions
114(5)
References
115(4)
6 Visuomotor Transformations for Grasp Planning and Execution
119(26)
6.1 Neural Coding in the Caudal Intraparietal Sulcus
119(10)
6.1.1 Understanding and Interpreting the Available Data
121(2)
6.1.2 SOS Neurons Transfer Function
123(2)
6.1.3 AOS Neurons Transfer Function
125(2)
6.1.4 Robotic SOS and AOS
127(2)
6.1.5 Discussion and Future Developments
129(1)
6.2 Planning and Executing the Grasping Action
129(13)
6.2.1 Characteristics of the Visual Input to AIP
130(1)
6.2.2 The Search for Grasp Quality
131(3)
6.2.3 Grasp Planning
134(2)
6.2.4 Grasp Execution
136(6)
6.3 Conclusions
142(3)
References
142(3)
7 An Ever-Developing Research Framework
145
7.1 Purely Visual and Visuomotor Transformations in AIP
145(5)
7.1.1 Visual-Visual Transformations
145(1)
7.1.2 Visuomotor Transformations
146(2)
7.1.3 The Reaching and Grasping Action
148(1)
7.1.4 After Contact
149(1)
7.2 A Tighter Interaction Between the Streams
150(2)
7.2.1 Links Between CIP and the Ventral Stream
150(1)
7.2.2 Links Between AIP and the Ventral Stream
151(1)
7.3 fRI, Functional Robotic Imaging: Visualizing a Robot Brain
152(6)
7.3.1 Modeling Requirements
153(1)
7.3.2 The fRI Interface
154(1)
7.3.3 Reproducing and Predicting Experiments
155(1)
7.3.4 fRI of the Posterior Parietal Cortex
156(1)
7.3.5 The Brain-Damaged Robot
157(1)
7.4 Further Extensions
158(2)
7.4.1 Temporal Coordination
158(1)
7.4.2 Tools
159(1)
7.4.3 Grasping Force
159(1)
7.4.4 Illusions
160(1)
7.5 Conclusions
160
References
161