Deep Learning for Robot Perception and Cognition

Deep Learning for Robot Perception and Cognition

1st Edition - February 4, 2022

Write a review

  • Editors: Alexandros Iosifidis, Anastasios Tefas
  • Paperback ISBN: 9780323857871
  • eBook ISBN: 9780323885720

Purchase options

Purchase options
Available
DRM-free (EPub, PDF)
Sales tax will be calculated at check-out

Institutional Subscription

Free Global Shipping
No minimum order

Description

Deep Learning for Robot Perception and Cognition introduces a broad range of topics and methods in deep learning for robot perception and cognition together with end-to-end methodologies. The book provides the conceptual and mathematical background needed for approaching a large number of robot perception and cognition tasks from an end-to-end learning point-of-view. The book is suitable for students, university and industry researchers and practitioners in Robotic Vision, Intelligent Control, Mechatronics, Deep Learning, Robotic Perception and Cognition tasks.

Key Features

  • Presents deep learning principles and methodologies
  • Explains the principles of applying end-to-end learning in robotics applications
  • Presents how to design and train deep learning models
  • Shows how to apply deep learning in robot vision tasks such as object recognition, image classification, video analysis, and more
  • Uses robotic simulation environments for training deep learning models
  • Applies deep learning methods for different tasks ranging from planning and navigation to biosignal analysis

Readership

Graduate students, university and industry researchers, practitioners in robot vision, Intelligent Control, and mechatronics

Table of Contents

  • Cover image
  • Title page
  • Table of Contents
  • Copyright
  • List of contributors
  • Preface
  • Acknowledgements
  • Editors biographies
  • Chapter 1: Introduction
  • Abstract
  • 1.1. Artificial intelligence and machine learning
  • 1.2. Real world problems representation
  • 1.3. Machine learning tasks
  • 1.4. Shallow and deep learning
  • 1.5. Robotics and deep learning
  • References
  • Chapter 2: Neural networks and backpropagation
  • Abstract
  • 2.1. Introduction
  • 2.2. Activation functions
  • 2.3. Cost functions
  • 2.4. Backpropagation
  • 2.5. Optimizers and training
  • 2.6. Overfitting
  • 2.7. Concluding remarks
  • References
  • Chapter 3: Convolutional neural networks
  • Abstract
  • 3.1. Introduction
  • 3.2. Structure of convolutional neural networks
  • 3.3. Training convolutional neural networks
  • 3.4. Conclusions
  • References
  • Chapter 4: Graph convolutional networks
  • Abstract
  • 4.1. Introduction
  • 4.2. Spectral graph convolutional network
  • 4.3. Spatial graph convolutional network
  • 4.4. Graph attention network (GAT)
  • 4.5. Graph convolutional networks for large graphs
  • 4.6. Datasets and libraries
  • 4.7. Conclusion
  • References
  • Chapter 5: Recurrent neural networks
  • Abstract
  • 5.1. Introduction
  • 5.2. Vanilla RNN
  • 5.3. Long-short term memory
  • 5.4. Gated recurrent unit
  • 5.5. Other RNN variants
  • 5.6. Applications
  • 5.7. Concluding remarks
  • References
  • Chapter 6: Deep reinforcement learning
  • Abstract
  • 6.1. Introduction
  • 6.2. Value-based methods
  • 6.3. Policy-based methods
  • 6.4. Concluding remarks
  • References
  • Chapter 7: Lightweight deep learning
  • Abstract
  • 7.1. Introduction
  • 7.2. Lightweight convolutional neural network architectures
  • 7.3. Regularization of lightweight convolutional neural networks
  • 7.4. Bag-of-features for improved representation learning
  • 7.5. Early exits for adaptive inference
  • 7.6. Concluding remarks
  • References
  • Chapter 8: Knowledge distillation
  • Abstract
  • 8.1. Introduction
  • 8.2. Neural network distillation
  • 8.3. Probabilistic knowledge transfer
  • 8.4. Multilayer knowledge distillation
  • 8.5. Teacher training strategies
  • 8.6. Concluding remarks
  • References
  • Chapter 9: Progressive and compressive learning
  • Abstract
  • 9.1. Introduction
  • 9.2. Progressive neural network learning
  • 9.3. Compressive learning
  • 9.4. Conclusions
  • References
  • Chapter 10: Representation learning and retrieval
  • Abstract
  • 10.1. Introduction
  • 10.2. Discriminative and self-supervised autoencoders
  • 10.3. Deep representation learning for content based image retrieval
  • 10.4. Model retraining methods for image retrieval
  • 10.5. Variance preserving supervised representation learning
  • 10.6. Concluding remarks
  • References
  • Chapter 11: Object detection and tracking
  • Abstract
  • 11.1. Object detection
  • 11.2. Object tracking
  • 11.3. Conclusion
  • References
  • Chapter 12: Semantic scene segmentation for robotics
  • Abstract
  • 12.1. Introduction
  • 12.2. Algorithms and architectures for semantic segmentation
  • 12.3. Loss functions for semantic segmentation
  • 12.4. Semantic segmentation using multiple inputs
  • 12.5. Semantic segmentation data sets and benchmarks
  • 12.6. Semantic segmentation metrics
  • 12.7. Conclusion
  • References
  • Chapter 13: 3D object detection and tracking
  • Abstract
  • 13.1. Introduction
  • 13.2. 3D object detection
  • 13.3. 3D object tracking
  • 13.4. Conclusion
  • References
  • Chapter 14: Human activity recognition
  • Abstract
  • 14.1. Introduction
  • 14.2. Trimmed action recognition
  • 14.3. Temporal action localization
  • 14.4. Spatiotemporal action localization
  • 14.5. Data sets for human activity recognition
  • 14.6. Conclusion
  • References
  • Chapter 15: Deep learning for vision-based navigation in autonomous drone racing
  • Abstract
  • 15.1. Introduction
  • 15.2. System decomposition approach in drone racing navigation
  • 15.3. Transfer learning and end-to-end planning
  • 15.4. Useful tools for data collection and training
  • 15.5. Conclusions and future work
  • References
  • Chapter 16: Robotic grasping in agile production
  • Abstract
  • 16.1. Introduction
  • 16.2. Grasping and object manipulation
  • 16.3. Grasp evaluation
  • 16.4. Manipulation benchmarking
  • 16.5. Data sets
  • 16.6. Conclusion
  • References
  • Chapter 17: Deep learning in multiagent systems
  • Abstract
  • 17.1. Introduction
  • 17.2. Setting the scene
  • 17.3. Challenges
  • 17.4. Deep learning in multiagent systems
  • 17.5. Conclusion
  • References
  • Chapter 18: Simulation environments
  • Abstract
  • 18.1. Introduction
  • 18.2. Robotic simulators
  • 18.3. Conclusions
  • References
  • Chapter 19: Biosignal time-series analysis
  • Abstract
  • 19.1. Introduction
  • 19.2. ECG classification and advance warning for arrhythmia
  • 19.3. Early prediction of mortality risk for COVID-19 patients
  • 19.4. Conclusion
  • References
  • Chapter 20: Medical image analysis
  • Abstract
  • 20.1. Introduction
  • 20.2. Early detection of myocardial infarction using echocardiography
  • 20.3. COVID-19 recognition from X-ray images via convolutional sparse support estimator based classifier
  • 20.4. Conclusion
  • References
  • Chapter 21: Deep learning for robotics examples using OpenDR
  • Abstract
  • 21.1. Introduction
  • 21.2. Structure of OpenDR toolkit and application examples
  • 21.3. Cointegration of simulation and training
  • 21.4. Concluding remarks
  • References
  • Index

Product details

  • No. of pages: 634
  • Language: English
  • Copyright: © Academic Press 2022
  • Published: February 4, 2022
  • Imprint: Academic Press
  • Paperback ISBN: 9780323857871
  • eBook ISBN: 9780323885720

About the Editors

Alexandros Iosifidis

Alexandros Iosifidis is a Professor at Aarhus University, Denmark. He leads the Machine Learning and Computational Intelligence group at the Department of Electrical and Computer Engineering. He received his Ph.D. from the Department of Informatics at Aristotle University of Thessaloniki, Greece in 2014. He participated in more than 15 research and development projects financed by national and European funds.

Affiliations and Expertise

Aarhus University, Denmark

Anastasios Tefas

Anastasios Tefas received the B.Sc. in Informatics in 1997 and the Ph.D. degree in Informatics in 2002, both from the Aristotle University of Thessaloniki, Greece. Since 2017, he has been an Associate Professor at the Department of Informatics, Aristotle University of Thessaloniki. Dr. Tefas participated in 20 research projects financed by national and European funds. He is the coordinator of the H2020 project OpenDR, “Open Deep Learning Toolkit for Robotics.”

Affiliations and Expertise

Department of Informatics, Aristotle University of Thessaloniki

Ratings and Reviews

Write a review

There are currently no reviews for "Deep Learning for Robot Perception and Cognition"