book

Deep Learning for Robot Perception and Cognition

Name: Deep Learning for Robot Perception and Cognition
ISBN: 9780323885720

by Alexandros Iosifidis, Anastasios Tefas

February 2022

Beginner to intermediate

634 pages

22h 8m

English

Academic Press

Read now

Unlock full access

Cover image
Title page
Table of Contents
Copyright
List of contributors
Preface
Acknowledgements
Editors biographies
Chapter 1: Introduction
Abstract1.1. Artificial intelligence and machine learning1.2. Real world problems representation1.3. Machine learning tasks1.4. Shallow and deep learning1.5. Robotics and deep learningReferences
Chapter 2: Neural networks and backpropagation
Abstract2.1. Introduction2.2. Activation functions2.3. Cost functions2.4. Backpropagation2.5. Optimizers and training2.6. Overfitting2.7. Concluding remarksReferences

Chapter 3: Convolutional neural networks
Abstract3.1. Introduction3.2. Structure of convolutional neural networks3.3. Training convolutional neural networks3.4. ConclusionsReferences
Chapter 4: Graph convolutional networks
Abstract4.1. Introduction4.2. Spectral graph convolutional network4.3. Spatial graph convolutional network4.4. Graph attention network (GAT)4.5. Graph convolutional networks for large graphs4.6. Datasets and libraries4.7. ConclusionReferences
Chapter 5: Recurrent neural networks
Abstract5.1. Introduction5.2. Vanilla RNN5.3. Long-short term memory5.4. Gated recurrent unit5.5. Other RNN variants5.6. Applications5.7. Concluding remarksReferences
Chapter 6: Deep reinforcement learning
Abstract6.1. Introduction6.2. Value-based methods6.3. Policy-based methods6.4. Concluding remarksReferences
Chapter 7: Lightweight deep learning
Abstract7.1. Introduction7.2. Lightweight convolutional neural network architectures7.3. Regularization of lightweight convolutional neural networks7.4. Bag-of-features for improved representation learning7.5. Early exits for adaptive inference7.6. Concluding remarksReferences
Chapter 8: Knowledge distillation
Abstract8.1. Introduction8.2. Neural network distillation8.3. Probabilistic knowledge transfer8.4. Multilayer knowledge distillation8.5. Teacher training strategies8.6. Concluding remarksReferences
Chapter 9: Progressive and compressive learning
Abstract9.1. Introduction9.2. Progressive neural network learning9.3. Compressive learning9.4. ConclusionsReferences
Chapter 10: Representation learning and retrieval
Abstract10.1. Introduction10.2. Discriminative and self-supervised autoencoders10.3. Deep representation learning for content based image retrieval10.4. Model retraining methods for image retrieval10.5. Variance preserving supervised representation learning10.6. Concluding remarksReferences
Chapter 11: Object detection and tracking
Abstract11.1. Object detection11.2. Object tracking11.3. ConclusionReferences
Chapter 12: Semantic scene segmentation for robotics
Abstract12.1. Introduction12.2. Algorithms and architectures for semantic segmentation12.3. Loss functions for semantic segmentation12.4. Semantic segmentation using multiple inputs12.5. Semantic segmentation data sets and benchmarks12.6. Semantic segmentation metrics12.7. ConclusionReferences
Chapter 13: 3D object detection and tracking
Abstract13.1. Introduction13.2. 3D object detection13.3. 3D object tracking13.4. ConclusionReferences
Chapter 14: Human activity recognition
Abstract14.1. Introduction14.2. Trimmed action recognition14.3. Temporal action localization14.4. Spatiotemporal action localization14.5. Data sets for human activity recognition14.6. ConclusionReferences
Chapter 15: Deep learning for vision-based navigation in autonomous drone racing
Abstract15.1. Introduction15.2. System decomposition approach in drone racing navigation15.3. Transfer learning and end-to-end planning15.4. Useful tools for data collection and training15.5. Conclusions and future workReferences
Chapter 16: Robotic grasping in agile production
Abstract16.1. Introduction16.2. Grasping and object manipulation16.3. Grasp evaluation16.4. Manipulation benchmarking16.5. Data sets16.6. ConclusionReferences
Chapter 17: Deep learning in multiagent systems
Abstract17.1. Introduction17.2. Setting the scene17.3. Challenges17.4. Deep learning in multiagent systems17.5. ConclusionReferences
Chapter 18: Simulation environments
Abstract18.1. Introduction18.2. Robotic simulators18.3. ConclusionsReferences
Chapter 19: Biosignal time-series analysis
Abstract19.1. Introduction19.2. ECG classification and advance warning for arrhythmia19.3. Early prediction of mortality risk for COVID-19 patients19.4. ConclusionReferences
Chapter 20: Medical image analysis
Abstract20.1. Introduction20.2. Early detection of myocardial infarction using echocardiography20.3. COVID-19 recognition from X-ray images via convolutional sparse support estimator based classifier20.4. ConclusionReferences
Chapter 21: Deep learning for robotics examples using OpenDR
Abstract21.1. Introduction21.2. Structure of OpenDR toolkit and application examples21.3. Cointegration of simulation and training21.4. Concluding remarksReferences
Index

Content preview from Deep Learning for Robot Perception and Cognition

Chapter 21: Deep learning for robotics examples using OpenDR

Manos Kirtas; Konstantinos Tsampazis; Pavlos Tosidis; Nikolaos Passalis; Anastasios Tefas Aristotle University of Thessaloniki, Thessaloniki, Greece

Abstract

Robotics often involve solving challenging perception, planning, and action problems. Deep Learning (DL) provided powerful tools for solving these problems, by employing neural architectures that are trained in an end-to-end fashion. However, these DL tools are not always straightforward to use, due to their steep learning curve. Apart from this, a number of domain-specific additional limitations, for example, computational constraints of embedded devices, is further hindering the adoption of DL on various fields, including robotics. ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Publisher Resources

ISBN: 9780323885720

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Deep Learning for Robot Perception and Cognition

by Alexandros Iosifidis, Anastasios Tefas

Chapter 21: Deep learning for robotics examples using OpenDR

Abstract

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.