Skip to main content

Disciplines

Automotive
Business IT + Informatics
Construction + Real Estate
Electrical Engineering + Electronics
Energy + Sustainability
Insurance + Risk
Finance + Banking
Management + Leadership
Marketing + Sales
Mechanical Engineering + Materials

Events

DE
EN

Books

Journals

Start single access now

Request access for companies

EXTENDED SEARCH
Log in
Top

2023 | Book

Introduction Read chapter Read first chapter

Agile Autonomy: Learning High-Speed Vision-Based Flight

Author: Antonio Loquercio

Publisher: Springer Nature Switzerland

Book Series : Springer Tracts in Advanced Robotics

Part of: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Login to get access
insite
SEARCH

About this book

This book presents the astonishing potential of deep sensorimotor policies for agile vision-based quadrotor flight. Quadrotors are among the most agile and dynamic machines ever created. However, developing fully autonomous quadrotors that can approach or even outperform the agility of birds or human drone pilots with only onboard sensing and computing is challenging and still unsolved.

Deep sensorimotor policies, generally trained in simulation, enable autonomous quadrotors to fly faster and more agile than what was possible before. While humans and birds still have the advantage over drones, the author shows the current research gaps and discusses possible future solutions.

Table of Contents

Frontmatter
Chapter 1. Introduction
Abstract
This thesis presents algorithms for tightly-coupled robotic perception and action. According to this paradigm, in an iterative and infinite loop, action controls the amount of information coming from sensory data, and perception guides and provides feedback to action. Ecological psychology showed that the seamless integration of sensing and control is a fundamental feature of biological agents [55]. Can also artificial and embodied agents benefit from a tightly-coupled perception and action loop? My work addresses this question in the context of high-speed agile quadrotor flight.
Antonio Loquercio
Chapter 2. Contributions
Abstract
This chapter summarizes the key contributions of the papers that are reprinted in the appendix. It further highlights the connections between the individual results and refers to related work and video contributions. In total, this research has been published in 4 peer-reviewed conference publications and 5 journal publications (one in the IEEE Transactions on Robotics, one in Science Robotics, and three in the Robotics Automation Letters (RA-L)).
Antonio Loquercio
Chapter 3. Future Directions
Abstract
Deep learning is an emerging technology with the promise of addressing the synergy between robotic perception and action. Research on learning-based robotics is still in the early stages and has not yet reached the same maturity level as traditional model-based algorithms. Yet, considerable progress has been made in the last few years, which has clearly shown the potential of deep learning to overcome some of the limitations of conventional model-based autonomy.
Antonio Loquercio
Backmatter
Metadata
Title
Agile Autonomy: Learning High-Speed Vision-Based Flight
Author
Antonio Loquercio
Copyright Year
2023
Electronic ISBN
978-3-031-27288-2
Print ISBN
978-3-031-27287-5
DOI
https://doi.org/10.1007/978-3-031-27288-2

Premium Partner

Neuer Inhalt
    Image Credits