Visual Homing for Micro Aerial Vehicles using Scene Familiarity

Gerald van Dalen; Kimberly Mcguire; Guido de Croon

Visual Homing for Micro Aerial Vehicles using Scene Familiarity

Gerald van Dalen, Kimberly Mcguire, Guido de Croon

Control & Simulation

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

123 Downloads (Pure)

Abstract

Autonomous navigation is a major challenge in the development of Micro Aerial Vehicles (MAVs). Especially when an algorithm has to be efficient, insect intelligence can be a source of inspiration. An elementary navigation task is homing, which means autonomously returning to the initial location. A promising approach uses learned visual familiarity of a route to determine reference headings during homing. In this paper an existing biological proof-of-concept is transferred to an algorithm for micro drones, using vision-in-the-loop experiments in indoor environments. An artificial neural network determines which control actions to take.

Original language	English
Title of host publication	International Micro Air Vechicle Competition and Conference 2016
Subtitle of host publication	Beijing, China
Editors	Zhihong Peng, Feng Lin
Pages	307-313
Publication status	Published - 2016
Event	International Micro Air Vechicle Competition and Conference 2016 - Beijing, China Duration: 17 Oct 2016 → 21 Oct 2016 http://www.imavs.org/2016/

Conference

Conference	International Micro Air Vechicle Competition and Conference 2016
Abbreviated title	IMAV2016
Country/Territory	China
City	Beijing
Period	17/10/16 → 21/10/16
Internet address	http://www.imavs.org/2016/

Access to Document

imav_paperFinal published version, 4.13 MB

Cite this

@inproceedings{40e76fe5896a41dab675ecdb11f1f991,

title = "Visual Homing for Micro Aerial Vehicles using Scene Familiarity",

abstract = "Autonomous navigation is a major challenge in the development of Micro Aerial Vehicles (MAVs). Especially when an algorithm has to be efficient, insect intelligence can be a source of inspiration. An elementary navigation task is homing, which means autonomously returning to the initial location. A promising approach uses learned visual familiarity of a route to determine reference headings during homing. In this paper an existing biological proof-of-concept is transferred to an algorithm for micro drones, using vision-in-the-loop experiments in indoor environments. An artificial neural network determines which control actions to take. ",

author = "{van Dalen}, Gerald and Kimberly Mcguire and {de Croon}, Guido",

year = "2016",

language = "English",

pages = "307--313",

editor = "Zhihong Peng and Feng Lin",

booktitle = "International Micro Air Vechicle Competition and Conference 2016",

note = "International Micro Air Vechicle Competition and Conference 2016, IMAV2016 ; Conference date: 17-10-2016 Through 21-10-2016",

url = "http://www.imavs.org/2016/",

}

Visual Homing for Micro Aerial Vehicles using Scene Familiarity. / van Dalen, Gerald; Mcguire, Kimberly; de Croon, Guido.
International Micro Air Vechicle Competition and Conference 2016: Beijing, China. ed. / Zhihong Peng; Feng Lin. 2016. p. 307-313.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Visual Homing for Micro Aerial Vehicles using Scene Familiarity

AU - van Dalen, Gerald

AU - Mcguire, Kimberly

AU - de Croon, Guido

PY - 2016

Y1 - 2016

N2 - Autonomous navigation is a major challenge in the development of Micro Aerial Vehicles (MAVs). Especially when an algorithm has to be efficient, insect intelligence can be a source of inspiration. An elementary navigation task is homing, which means autonomously returning to the initial location. A promising approach uses learned visual familiarity of a route to determine reference headings during homing. In this paper an existing biological proof-of-concept is transferred to an algorithm for micro drones, using vision-in-the-loop experiments in indoor environments. An artificial neural network determines which control actions to take.

AB - Autonomous navigation is a major challenge in the development of Micro Aerial Vehicles (MAVs). Especially when an algorithm has to be efficient, insect intelligence can be a source of inspiration. An elementary navigation task is homing, which means autonomously returning to the initial location. A promising approach uses learned visual familiarity of a route to determine reference headings during homing. In this paper an existing biological proof-of-concept is transferred to an algorithm for micro drones, using vision-in-the-loop experiments in indoor environments. An artificial neural network determines which control actions to take.

UR - http://resolver.tudelft.nl/uuid:40e76fe5-896a-41da-b675-ecdb11f1f991

M3 - Conference contribution

SP - 307

EP - 313

BT - International Micro Air Vechicle Competition and Conference 2016

A2 - Peng, Zhihong

A2 - Lin, Feng

T2 - International Micro Air Vechicle Competition and Conference 2016

Y2 - 17 October 2016 through 21 October 2016

ER -

Visual Homing for Micro Aerial Vehicles using Scene Familiarity

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this