Header

UZH-Logo

Maintenance Infos

A machine learning approach to visual perception of forest trails for mobile robots - Zurich Open Repository and Archive


Giusti, Alessandro; Guzzi, Jerome; Ciresan, Dan; He, Fang-Lin; Rodriguez, Juan Pablo; Fontana, Flavio; Fässler, Matthias; Forster, Christian; Schmidhuber, Jurgen; Di Caro, Gianni; Scaramuzza, Davide; Gambardella, Luca (2016). A machine learning approach to visual perception of forest trails for mobile robots. IEEE Robotics and Automation Letters, 1(2):661-667.

Abstract

We study the problem of perceiving forest or mountain trails from a single monocular image acquired from the viewpoint of a robot traveling on the trail itself. Previous literature focused on trail segmentation, and used low-level features such as image saliency or appearance contrast; we propose a different approach based on a deep neural network used as a supervised image classifier. By operating on the whole image at once, our system outputs the main direction of the trail compared to the viewing direction. Qualitative and quantitative results computed on a large real-world dataset (which we provide for download) show that our approach outperforms alternatives, and yields an accuracy comparable to the accuracy of humans that are tested on the same image classification task. Preliminary results on using this information for quadrotor control in unseen trails are reported. To the best of our knowledge, this is the first letter that describes an approach to perceive forest trials, which is demonstrated on a quadrotor micro aerial vehicle.

Abstract

We study the problem of perceiving forest or mountain trails from a single monocular image acquired from the viewpoint of a robot traveling on the trail itself. Previous literature focused on trail segmentation, and used low-level features such as image saliency or appearance contrast; we propose a different approach based on a deep neural network used as a supervised image classifier. By operating on the whole image at once, our system outputs the main direction of the trail compared to the viewing direction. Qualitative and quantitative results computed on a large real-world dataset (which we provide for download) show that our approach outperforms alternatives, and yields an accuracy comparable to the accuracy of humans that are tested on the same image classification task. Preliminary results on using this information for quadrotor control in unseen trails are reported. To the best of our knowledge, this is the first letter that describes an approach to perceive forest trials, which is demonstrated on a quadrotor micro aerial vehicle.

Citations

Altmetrics

Downloads

72 downloads since deposited on 12 Aug 2016
71 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Uncontrolled Keywords:autonomous aerial vehicles;helicopters;image classification;learning (artificial intelligence);microrobots;neural nets;robot vision;deep-neural network;forest trails;machine learning approach;mobile robots;monocular image;quadrotor microaerial vehicle control;qualitative analysis;quantitative analysis;supervised image classifier;viewing direction;visual perception;Cameras;Image segmentation;Mobile robots;Roads;Robot vision systems;Visual perception;Aerial Robotics;Deep Learning;Machine Learning;Visual-Based Navigation
Language:English
Date:17 December 2016
Deposited On:12 Aug 2016 06:00
Last Modified:13 Aug 2016 03:07
Publisher:Institute of Electrical and Electronics Engineers
ISSN:2377-3766
Additional Information:© 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Publisher DOI:https://doi.org/10.1109/LRA.2015.2509024
Related URLs:http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7358076&isnumber=7419970 (Publisher)
Other Identification Number:merlin-id:12929

Download

Preview Icon on Download
Preview
Content: Accepted Version
Filetype: PDF
Size: 4MB
View at publisher

TrendTerms

TrendTerms displays relevant terms of the abstract of this publication and related documents on a map. The terms and their relations were extracted from ZORA using word statistics. Their timelines are taken from ZORA as well. The bubble size of a term is proportional to the number of documents where the term occurs. Red, orange, yellow and green colors are used for terms that occur in the current document; red indicates high interlinkedness of a term with other terms, orange, yellow and green decreasing interlinkedness. Blue is used for terms that have a relation with the terms in this document, but occur in other documents.
You can navigate and zoom the map. Mouse-hovering a term displays its timeline, clicking it yields the associated documents.

Author Collaborations