Header

UZH-Logo

Maintenance Infos

"On-the-spot Training" for Terrain Classification in Autonomous Air-Ground Collaborative Teams


Delmerico, Jeffrey; Giusti, Alessandro; Müggler, Elias; Gambardella, Luca; Scaramuzza, Davide (2016). "On-the-spot Training" for Terrain Classification in Autonomous Air-Ground Collaborative Teams. In: International Symposium on Experimental Robotics, Tokyo, Japan, 3 October 2016 - 6 October 2016.

Abstract

We consider the problem of performing rapid training of a terrain classifier in the context of a collaborative robotic search and rescue system. Our system uses a vision-based flying robot to guide a ground robot through unknown terrain to a goal location by building a map of terrain class and elevation. However, due to the unknown environments present in search and rescue scenarios, our system requires a terrain classifier that can be trained and deployed quickly, based on data collected on the spot. We investigate the relationship of training set size and complexity on training time and accuracy, for both feature-based and convolutional neural network classifiers in this scenario. Our goal is to minimize the deployment time of the classifier in our terrain mapping system within acceptable classification accuracy tolerances. So we are not concerned with training a classifier that generalizes well, only one that works well for this particular environment. We demonstrate that we can launch our aerial robot, gather data, train a classifier, and begin building a terrain map after only 60 seconds of flight.

Abstract

We consider the problem of performing rapid training of a terrain classifier in the context of a collaborative robotic search and rescue system. Our system uses a vision-based flying robot to guide a ground robot through unknown terrain to a goal location by building a map of terrain class and elevation. However, due to the unknown environments present in search and rescue scenarios, our system requires a terrain classifier that can be trained and deployed quickly, based on data collected on the spot. We investigate the relationship of training set size and complexity on training time and accuracy, for both feature-based and convolutional neural network classifiers in this scenario. Our goal is to minimize the deployment time of the classifier in our terrain mapping system within acceptable classification accuracy tolerances. So we are not concerned with training a classifier that generalizes well, only one that works well for this particular environment. We demonstrate that we can launch our aerial robot, gather data, train a classifier, and begin building a terrain map after only 60 seconds of flight.

Statistics

Downloads

47 downloads since deposited on 25 Aug 2016
30 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Language:English
Event End Date:6 October 2016
Deposited On:25 Aug 2016 09:20
Last Modified:08 Dec 2017 20:13
Publisher:Springer
Other Identification Number:merlin-id:13665

Download

Download PDF  '"On-the-spot Training" for Terrain Classification in Autonomous Air-Ground Collaborative Teams'.
Preview
Filetype: PDF
Size: 4MB