Online learning for offroad robots: Using spatial label propagation to learn long-range traversability

Raia Hadsell, Pierre Sermanet, Ayse Naz Erkan, Jan Ben, Jefferson Han, Beat Flepp, Urs Muller, Yann LeCun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a solution to the problem of long-range obstacle/path recognition in autonomous robots. The system uses sparse traversability information from a stereo module to train a classifier online. The trained classifier can then predict the traversability of the entire scene. A distance-normalized image pyramid makes it possible to efficiently train on each frame seen by the robot, using large windows that contain contextual information as well as shape, color, and texture. Traversability labels are initially obtained for each target using a stereo module, then propagated to other views of the same target using temporal and spatial concurrences, thus training the classifier to be viewinvariant. A ring buffer simulates short-term memory and ensures that the discriminative learning is balanced and consistent. This long-range obstacle detection system sees obstacles and paths at 30-40 meters, far beyond the maximum stereo range of 12 meters, and adapts very quickly to new environments. Experiments were run on the LAGR robot platform.

Original languageEnglish (US)
Title of host publicationRobotics
Subtitle of host publicationScience and Systems III
EditorsWolfram Burgard, Oliver Brock, Cyrill Stachniss
PublisherMIT Press Journals
Pages17-23
Number of pages7
ISBN (Print)9780262524841
StatePublished - Jan 1 2008
Event3rd International Conference on Robotics Science and Systems, RSS 2007 - Atlanta, United States
Duration: Jun 27 2007Jun 30 2007

Publication series

NameRobotics: Science and Systems
Volume3
ISSN (Print)2330-7668
ISSN (Electronic)2330-765X

Other

Other3rd International Conference on Robotics Science and Systems, RSS 2007
CountryUnited States
CityAtlanta
Period6/27/076/30/07

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Online learning for offroad robots: Using spatial label propagation to learn long-range traversability'. Together they form a unique fingerprint.

  • Cite this

    Hadsell, R., Sermanet, P., Erkan, A. N., Ben, J., Han, J., Flepp, B., Muller, U., & LeCun, Y. (2008). Online learning for offroad robots: Using spatial label propagation to learn long-range traversability. In W. Burgard, O. Brock, & C. Stachniss (Eds.), Robotics: Science and Systems III (pp. 17-23). (Robotics: Science and Systems; Vol. 3). MIT Press Journals.