Real-time adaptive o-road vehicle navigation and terrain classification

Urs A. Muller, Lawrence D. Jackel, Yann Lecun, Beat Flepp

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


We are developing a complete, self-contained autonomous navigation system for mobile robots that learns quickly, uses commodity components, and has the added benefit of emitting no radiation signature. It builds on the au- Tonomous navigation technology developed by Net-Scale and New York University during the Defense Advanced Research Projects Agency (DARPA) Learning Applied to Ground Robots (LAGR) program and takes advantage of recent scientific advancements achieved during the DARPA Deep Learning program. In this paper we will present our approach and algorithms, show results from our vision system, discuss lessons learned from the past, and present our plans for further advancing vehicle autonomy.

Original languageEnglish (US)
Title of host publicationUnmanned Systems Technology XV
StatePublished - 2013
EventUnmanned Systems Technology XV Conference - Baltimore, MD, United States
Duration: May 1 2013May 3 2013

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X


OtherUnmanned Systems Technology XV Conference
Country/TerritoryUnited States
CityBaltimore, MD


  • Continuous real-time learning
  • Intelligent systems
  • Machine learning
  • Off-road autonomous vehicle navigation
  • Self learning system
  • Sharing learned knowledge between systems
  • Vision-based passive long range sensing

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'Real-time adaptive o-road vehicle navigation and terrain classification'. Together they form a unique fingerprint.

Cite this