Improving Robot Navigation Through Self-Supervised Online Learning

Boris Sofman, Ellie Lin Ratliff, J. Andrew (Drew) Bagnell, John Cole, Nicolas Vandapel, and Anthony (Tony) Stentz
Journal of Field Robotics, Vol. 23, No. 12, December, 2006


Download
  • Adobe portable document format (pdf) (2MB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract
In mobile robotics, there are often features that, while potentially powerful for improving navigation, prove difficult to profit from as they generalize poorly to novel situations. Overhead imagery data, for instance, has the potential to greatly enhance autonomous robot navigation in complex outdoor environments. In practice, reliable and effective automated interpretation of imagery from diverse terrain, environmental conditions, and sensor varieties proves challenging. Similarly, fixed techniques that successfully interpret on-board sensor data across many environments begin to fail past short ranges as the density and accuracy necessary for such computation quickly degrade and features that are able to be computed from distant data are very domain-specific. We introduce an online, probabilistic model to effectively learn to use these scope-limited features by leveraging other features that, while perhaps otherwise more limited, generalize reliably. We apply our approach to provide an efficient, self-supervised learning method that accurately predicts traversal costs over large areas from overhead data. We present results from field testing on-board a robot operating over large distances in various off-road environments. Additionally, we show how our algorithm can be used offline with overhead data to produce a priori traversal cost maps and detect misalignments between overhead data and estimated vehicle positions. This approach can significantly improve the versatility of many unmanned ground vehicles by allowing them to traverse highly varied terrains with increased performance.

Keywords
mobile robot, navigation, self-supervised, online learning

Notes
Associated Project(s): UGCV PerceptOR Integrated
Number of pages: 24

Text Reference
Boris Sofman, Ellie Lin Ratliff, J. Andrew (Drew) Bagnell, John Cole, Nicolas Vandapel, and Anthony (Tony) Stentz, "Improving Robot Navigation Through Self-Supervised Online Learning," Journal of Field Robotics, Vol. 23, No. 12, December, 2006

BibTeX Reference
@article{Sofman_2006_5603,
   author = "Boris Sofman and Ellie Lin Ratliff and J. Andrew (Drew) Bagnell and John Cole and Nicolas Vandapel and Anthony (Tony) Stentz",
   title = "Improving Robot Navigation Through Self-Supervised Online Learning",
   journal = "Journal of Field Robotics",
   month = "December",
   year = "2006",
   volume = "23",
   number = "12",
}