1556-4967/asset/ROB_left.gif?v=1&s=d65b44dc034437d2164c862740196cc4d1b24f3a)
1556-4967/asset/ROB_centre.gif?v=1&s=8b5f44f63c82103a7257ec6cbd7cb40d97d8f848)
1556-4967/asset/ROB_right.gif?v=1&s=f7ac5ea957d16549f93a760a61769cc5cf58b069)
Research Article
Learning from examples in unstructured, outdoor environments
Article first published online: 23 JAN 2007
DOI: 10.1002/rob.20167
Copyright © 2007 Wiley Periodicals, Inc., A Wiley Company
Issue
1556-4967/asset/cover.gif?v=1&s=8ae8a664db917614691f9be04768e6cd3c4aab3d "Journal of Field Robotics")
Journal of Field Robotics
Special Issue: Special Issue on Machine Learning Based Robotics in Unstructured Environments
Volume 23, Issue 11-12, pages 1019–1036, November - December 2006
Additional Information
How to Cite
Sun, J., Mehta, T., Wooden, D., Powers, M., Rehg, J., Balch, T. and Egerstedt, M. (2006), Learning from examples in unstructured, outdoor environments. Journal of Field Robotics, 23: 1019–1036. doi: 10.1002/rob.20167
Publication History
- Issue published online: 23 JAN 2007
- Article first published online: 23 JAN 2007
- Manuscript Accepted: 23 OCT 2006
- Manuscript Received: 15 MAY 2006
Funded by
- DARPA. Grant Number: FA8650-04-C-7131
- Abstract
- References
- Cited By
Abstract
In this paper, we present a multi-pronged approach to the “Learning from Example” problem. In particular, we present a framework for integrating learning into a standard, hybrid navigation strategy, composed of both plan-based and reactive controllers. Based on the classification of colors and textures as either good or bad, a global map is populated with estimates of preferability in conjunction with the standard obstacle information. Moreover, individual feedback mappings from learned features to learned control actions are introduced as additional behaviors in the behavioral suite. A number of real-world experiments are discussed that illustrate the viability of the proposed method. © 2007 Wiley Periodicals, Inc.