Sciweavers

Share
IROS
2007
IEEE

Long-Term learning using multiple models for outdoor autonomous robot navigation

8 years 10 months ago
Long-Term learning using multiple models for outdoor autonomous robot navigation
Abstract—Autonomous robot navigation in unstructured outdoor environments is a challenging area of active research. The navigation task requires identifying safe, traversable paths which allow the robot to progress toward a goal while avoiding obstacles. One approach is to apply Machine Learning techniques that accomplish near to far learning by augmenting near-field Stereo to identify safe terrain and obstacles in the far field. Some mechanism for applying past learned experience to the active navigation task is crucial for effective far-field classification. We introduce a new method for long-term learning in the robot navigation task by selecting a subset of previously learned linear binary classifiers. We then combine their output to produce a final classification for a new image. Techniques for efficient selection of models, as well as the combination of their output, are addressed. We evaluate the performance of our technique on three fully labeled datasets, and show th...
Michael J. Procopio, Jane Mulligan, Gregory Z. Gru
Added 03 Jun 2010
Updated 03 Jun 2010
Type Conference
Year 2007
Where IROS
Authors Michael J. Procopio, Jane Mulligan, Gregory Z. Grudic
Comments (0)
books