USING VIRTUAL ACTIVE VISION TOOLS TO IMPROVE AUTONOMOUS DRIVING TASKS
ALVINN is a simulated neural network for road following. In its most basic form, it is trained to take subsampled, preprocessed video image as input, and produce a steering wheel position as output. ALVINN has demonstrated robust performance in a wide variety of situations, but is limited due to its lack of geometric models. Grafting geometric reasoning onto a non-geometric base would be difficult and would create a system with diluted capabilities. A much better approach is to leave the basic neural network intact, preserving its real-time performance and generalization capabilities, and to apply geometric transformation to the input image and the output steering vector. These transformations form a new set of tools and techniques called Virtual Active Vision. The thesis for this work is: Virtual Active Vision tools will improve the capabilities of neural network based autonomous driving systems.
Carnegie Mellon UniversityRobotics Institute, 5000 Forbes Avenue
Pittsburgh, PA United States 15213-3890
- Jochem, T M
- Publication Date: 1994-10
- Pagination: 23 p.
- TRT Terms: Advanced vehicle control systems; Neural networks
- Uncontrolled Terms: Video technology
- Old TRIS Terms: Autonomous vehicle navigation; Geometric transformation; Road following
- Subject Areas: Highways; Operations and Traffic Management; I73: Traffic Control;
- Accession Number: 00716392
- Record Type: Publication
- Report/Paper Numbers: CMU-RI-TR-94-39
- Files: TRIS
- Created Date: Feb 22 1996 12:00AM