Stereo vision for planetary rovers: stochastic modeling to near real-time implementation
International Journal of Computer Vision
Autonomous Cross-Country Navigation: An Integrated Perception and Planning System
IEEE Expert: Intelligent Systems and Their Applications
Electronically directed "focal" stereo
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Vehicles capable of dynamic vision
IJCAI'97 Proceedings of the Fifteenth international joint conference on Artifical intelligence - Volume 2
VisionBug: A Hexapod Robot Controlled by Stereo Cameras
Autonomous Robots
Combining EMS-Vision and Horopter Stereo for Obstacle Avoidance of Autonomous Vehicles
ICVS '01 Proceedings of the Second International Workshop on Computer Vision Systems
Toward Reliable Off Road Autonomous Vehicles Operating in Challenging Environments
International Journal of Robotics Research
| Hi-index | 0.00 |
The authors present research under way in the AutoNav program, a collaborative effort sponsored by the German and US Departments of Defense to develop the next generation autonomous vehicle navigation and control system. UBM, one of the German participants, has over 10 years of experience in developing vision-based autonomous vehicle navigation systems. Until now, however, vision processing on these vehicles has been based on the extraction and analysis of simple spatial features. Over approximately the same time period, Sarnoff Corporation, a program partner on the US side, has developed powerful real-time algorithms and hardware systems for image and scene motion analysis. This article describes UBM and Sarnoff's progress in achieving the integration of Sarnoff's area-based vision techniques within the 4D perception and control architecture UBM has developed. In this way, they can extend UBM's autonomous navigation capabilities to unpaved and off-road navigation scenarios. In particular, the authors describe the use of directed real-time area-based stereo processing for determining the vertical profile of the path to be traversed by the autonomous vehicle.