原文传递
Using Virtual Active Vision Tools to Improve Autonomous Driving Tasks.
| 题名： | Using Virtual Active Vision Tools to Improve Autonomous Driving Tasks. |
| 作者： | Jochem, Todd M.; |
| 关键词： | NEURAL NETS, AUTONOMOUS NAVIGATION, COMPUTER VISION, COMPUTERIZED SIMULATION, INPUT, OUTPUT, POSITION(LOCATION), STEERING, MODELS, REAL TIME, REASONING, THESES, GEOMETRIC FORMS, IMAGES, WHEELS, SELF OPERATION, GEOMETRY, VIDEO SIGNALS, TRANSPLANTATION, PREPROCESSING, TRANSFORMATIONS. |
| 摘要： | ALVINN is a simulated neural network for road following. In its most basic form, it is trained to take a 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 transformations 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. |
| 总页数： | 23 |
| 报告类型： | 科技报告 |
相关文献
- Bus Rapid Transit Technologies: A Virtual Mirror for Eliminating Vehicle Blind Zones. Volume 2.
- Bus Rapid Transit Technologies: Assisting Drivers Operating Buses on Road Shoulders. Volume I.
- Bus Rapid Transit Technologies: A Virtual Mirror for Eliminating Vehicle Blind Zones. Volume 2.
- Bus Rapid Transit Technologies: Assisting Drivers Operating Buses on Road Shoulders. Volume I.
- Autonomous Road Driving Arenas for Performance Evaluation
- HUMAN FACTORS ISSUES RELATED TO USE OF VISION ENHANCEMENT SYSTEMS.
检索历史
应用推荐
