首页 | 本学科首页   官方微博 | 高级检索  
     检索      


Extending Time to Collision for probabilistic reasoning in general traffic scenarios
Institution:1. Intelligent Vehicles and Safety Systems Group, The Australian Centre for Field Robotics, The University of Sydney, NSW 2006, Australia;2. Institute of Robotics and Intelligent Systems, ETH Zurich, 8092 Zurich, Switzerland;1. Griffith School of Engineering, Griffith University, Gold Coast, QLD 4222, Australia;2. Strome College of Business, Old Dominion University, Norfolk, Virginia 23529, USA;1. Jiangsu Key Laboratory of Urban ITS, Southeast University, Si Pai Lou #2, Nanjing, 210096, China;2. Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, Si Pai Lou #2, Nanjing, 210096, China;1. Technical University of Munich, Chair of Ergonomics, Boltzmannstraße 15, D-85747 Garching, Germany;2. Delft University of Technology, BioMechanical Engineering, Mekelweg 2, 2628 CD, Delft, The Netherlands;3. BMW Group, Petuelring 130, D-80788 Munich, Germany;1. Department of Transportation Planning & Engineering, School of Civil Engineering, National Technical University of Athens, 15773, Greece;2. School of Architecture, Civil and Building Engineering, Loughborough University, Ashby Road, Loughborough, LE11 3TU, United Kingdom;3. Department of Civil, Geo and Environmental Engineering, Technical University of Munich, Munich, 80333, Germany;4. Faculty of Technology, Policy and Management, Technical University of Delft, Jaffalaan 5, Delft, 2628 BX, Netherlands;5. Lab for Transport Engineering, Department of Civil and Environmental Engineering, University of Nicosia, Nicosia, 2111, Cyprus;6. Chair of Transportation Systems Engineering, Department of Civil, Geo and Environmental Engineering, Technical University of Munich, Munich, 80333, Germany;1. Transport and Roads, Department of Technology and Society,Faculty of Engineering, LTH Lund University, Box 118,SE-22100 Lund, Sweden;2. Institute of Transport Economics, Gaustadalléen 21,NO-0349 Oslo, Norway;3. Transportation Research Institute, Hasselt University, Wetenschapspark 5, bus 6,BE-3590 Diepenbeek, Belgium
Abstract:Vehicle-to-vehicle communication systems allow vehicles to share state information with one another to improve safety and efficiency of transportation networks. One of the key applications of such a system is in the prediction and avoidance of collisions between vehicles. If a method to do this is to succeed it must be robust to measurement uncertainty and to loss of communication links. The method should also be general enough that it does not rely on constraints on vehicle motion for the accuracy of its predictions. It should work for all interactions between vehicles and not just a select subset. This paper presents a method to calculate Time to Collision for unconstrained vehicle motion. This metric is gated using a novel technique based on relative vehicle motion that we call “looming”. Finally, these ideas are integrated into a probabilistic framework that accounts for uncertainty in vehicle state and loss of vehicle-to-vehicle communication. Together this work represents a new way of considering vehicle collision estimation. These algorithms are validated on data collected from real world vehicle trials.
Keywords:Collision avoidance  Vehicle safety communications  Probabilistic model  Intelligent Transportation Systems  Vehicle to vehicle communication
本文献已被 ScienceDirect 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号