Best Paper Award at COSIT’17

Our paper on avoiding traffic jams with dynamic self-organizing trip planning [1] received the best paper award at COSIT conference in L’Aquila. Congratulations to my coauthor Maurice Sotzny, and special thanks to the audience!

Our paper is motivated by the increasing congestions in urban areas. Most navigation systems and algorithms that avoid these congestions consider drivers independently and can, thus, cause novel congestions at unexpected places. Pre-computation of optimal trips (Nash equilibrium) could be a solution to the problem but is due to its static nature of no practical relevance.
In contrast, our paper provides an approach to avoid traffic jams with dynamic selforganizing trip planning. We apply reinforcement learning to learn dynamic weights for routing from the decisions and feedback logs of the vehicles and alter navigation plans of the vehicles on the tactical level (compare Hoogendors hierarchy of motion). In order to compare our routing regime against others, we validate our approach in an open simulation environment (LuST) that allows reproduction of the traffic in Luxembourg for a particular day. Additionally, in two realistic scenarios: (1) usage of stationary sensors and (2) deployment in a mobile navigation system, we perform experiments with varying penetration rates. All our experiments reveal that performance of the traffic network is increased and occurrence of traffic jams are reduced by application of our routing regime

[1] [pdf] [doi] T. Liebig and M. Sotzny, “On Avoiding Traffic Jams with Dynamic Self-Organizing Trip Planning,” in 13th International Conference on Spatial Information Theory (COSIT 2017), E. Clementini, M. Donnelly, M. Yuan, C. Kray, P. Fogliaroni, and A. Ballatore, Eds., Dagstuhl, Germany: Schloss Dagstuhl–Leibniz-Zentrum fuer Informatik, 2017, vol. 86, p. 17:1–17:12.
[Bibtex]
@incollection{liebig17b,
author ={Thomas Liebig and Maurice Sotzny},
title ={{On Avoiding Traffic Jams with Dynamic Self-Organizing Trip Planning}},
booktitle ={13th International Conference on Spatial Information Theory (COSIT 2017)},
pages ={17:1--17:12},
series ={Leibniz International Proceedings in Informatics (LIPIcs)},
ISBN ={978-3-95977-043-9},
ISSN ={1868-8969},
year ={2017},
volume ={86},
editor ={Eliseo Clementini and Maureen Donnelly and May Yuan and Christian Kray and Paolo Fogliaroni and Andrea Ballatore},
publisher ={Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik},
address ={Dagstuhl, Germany},
URL ={http://drops.dagstuhl.de/opus/volltexte/2017/7761},
URN ={urn:nbn:de:0030-drops-77615},
doi ={10.4230/LIPIcs.COSIT.2017.17},
notes ={Best Paper},
annote ={Keywords: situation-aware trip planning, self-organizing traffic, reinforcement learning}
}