Continuous Selection of Optimized Traffic Light Schedules: A Machine Learning Approach

Machine learning-based optimization of traffic light programs has been successfully employed to reduce emissions and traffic delays. Due to the variability of traffic flows, it is common practice to optimize multiple traffic light programs tailored for specific conditions and deploy them at predetermined times of the day or days of the week. We explore an alternative to this manual set-interval methodology. We create a system to automatically select the appropriate light controller program in response to continuously changing conditions. We analyze the current traffic density and close-time traffic patterns and instantiate the correct pre-optimized light program based on current conditions. Rather than creating a small set of programs tailored for specific periods of the day, we automatically create, and select from, an over-complete set of light controllers. Based on historic observations, a combination of machine learning approaches are used to find the best representative set of traffic flows to model the system. From these, multiple traffic-light controllers are created to address each flow individually. Using the automated matching system, we achieved reductions in both emissions and travel time over previously optimized lights. We examine the robustness of the system by ensuring that the system operates under large amounts of variability in traffic.

[1]  T. Nagatani.  The physics of traffic jams , 2002 .

[2]  Janet L. Kolodner,et al.  Case-Based Reasoning , 1989, International Joint Conference on Artificial Intelligence.

[3]  Pat Langley,et al.  Learning Cooperative Lane Selection Strategies for Highways , 1998, AAAI/IAAI.

[4]  T. Urbanik,et al.  Reinforcement learning-based multi-agent system for network traffic signal control , 2010 .

[5]  Marco Wiering,et al.  Multi-Agent Reinforcement Learning for Traffic Light control , 2000 .

[6]  Peter Stone,et al.  Traffic Intersections of the Future , 2006, AAAI.

[7]  C. A. Murthy,et al.  Unsupervised Feature Selection Using Feature Similarity , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Teuvo Kohonen,et al.  Learning vector quantization , 1998 .

[9]  Rahul Sukthankar,et al.  Micro-Auction-Based Traffic-Light Control: Responsive, Local Decision Making , 2015, 2015 IEEE 18th International Conference on Intelligent Transportation Systems.

[10]  Andrew Cumming,et al.  Multiple Traffic Signal Control Using A Genetic Algorithm , 1999, ICANNGA.

[11]  Ari Juels,et al.  Stochastic Hillclimbing as a Baseline Method for , 1994 .

[12]  David Leake,et al.  Case-Based Reasoning: Experiences, Lessons and Future Directions , 1996 .

[13]  Hesham Rakha,et al.  A Novel Clustering Algorithm for Traffic Operational Analysis , 2018 .

[14]  Rahul Sukthankar,et al.  Approximating the Effects of Installed Traffic Lights: A Behaviorist Approach Based on Travel Tracks , 2015, 2015 IEEE 18th International Conference on Intelligent Transportation Systems.

[15]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[16]  Daniel Krajzewicz,et al.  Recent Development and Applications of SUMO - Simulation of Urban MObility , 2012 .

[17]  Thomas Urbanik,et al.  Enhanced Genetic Algorithm for Signal-Timing Optimization of Oversaturated Intersections , 2000 .

[18]  J. Wielinski,et al.  Annual Meeting of the Transportation Research Board , 2010 .

[19]  Agnar Aamodt,et al.  Case-Based Reasoning for Improving Traffic Flow in Urban Intersections , 2014, ICCBR.

[20]  J. Y. K. Luk,et al.  Two traffic responsive area traffic control methods: SCAT and SCOOT , 1983 .

[21]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[22]  Jalan Kajang-Puchong,et al.  The Use of Genetic Algorithm for Traffic Light and Pedestrian Crossing Control , 2009 .

[23]  Aleksandar Stevanovic,et al.  SCOOT and SCATS: Closer Look into Their Operations , 2009 .

[24]  Rahul Sukthankar,et al.  Traffic Lights with Auction-Based Controllers: Algorithms and Real-World Data , 2017, ArXiv.

[25]  Baher Abdulhai,et al.  Reinforcement learning for true adaptive traffic signal control , 2003 .

[26]  Javier J. Sánchez Medina,et al.  Genetic algorithms and cellular automata: a new architecture for traffic light cycles optimization , 2004, Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753).

[27]  Tong Li,et al.  Nonlinear Dynamics of Traffic Jams , 2005, Second International Multi-Symposiums on Computer and Computational Sciences (IMSCCS 2007).