Finding Feasible Routes with Reinforcement
Learning Using Macro-Level Traffic Measurements
Mustafa Can Ozkan
1
#
SpaceTimeLab, University College London, UK
Tao Cheng #
SpaceTimeLab, University College London, UK
Abstract
The quest for identifying feasible routes holds immense significance in the realm of transportation,
spanning a diverse range of applications, from logistics and emergency systems to taxis and public
transport services. This research area offers multifaceted benefits, including optimising traffic
management, maximising traffic flow, and reducing carbon emissions and fuel consumption. Extensive
studies have been conducted to address this critical issue, with a primary focus on finding the
shortest paths, while some of them incorporate various traffic conditions such as waiting times at
traffic lights and traffic speeds on road segments. In this study, we direct our attention towards
historical data sets that encapsulate individuals’ route preferences, assuming they encompass all
traffic conditions, real-time decisions and topological features. We acknowledge that the prevailing
preferences during the recorded period serve as a guide for feasible routes. The study’s noteworthy
contribution lies in our departure from analysing individual preferences and trajectory information,
instead focusing solely on macro-level measurements of each road segment, such as traffic flow or
traffic speed. These types of macro-level measurements are easier to collect compared to individual
data sets. We propose an algorithm based on Q-learning, employing traffic measurements within a
road network as positive attractive rewards for an agent. In short, observations from macro-level
decisions will help us to determine optimal routes between any two points. Preliminary results
demonstrate the agent’s ability to accurately identify the most feasible routes within a short training
period.
2012 ACM Subject Classification Computing methodologies → Q-learning
Keywords and phrases routing, reinforcement learning, q-learning, data mining, macro-level patterns
Digital Object Identifier 10.4230/LIPIcs.GIScience.2023.58
Category Short Paper
1 Introduction
The topic of finding routes between two points has been studied in many different fields, such
as computer systems, transportation systems and communication networks. The majority
of research concentrates on route optimisation, seeking to reduce travel time or distance
or to maximise operational efficiencies, such as the maximum number of taxi customers
or the maximum storage of a delivery truck. These studies, which employ mathematical
optimisation techniques, include optimisation constraints such as the truck’s maximum cargo
capacity and minimise/maximise the objective function of the main aim, such as travel time.
They often take into account the average travel time on a route depending on the length of
the road, the timing of the traffic lights, or occasionally the traffic situation, including actual
or historical traffic flow and speeds. They also factor in user preferences from surveys or GPS
1
corresponding author
© Mustafa Can Ozkan and Tao Cheng;
licensed under Creative Commons License CC-BY 4.0
12th International Conference on Geographic Information Science (GIScience 2023).
Editors: Roger Beecham, Jed A. Long, Dianna Smith, Qunshan Zhao, and Sarah Wise; Article No. 58; pp. 58:1–58:6
Leibniz International Proceedings in Informatics
Schloss Dagstuhl – Leibniz-Zentrum für Informatik, Dagstuhl Publishing, Germany
资源评论
