Efficient Macroscopic Urban Traffic Models for Reducing Congestion: A PDDL+ Planning Approach

Abstract

The global growth in urbanisation increases the demand for services including road transport infrastructure, presenting challenges in terms of mobility. In this scenario, optimising the exploitation of urban road networks is a pivotal challenge. Existing urban traffic control approaches, based on complex mathematical models, can effectively deal with planned-ahead events, but are not able to cope with unexpected situations --such as roads blocked due to car accidents or weather-related events-- because of their huge computational requirements. Therefore, such unexpected situations are mainly dealt with manually, or by exploiting pre-computed policies. Our goal is to show the feasibility of using mixed discrete-continuous planning to deal with unexpected circumstances in urban traffic control. We present a PDDL+ formulation of urban traffic control, where continuous processes are used to model flows of cars, and show how planning can be used to efficiently reduce congestion of specified roads by controlling traffic light green phases. We present simulation results on two networks (one of them considers Manchester city centre) that demonstrate the effectiveness of the approach, compared with fixed-time and reactive techniques.

Embedding Automated Planning within Urban Traffic Management Operations

“…The existing conditions and set of corrective goals required to deal with these events are so varied that detailed strategies are impossible to draw up a priori in a large, dense urban area. Approaches to regionwide traffic control has been trialled using model predictive control (MPC) strategies and optimisation (Lin 2011;Dotoli, Fanti, and Meloni 2006;van den Berg et al 2004). This line of research uses a control theory approach which, given an adequate dynamical model, can be used to derive a solution that can give continuous responses to changing inputs.…”

“…The planner used in the project was the domain independent planner UPMurphi (Della Penna et al 2009), which inputs models in PDDL+ (Fox and Long 2006). To produce a working executable of UPMurphi which generated UTM strategies in real-time, we had to perform several cycles of iterations over the engineering of the PDDL+ mod-els, starting from the model proposed in (Vallati et al 2016). The quality of the strategies output from the planner was evaluated firstly by hand inspecting the strategies to check that they were "sensible".…”

An ASP Framework for Efficient Urban Traffic Optimization

“…The use of Artificial Intelligence techniques in road transportation has already been found to be efficient in optimizing traffic flow [1,20]. For instance, [25] introduced a mixed discrete-continuous planning [14] approach for reducing congestion through a macroscopic point of view. In [9] instead, a temporal planning approach was used for managing traffic, now through a microscopic prospective, with the intention of reducing air pollution and respect air quality limitations.…”

Macroscopic Traffic-Flow Modelling Based on Gap-Filling Behavior of Heterogeneous Traffic

“…In addition, researchers are now focusing on providing traffic planners with tools helping them in controlling traffic facilities in order to mitigate traffic congestion. In this regard, a PDDL+ approach was introduced by Vallati et al [5], which controls traffic lights to aid in congestion reduction. Latest research interests include developing models to characterize the vehicular travel times.…”