Automated planning for Urban traffic control: Strategic vehicle routing to respect air quality limitations

Abstract

Abstract. The global growth in urbanisation increases the demand for services including road transport infrastructure, presenting challenges in terms of mobility. These trends are occurring in the context of concerns around environmental issues of poor air quality and transport related carbon dioxide emissions. One out of several ways to help meet these challenges is in the intelligent routing of road traffic through congested urban areas.Our goal is to show the feasibility of using automated planning to perform this routing, taking into account a knowledge of vehicle types, vehicle emissions, route maps, air quality zones, etc. Specifically focusing on air quality concerns, in this paper we investigate the problem where the goals are to minimise overall vehicle delay while utilising network capacity fully, and respecting air quality limits. We introduce an automated planning approach for the routing of traffic to address these areas. The approach has been evaluated on micro-simulation models that use real-world data supplied by our industrial partner. Results show the feasibility of using AI planning technology to deliver efficient routes for vehicles that avoid the breaking of air quality limits, and that balance traffic flow through the network.

Centralised Versus Decentralised Traffic Optimisation of Urban Road Networks: A Simulation Study

“…Jimoh et al demonstrated the feasibility of the current AI planning technology to address this issue on a small scale; the proposed approach is able to produce plans for re-routing tens of vehicles using a simple yet effective micro-simulation model. The work of Chrpa et al [6] exploits AI-based automated planning techniques for enforcing air-quality constraints in urban traffic. In a more recent work, Chrpa et al [7], showed that AI-based planning techniques can be used for reducing congestion of a controlled urban region by re-routing vehicles, but their work is at an exploratory stage and can cope only with a very limited number of vehicles.…”

A hyper-heuristic with two guidance indicators for bi-objective mixed-shift vehicle routing problem with time windows

“…Completing a transport task consists of loading the container to the truck at the source terminal, transporting the container from the source to the destination terminal and then unloading the container over there. The wellknown Planning Domain Description Language (PDDL) is a complex descriptive system providing a standard and flexible formalism for various AI planning domains including the VRPs [48]. It is supported by state-of-the-art planning methodologies, producing high quality solutions in various planning problems.…”

Exploiting automated planning for efficient centralized vehicle routing and mitigating congestion in urban road networks

“…AI planning has been exploited as a centralized tool for navigating vehicles in the road network, although with different aims -Jimoh et al [6] focused on exceptional circumstances (e.g. traffic accidents) while Chrpa et al [2] focused on enforcing air quality constraints.…”

“…Advantages of the exploitation of Automated Planning in a centralized architecture include having a global view of the situation, i.e., positions and intentions (goals) of vehicles in the network, and can thus take better (globally motivated) informed decisions than individual vehicles (or their drivers). In contrast to related works [2,6] that use temporal PDDL models to route vehicles (while optimizing for different objectives), we specify a planning domain model in the classical subset of PDDL (typed STRIPS). Exploiting temporal planning has shown to be computationally expensive (e.g.…”