Embedding Automated Planning within Urban Traffic Management Operations

Abstract

This paper is an experience report on the results of an industry-led collaborative project aimed at automating the control of traffic flow within a large city centre. A major focus of the automation was to deal with abnormal or unexpected events such as roadworks, road closures or excessive demand, resulting in periods of saturation of the network within some region of the city. We describe the resulting system which works by sourcing and semantically enriching urban traffic data, and uses the derived knowledge as input to an automated planning component to generate light signal control strategies in real time. This paper reports on the development surrounding the planning component, and in particular the engineering, configuration and validation issues that arose in the application. It discusses a range of lessons learned from the experience of deploying automated planning in the road transport area, under the direction of transport operators and technology developers.

Exploiting Classical Planning Grounding in Hybrid PDDL+ Planning Engines

“…1. An example of PDDL+ action, process, and event taken from the Urban Traffic Control domain [6], [13].…”

“…Most of the research on hybrid PDDL+ planning focuses on the design of complete domain-independent planning engines, such as DiNo [2], SMTPlan [3], and CASP [4]; and emphasis has been given to the search module of such engines. Relevant work in the area of efficiently PDDL+ grounding focused on reformulating the input models in order make them more amenable to planning engines [5], on modifying the internal behaviour of planning engines to adapt them to the specific application domain [6], [7] , rather than on designing principled grounding modules for domainindependent planning engines.…”

Refining Process Descriptions from Execution Data in Hybrid Planning Domain Models

“…Each road link has a maximum capacity, and the occupancy of a road link denotes the current number of PCUs within it. This approach was used in feasibility trials and incorporated a simple description of the flow process (called flowrun green), which took no account of the chang-ing features of the road network (McCluskey and Vallati 2017). The use of this case study in this paper is to demonstrate the utility of learning an improved specification for the flowrun green processes, which leads to more accurate simulation and better solution plans.…”

Urban Traffic Control via Planning with Global State Constraints (Extended Abstract)

“…iii) we consider several UTC reference scenarios taken from the literature and new real-world scenarios for an experimental evaluation comparing the performance and quality of the GSC approach w.r.t. the state-of-the-art approach based on PDDL+ (Vallati et al 2016;McCluskey and Vallati 2017).…”