On the exploitation of Automated Planning for efficient decision making in road traffic accident management

Abstract

Abstract-Automated Planning can be fruitfully exploited as a Decision Support toolkit that, given a specification of available actions (elementary decisions to be taken), an initial situation and goals to be achieved, generates a plan that represents a (partially ordered) sequence of such elementary decisions that once performed the required goals are achieved. Road Traffic Accident Management is a life-critical task that deals with effective planning of emergency response when accidents occur, in order to mitigate negative effects, especially saving human lives that might be in imminent danger.In this paper, we exploit Automated Planning in the Road Traffic Accident Management domain. We specifically focus on providing necessary treatment for victims injured during accidents. This involves coordination of medical teams responsible for providing medical treatment to the victims and fire brigades that are required to release victims trapped in damaged vehicles. An empirical analysis, based in the region of West Yorkshire (UK) with a number of real accidents recently occurred there, shows the suitability of the proposed Automated Planning approach to be used in time-critical conditions, and confirms the effectiveness of the generated plans. We also demonstrated its usefulness as a tool for evaluating the impact of additional resources, in order to provide guidance for future investments.

A Hybrid Automated Planning Approach for Urban Real-time Routing of Connected Vehicles

“…The generation of routes for vehicles in a road network has been considered by the perspective of routing emergency vehicles [20], or by considering small urban areas and model the movement of vehicles to respect air quality limitations [21]. In both cases, microscopic representations are used, and the scalability of the approaches is limited.…”

How to Plan Roadworks in Urban Regions? A Principled Approach Based on AI Planning

“…This independence between reasoning and domain knowledge gives engineers a high level of flexibility since planning domain models and planning engines can be used as "black-boxes" that can be easily embedded into larger systems. Examples of embedding planning into larger frameworks include recent works in road traffic accident management [1], and urban traffic control [8].…”