Gábor Szücs

Developing co‐operative transport system and route planning

Abstract This paper consists of two parts: planning Co‐operative Transport Systems (CTS) with general rules (communication is a new idea in this system) and an investigation into route planning as a part of services provided in CTS. Part one reveals developing new systems for cooperative sensing and predicting flow, infrastructure and environmental conditions surrounding traffic, with a view to improve the safety and efficiency of road transport operations. Part two introduces the enhancement of the performance of the route planning algorithms. The key issues of these parts are communication and co‐operation between the elements of the whole Co‐operative Transport System.

Route Planning with Uncertain Information using Dempster-Shafer theory

The aim of this paper is to find a solution for route planning in a road network, where the costs of roads are uncertain. Our concept is based on the Dempster-Shafer theory and Dijkstras algorithm, which helps to find the best routes. We model the influencing factors of the traffic congestion on the roads using uncertain probabilities described by probability intervals. Based on these intervals the cost intervals of each road can be calculated. Taking the uncertain values of costs into account an algorithm has been outlined for determination the best routes from a node to all other nodes comparing the cost intervals and using decision rules. Decision rules can be defined by the end user, if necessary node by node.

Route planning based on uncertain information in transport networks

The goal of this paper is to find a solution for route planning in a transport network where the network type can be arbitrary: a network of bus routes, a network of tram rails, a road network or any other type of a transport network. Furthermore, the costs of network elements are uncertain. The concept is based on the Dempster-Shafer theory and Dijkstras algorithm which helps with finding the best routes. The paper focuses on conventional studies without considering traffic accidents or other exceptional circumstances. The concept is presented by an undirected graph. In order to model conventional real transport, the influencing factors of traffic congestion have been applied in the abstract model using uncertain probabilities described by probability intervals. On the basis of these intervals, the cost intervals of each road can be calculated. Taking into account the uncertain values of costs, an algorithm has been outlined for determining the best routes from one node to all other nodes comparing cost intervals and using decision rules that can be defined by the end user, and if necessary, node by node. The suggested solution can be applied for both one type of network as well as for a combination of a few of those.