Congestion-aware Traffic Routing System using sensor data

Abstract

In this paper, we present a congestion-aware route planning system. First we learn the congestion model based on real data from a fleet of taxis and loop detectors. Using the learned street-level congestion model, we develop a congestionaware traffic planning system that operates in one of two modes:(1) to achieve the social optimum with respect to travel time over all the drivers in the system or (2) to optimize individual travel times. We evaluate the performance of this system using 10,000+ taxis trips and show that on average our approach improves the total travel time by 15%.

Information Dynamics in Transportation Systems with Traffic Lights Control

“…Surveys show that, in most cases, traffic participants trust and follow the navigation recommendations [9]. Systems for traffic planning in the presence of congestion have been researched by [3,13,14,15] by controlling the information given to each participant (proposing certain routes) to achieve individual or global social optimum performance [3]. The studies done in [21] and [24] analyse the traffic performance when information about congestion, containing either local details about the neighbouring nodes or global details about the traffic networks, is disseminated according to a model of information dissemination.…”

Congestion-Aware Warehouse Flow Analysis and Optimization

“…Moreover, Gallager [20] proposed a routing algorithm that achieves the total minimum delay in the network. Aslam et al [21] learn a congestion model based on real data and develop a congestion aware traffic planning system. When shortest paths are congested, passing through them can deteriorate the network efficiency considerably.…”

Themis: A participatory navigation system for balanced traffic routing

“…They assign a group of drivers to the combination of paths that optimize the total travel time. This algorithm was evaluated using the taxi trajectory data in Singapore [17].…”

“…We present a participatory system, using up-to-present data collected from cars to determine the information, based on which cooperative routing algorithms make decisions (i.e., real-time traffic and PTT or ATV). Compared with the taxi data evaluation in [17], our evaluation method investigates the performance of cooperative navigation at different penetration rates by meaningfully expanding the trajectory data.…”

“…Using a similar method as [17], we learned the parameters α and β for 7,411 road segments from the total of 11,450 road segments. These segments were used because they have good direct travel time estimation.…”