Data Fusion Techniques for Adaptive Traffic Signal Control

Friedrich, Bernhard; Matschke, Irina; Almasri, Essam; Mück, Jürgen

doi:10.1016/s1474-6670(17)32396-0

Cited by 9 publications

(6 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang and Papageorgiou [67] performed the freeway traffic control using extended Kalman filter. Along this direction, Friedrich et al [68] introduced a new approach based on in queuing theory models for real time queue length determination. In this later method, Mueck's model serves as a quasi measurement with Kalman filtering technique.…”

Section: Network Controlmentioning

confidence: 99%

Data fusion in intelligent transportation systems: Progress and challenges – A survey

Faouzi¹,

Leung²,

Kurian³

2011

Information Fusion

356

155

View full text Add to dashboard Cite

Section: Network Controlmentioning

confidence: 99%

Data fusion in intelligent transportation systems: Progress and challenges – A survey

Faouzi¹,

Leung²,

Kurian³

2011

Information Fusion

356

155

View full text Add to dashboard Cite

“…Accurate traffic models should consider drivers' behaviour and variable route choices due to changing traffic conditions; this is the essence of dynamic traffic assignment-based methods (Gartner et al, 1992). Extensive research efforts have been conducted to develop sophisticated models (Friedrich et al, 2003); however the problem persists because: 1) models are not perfect, and equally importantly 2) the performance of controlling strategies depend on such inaccurate models;…”

Section: -Gc Summary and Limitationsmentioning

confidence: 99%

Multi-Agent Reinforcement Learning for Integrated Network of Adaptive Traffic Signal Controllers (MARLIN-ATSC)

El-Tantawy

Abdulhai

2012

2012 15th International IEEE Conference on Intelligent Transportation Systems

View full text Add to dashboard Cite

The population is steadily increasing worldwide resulting in intractable traffic congestion in dense urban areas. Adaptive Traffic Signal Control (ATSC) has shown strong potential to effectively alleviate urban traffic congestion by adjusting the signal timing plans in real-time in response to traffic fluctuations to achieve the desired objectives (e.g., minimizing delay). Efficient and robust ATSC can be designed using a multi-agent reinforcement learning (MARL) approach in which each controller (agent) is responsible for the control of traffic lights around a single traffic junction. Applying MARL approaches to ATSC problem is associated with a few challenges as agents typically react to changes in the environment at the individual level but the overall behaviour of all agents may not be optimal. This dissertation presents the development and evaluation of a novel system of Multi-Agent Reinforcement Learning for Integrated Network of Adaptive Traffic Signal Controllers (MARLIN-ATSC). The MARLIN-ATSC control system is developed to provide a self-learning ATSC using a synergetic combination of reinforcement learning approaches and game theory. MARLIN-ATSC operates in two modes: (1) independent mode, i.e. each intersection controller operates independently of other agents; and (2) integrated mode, where each controller coordinates the signal control actions with the neighbouring intersections. The system was tested on three networks (i.e., small, medium, large-scale) to ensure seamless transferability of the system design and results. The large-scale application was conducted on a computerized testbed network of 60 intersections in the lower downtown core of the City of Toronto for the morning rush hour handling 25,000 trips. The results show unprecedented reduction in the average intersection delay ranging from 27% in mode 1 to 39% in mode 2 at the network level; and travel time savings of 15% in mode 1 and 26% in mode 2, iii along the busiest routes in downtown Toronto. The thesis shows how mathematical modelling of the traffic control problem as a stochastic control problem, combined with the utilisation of artificial intelligence techniques such as reinforcement learning in a game-theory setup, can provide highly useful and economically inexpensive solutions to real-life problems such as urban traffic congestion.

show abstract

“…The information serving as input for ATSC needs to be as complete and precise as possible [5]. Therefore, additional C2I-data beside existing detectors (e.g.…”

Section: A Current Scientific Researchesmentioning

confidence: 99%

Exploitability of vehicle related sensor data in cooperative systems

Saust

Bley

Kutzner

et al. 2010

13th International IEEE Conference on Intelligent Transportation Systems

Self Cite

View full text Add to dashboard Cite

This paper shows how extended vehicle related sensor data is gained and used within the cooperative system de veloped in the project KOLINE. This system aims at coordinat ing traffic in order to achieve a reduction of delay and emissions in urban networks by exchanging information between traffic signals and approaching vehicles. Besides receiving information about the signal program and traffic state at the intersection the vehicle also uses data of mUltiple sensors and different sensor technologies. This allows the creation of a redundant representation of the vehicle's environment which is used to improve the vehicle's approach to intersections. Additionally, the information can be used by the infrastructure to improve the performance of the adaptive traffic control system by using it for tailback approximation and for the calibration of the underlying traffic model.

show abstract

Data Fusion Techniques for Adaptive Traffic Signal Control

Cited by 9 publications

References 2 publications

Data fusion in intelligent transportation systems: Progress and challenges – A survey

Data fusion in intelligent transportation systems: Progress and challenges – A survey

Multi-Agent Reinforcement Learning for Integrated Network of Adaptive Traffic Signal Controllers (MARLIN-ATSC)

Exploitability of vehicle related sensor data in cooperative systems

Contact Info

Product

Resources

About