Comparison of signalized junction control strategies that use localization probe data

IET Intell. Transp. Syst.

2012

Self Cite

This study investigates theoretical signal control algorithms based solely on probe vehicle data. Through development of a simulation system that can model urban signalised junction control using localisation probe data from all vehicles in the local area, improvements in junction operational efficiency that result from the improved input data are demonstrated for both isolated and coordinated junctions. Results from the isolated junction scenario show that the richness of the information contained within probe vehicle data means that control algorithms based just on positions and velocities of vehicles can produce 25% reductions in average delay compared to the current standard control algorithm MOVA. Results from the twin junction scenario confirm the importance of using high-level synchronisation to coordinate closely connected junctions, achieving reductions in average delays (compared to independent control approaches) of up to 40% through a process of weighting the probe vehicle data to reflect prior stage decisions of other parts of the junction. Critical to achieving these benefits, however, is the availability of high localisation accuracy probe data, with results indicating that the levels of accuracy necessary are representative of the typical performance of current in-vehicle global positioning system units, except when those vehicles are operating in urban canyon environments.

Section: Introductionmentioning

confidence: 99%

Quantifying the impact of probe vehicle localisation data errors on signalised junction control

IET Intell. Transp. Syst.

2012

Self Cite

“…Box and Waterson (2010a) presents an auctioning agent control method. This work showed the auctioning agent approach outperforming MOVA in simulations on an isolated T-junction.…”

Section: Context and Motivationmentioning

confidence: 99%

“…The simulation test bed used for the work presented in this paper is described in detail in Box and Waterson (2010a); Waterson and Box (2011). In summarry: it uses S-Paramics microsimulation software to model networks and simulate the movement of individual vehicles through junctions.…”

Section: Context and Motivationmentioning

confidence: 99%

See 1 more Smart Citation

An automated signalized junction controller that learns strategies from a human expert

Engineering Applications of Artificial Intelligence

2012

An automated signalized junction control system that can learn strategies from a human expert has been developed. This system applies Machine Learning techniques based on Logistic Regression and Neural Networks to affect a classification of state space using evidence data generated when a human expert controls a simulated junction.The state space is constructed from a series of bids from agents, which monitor regions of the road network. This builds on earlier work, which has developed the High Bid auctioning agent system to control signalized junctions using localization probe data. For reference the performance of the Machine Learning signal control strategies are compared to that of High Bid and the MOVA system, which uses inductive loop detectors.Performance is evaluated using simulation experiments on two networks. One is an isolated T-junction and the other is a two junction network modelled on the High Road area of Southampton, UK. The experimental results indicate that Machine Learning junction control strategies, trained by a human expert can outperform High Bid and MOVA both in terms of minimizing average delay and maximizing equitability; where the variance of the distribution over journey times is taken as a quantitative measure of equitability. Further experimental tests indicate that the Machine Learning control strategies are robust to variation in the positioning accuracy of localization probes and to the fraction of vehicles equipped with probes.

An automated signalized junction controller that learns strategies by temporal difference reinforcement learning

Engineering Applications of Artificial Intelligence

2013

This paper shows how temporal difference learning can be used to build a signalized junction controller that will learn its own strategies though experience. Simulation tests detailed here show that the learned strategies can have high performance. This work builds upon previous work where a neural network based junction controller that can learn strategies from a human expert was developed . In the simulations presented, vehicles are assumed to be broadcasting their position over WiFi giving the junction controller rich information. The vehicle's position data are pre-processed to describe a simplified state. The state-space is classified into regions associated with junction control decisions using a neural network. This classification is the strategy and is parametrized by the weights of the neural network. The weights can be learned either through supervised learning with a human trainer or reinforcement learning by temporal difference (TD). Tests on a model of an isolated T junction show an average delay of 14.12 s and 14.36 s respectively for the human trained and TD trained networks. Tests on a model of a pair of closely spaced junctions show 17.44 s and 20.82 s respectively. Both methods of training produced strategies that were approximately equivalent in their equitable treatment of vehicles, defined here as the variance over the journey time distributions.