Highway Capacity Manual改訂の動向--テイラ-教授の講演より

[What is a cost-benefit analysis?].

Autonomous Agents and Multi-Agent Systems www.springer.com/10458 Michael Luck and Carles Sierra, Editors-in-Chief Published by Springer. About this Issue Learning is a critical component for autonomous agents so that they can discover novel behaviors, adapt to a nonstationary world, and handle unanticipated events. As virtual and physical agents become more common, these learning agents need to handle interactions not only with an environment, but also with other agents. Multiagent learning thus becomes an indispensable component of building intelligent systems, even though much of the current learning research focuses on single-agent settings.

Autonomous Agents and Multi-Agent Systems

The Knowledge Engineering Review

Effective prediction of pavement performance is essential for transportation agencies to appropriately strategize maintenance, rehabilitation, and reconstruction of roads. One of the primary performance indicators is the international roughness index (IRI) which represents the pavement roughness. Correlating the pavement roughness to other performance measures has been under continuous development in the past decade. However, the drawback of existing correlations is that most of them are not practical yet reliable for prediction of roughness. In this study a novel approach was developed to predict the IRI, utilizing two data sets extracted from long term pavement performance (LTPP) database. The proposed methodology included the application of a hybrid technique which combines the gene expression programming (GEP) and artificial neural network (ANN). The developed algorithm showed reasonable performance for prediction of IRI using traffic parameters and structural properties of pavement. Furthermore, estimation of present IRI from historical data was evaluated through another set of LTPP data. The second prediction model also depicted a reasonable performance power. Further extension of the proposed models including different pavement types, traffic and environmental conditions would be desirable in future studies.

https://cyberleninka.org/article/n/1441953.pdf

Prediction of pavement roughness using a hybrid gene expression programming-neural network technique

The pavement condition index (PCI) is a widely used numerical index for the evaluation of the structural integrity and operational condition of pavements. Estimation of the PCI is based on the results of a visual inspection in which the type, severity, and quantity of distresses are identified. The purpose of this study is to develop an alternative approach for forecasting the PCI using optimization techniques, including artificial neural networks (ANN) and genetic programming (GP). The proposed soft computing method can reliably estimate the PCI and can be used in a pavement management system (PMS) using simple and accessible spreadsheet softwares. A database composed of the PCI results of more than 1,250 km of highways in Iran was used to develop the models. The results showed that the ANN- and GP-based projected values are in good agreement with the field-measured data. In addition, the ANN-based model was more precise than the GP-based model. For more straightforward applications, a computer program was developed based on the results obtained.

Application of Soft Computing for Prediction of Pavement Condition Index

Introduction of perpetual pavement in the late 1990s provided the possibility of constructing a pavement with higher initial investment expenditure but lower maintenance and user costs. Life cycle cost (LCC) of a facility is the sum of all one-time and recurring costs over the full life span of that facility. As for highways, it includes agency costs (initial construction and maintenance costs), user costs (vehicle operation and time value costs), social costs (environmental costs) and salvage value at the end of pavement design life which is considered as a negative cost. This study compares the LCC of highways with conventional and perpetual pavements to figure out which system is economically preferred in various traffic and weather conditions for Iranian highways. Results of the study show that perpetual pavement construction can save LCC of pavements in the range of 4–20%.

Life cycle cost comparison of highways with perpetual and conventional pavements

The dynamic behavior of traffic lights regulating a network of intersections can be viewed as a complex discrete-event system that can be modeled and controlled by Petri nets. In this paper, a bilayer signalized control method is presented. In the lower layer, a colored stochastic Petri net controls the signal indication displays and stage transitions. In the upper layer, a supervisory logic layer decides which stage should be serviced next. The proposed model increases modularity, reduces complexity, and, more importantly, is capable of being used to implement various signal control strategies. The method is used to implement four different control strategies: pretimed control, fully actuated control, semiactuated control, and random stage selection (as a benchmark) in the context of a signalized traffic network containing six intersections. Extensibility and future potential research to further enhance the proposed method are discussed and proposed at the end.

A Modular Colored Stochastic Petri Net for Modeling and Analysis of Signalized Intersections

In a multiagent system, a (social) norm describes what the agents may expect from each other. Norms promote autonomy (an agent need not comply with a norm) and heterogeneity (a norm describes interactions at a high level independent of implementation details). Researchers have studied norm emergence through social learning where the agents interact repeatedly in a graph structure.

In contrast, we consider norm emergence in an open system, where membership can change, and where no predetermined graph structure exists. We propose Silk, a mechanism wherein a generator monitors interactions among member agents and recommends norms to help resolve conflicts. Each member decides on whether to accept or reject a recommended norm. Upon exiting the system, a member passes its experience along to incoming members of the same type. Thus, members develop norms in a hybrid manner to resolve conflicts.

We evaluate Silk via simulation in the traffic domain. Our results show that social norms promoting conflict resolution emerge in both moderate and selfish societies via our hybrid mechanism.

Silk: a simulation study of regulating open normative multiagent systems

This paper shows how the traffic interactions of an intersection can be regulated by means of auction theory, multi-agent systems and machine learning techniques. In the proposed work, the intersection space is viewed as a spatially complex set of scarce commodities whose temporal non-overlapping usage is adjudicated through an interactive bidding process that involves multiple agents. A machine learning technique is used to optimize the bidding strategies of the agents. The multi-tiered decentralized agent-based framework proposed here increases modularity by decomposing the intersection into smaller sub-parts, adds flexibility and effectiveness by designing it to account for variable stage sequence. Moreover, unlike most other control strategies which are either based on delay or queue length, the proposed method is based on both of these traffic-related metrics. The proposed method is used to regulate the traffic for a network of six intersections and its results are compared with two other control strategies including pre-timed and fully actuated.

Mehdi Mashayekhi

Papers

Application of Soft Computing for Prediction of Pavement Condition Index

Life cycle cost comparison of highways with perpetual and conventional pavements

A Modular Colored Stochastic Petri Net for Modeling and Analysis of Signalized Intersections

Silk: a simulation study of regulating open normative multiagent systems

A Multiagent Auction-based Approach for Modeling of Signalized Intersections