A Learning-based Adaptive Signal Control System with Function Approximation**This work is partially supported by J. Gust. Richert Foundation.

Investigating the impacts of crash prediction models on quantifying safety effectiveness of Adaptive Signal Control Systems

Existing traffic control systems are mostly deployed in private wired networks. With the development of wireless technology, vehicles and infrastructure devices will be connected through wireless communications, which might open a new door for cyberattackers. It is still not clear what types of cyberattacks can be performed through infrastructure-to-infrastructure and vehicle-to-infrastructure communications, whether such attacks can introduce critical failure to the system, and what the impacts are of cyberattacks on traffic operations. This paper investigates the vulnerability of traffic control systems in a connected environment. Four typical elements, including signal controllers, vehicle detectors, roadside units, and onboard units, are identified as the attack surfaces. The paper mainly focuses on attacking actuated and adaptive signal control systems by sending falsified data, which is considered as an indirect but realistic attack approach. The objective of an attacker is to maximize system delay with constraints such as budget and attack intensity. Empirical results show that different attack scenarios result in significant differences in delay, and some ineffective attacks may even improve the system performance. Simulation results from a real-world corridor show that critical intersections, which have a higher impact on network performance, can be identified by analyzing the attack locations. Identification of such intersections can be helpful in designing a more resilient transportation network.

With the development of connected vehicles (CVs) technology, it has become a new research topic to capture the dynamic traffic system by using CVs data. The traditional vehicle arrival prediction models are limited to the fixed detectors, which can only recognize the passing information of vehicles, but cannot identify the state of vehicles. This paper proposed a new vehicle arrival prediction model of traffic signal control in a connected vehicle environment. First, the vehicle's identification number (ID), position, velocity, and acceleration were obtained in a CV environment. Second, a new vehicle arrival prediction model was developed by the joint probability distribution calibrated based on CV data. Then, the simulation experiment was designed for analyzing influence factors on model performance. The results show that the average relative error of each factor is less than 10%. Finally, the reliability of the proposed model was verified based on an adaptive signal control algorithm. Therefore, the proposed model can be used in the adaptive signal control system.

Control methodologies of traffic signals have significantly improved during the recent past along with advancements in technology. Adaptive traffic signal control is the most recent and advanced control type of traffic signals. Adaptive control is able to efficiently relieve traffic congestion by continuously adjusting signal timings according to real-time traffic conditions. Conventional optimization methods such as integer programming, hill climbing, or descent gradient searching have been gradually overshadowed by genetic algorithms in many areas including traffic signal operation. The research presented in this article is distinct from previous studies in that it focuses on real-time adaptive signal optimization using genetic algorithms. The proposed adaptive signal system provides acyclic signal operation based on a rolling horizon real-time control approach. The algorithm was tested using microsimulation for on-line evaluation and comparison to fixed-time plans generated from the latest TRANSYT-7F version 9.7, which has a genetic optimization feature. The developed signal system consists of three major components including a genetic algorithm optimization module, an internal traffic simulation module, and a database management system all working in cooperation to optimize signal timings in real time. Using the pseudo on-line simulation platform, three testing scenarios for high, medium, and low level of traffic demands were conducted focusing on evaluating several important features of the proposed adaptive signal control system. The test results indicated that real-time genetic control outperformed fixed-signal timing plan in all scenarios based on total vehicle delay.

Road's traffic management is an important topic which is more and more covered by various actors in the Intelligent Transportation Systems field via many proposed solutions. Thus, in order to achieve the dream of a smart city, special attention was given to the treatment of cities' traffic management problem; especially in junctions which constitute bottlenecks for traffic flow leading to a poor quality of urban mobility. The aim of this study is to examine further the RED approach for traffic lights management recently proposed for the design of an adaptive signal control system In the context of ITL (Intelligent Traffic Lights) systems, based generally on sensors, and communication technologies. Traffic management is a well known problematic in data networks. Thus, several researchers have studied methods for providing congestion avoidance at the gateway called also router. Inspired by advanced technologies in Internet traffic management, we propose a system based on the RED (Random Early Detection) mechanism widely used by routers to avoid congestion. Our contribution consists of the adaptation of this mechanism to the ITS context by applying it for traffic lights management. Our system will certainly contribute to decrease waiting times, fuel consumption and pollution. This paper will present the complete adaptation of the RED algorithm to the context of the intelligent transport systems. In addition, the RED-based design performance is compared with that of the pre-timed model to gain insights between the two systems.

Traffic congestion and delays at signalized intersections remain a challenge in urban mobility. To minimize congestion, adaptive traffic signal control systems have been adopted across the United States. However, for these systems to function at their best, systems require an accurate estimation of traffic states, such as traffic density and queue length. This paper implements a relatively novel method, Physics-Informed Neural Networks (PINNs), for real-time traffic density estimation to enhance adaptive intersection signal control. The methodology leverages PINNs, which integrate both data-driven learning and physical constraints imposed by the Lighthill-Whitham-Richards (LWR) macroscopic traffic flow model. A simulation of a four-way intersection was used to generate realistic spatio-temporal traffic data to evaluate the performance of the model. Separate PINNs models, one trained for each incoming approach using simulation-based spatio-temporal density data, provide segment-level density predictions. These real-time density estimates are then employed within an adaptive traffic signal control algorithm designed to adjust green light phasing based on detected demand. The proposed PINNs control strategy was evaluated through simulation, comparing its performance against the Webster traffic timing method using key metrics such as average vehicle delay at the intersection and average vehicle travel time. The findings show an approximate 18% decrease in average vehicle delay and more than a 6% reduction in average travel time when utilizing adaptive traffic control based on the PINNs method for determining density values. These findings highlight the potential of leveraging PINNs for accurate, real-time traffic state estimation, which can effectively inform and improve the performance of adaptive traffic signal control systems, leading to reduced congestion and enhanced mobility at intersections.

Adaptive traffic control systems continuously monitor traffic conditions on an arterial and adjust traffic signal timings to accommodate variation in traffic volume and minimize stops and delays. This paper describes currently practical adaptive control systems which have been used in the United States and worldwide, which include Adaptive Control System-Lite (ACS-Lite), Optimization Policies for Adaptive Control (OPAC), Real-Time Hierarchical Optimized Distributed and Effective System (RHODES), Sydney Coordinated Adaptive Traffic System (SCATS) and Split Cycle Offset Optimization (SCOOT). The comparisons of the benefits from past experiences, cost and hardware requirements will help the traffic engineers and decision makers a guideline to select the optimized adaptive control system based on research objectives.

Important class of adaptive control systems with non-stochastic description of the uncertainty and disturbances is considered. New approach to the design of the non-stochastic adaptive dual control algorithms is suggested. The elaborated approach is based on the introducing of two new cost functions for optimisation of the control signal and exiting signal added to the control signal. The ellipsoid bounded estimation of the plant parameters is used for the plant parameter estimation and indirect adaptation. This estimation method was also named set-membership estimation. The approach is introduced and described comprehensive using simple controller of self-tuning type. The designed controller, which is used as an example to demonstrate the new suggested method, can be applied to control of nonminimumphase plants. The method can be extended to adaptive controllers of various other types. The violent contrast is attributed to the suggested design method as compared with other dual control approaches for non-stochastic systems with set-membership estimation. The method allows designing of non-stochastic dual adaptive controllers that are very simple computational and consist of the cautious controller with the optimal excitations. Non-stochastic adaptive dual controllers, which are designed using suggested approach, have superiorities over the similar controllers based on the certainty equivalence approach because of the properties of caution and optimal excitation.

A physics-informed road user safety field theory for traffic safety assessments applying artificial intelligence-based video analytics

SummaryIn this study, we present a reinforcement learning (RL)‐based flight control system design method to improve the transient response performance of a closed‐loop reference model (CRM) adaptive control system. The methodology, known as RL‐CRM, relies on the generation of a dynamic adaption strategy by implementing RL on the variable factor in the feedback path gain matrix of the reference model. An actor‐critic RL agent is designed using the performance‐driven reward functions and tracking error observations from the environment. In the training phase, a deep deterministic policy gradient algorithm is utilized to learn the time‐varying adaptation strategy of the design parameter in the reference model feedback gain matrix. The proposed control structure provides the possibility to learn numerous adaptation strategies across a wide range of flight and vehicle conditions instead of being driven by high‐fidelity simulators or flight testing and real flight operations. The performance of the proposed system was evaluated on an identified and verified mathematical model of an agile quadrotor platform. Monte‐Carlo simulations and worst case analysis were also performed over a benchmark helicopter example model. In comparison to the classical model reference adaptive control and CRM‐adaptive control system designs, the proposed RL‐CRM adaptive flight control system design improves the transient response performance on all associated metrics and provides the capability to operate over a wide range of parametric uncertainties.

SummaryAt the present time, there is a great deal of interest in the adaptive control of systems with rapidly varying parameters. Such problems arise in different forms and in many disciplines including finance, sociology, biology, and engineering. In general, these problems are intractable mathematically and the time variations have to be classified in some form to obtain rigorous results. In this paper, we consider the adaptive identification and control of linear systems with periodically varying parameters (referred to as linear time‐varying periodic (LTP) systems). The class of systems with known periodic parameters has been investigated widely since the pioneering work of Floquet and lends itself to rigorous mathematical analysis. However, very little was known until the early years of the last decade concerning the adaptive control of such systems. The problem was introduced by Xu and explored in detail by Narendra and Zhiling in 2006 and 2009, respectively. In 2012, a new method was introduced in adaptive control by Han and Narendra and is referred to as second‐level adaptation. In this paper, the adaptive identification and control of LTP systems using second‐level adaptation is discussed.

Purpose. The purpose of the article is to develop a methodology for creating cone crusher adaptive control system based on the model-based design method for automated software generation of microprocessor controllers. Methodology. A method based on a block-oriented predictive model was used to generate control signals for the cone crusher. The parameters and structure of this model were identified in real time using measured data from the plant. A prototype of the control system was created in MATLAB/Simulink. Then, the model-based design method was used to generate software for digital signal processors. Mathematical statistics methods were employed to analyze the experimental results. Findings. A method of model-based design of an adaptive control system for a cone crusher has been developed. This system uses a predictive model of a block-oriented structure. This model adjusts the predictive controller’s structure and parameters directly during operation. This approach makes it possible to divide the functions of identifying the process model and generating controls between the two digital controllers. Consequently, the average computational time is reduced while ensuring the stabilization of the degree of homogeneity of ore crushing and separate output of the control size class, with respective standard deviation coefficients not exceeding 3.42 and 1.83 %, respectively. Originality. The regularity of the effect of the closed-side setting and the eccentric speed on the particle size distribution of crushed ore has been established. This shows that high homogeneity of the crushed product is ensured by simultaneously adjusting these input coordinates. We propose a new method for synthesizing an adaptive cone crusher control system based on a model-based design approach. This method provides automated real-time generation of software for microprocessor-based controllers, allowing the system to quickly adjust to changes in rock mass characteristics and other disturbances. Practical value. A hardware and software implementation of an adaptive control system for a cone crusher is proposed. This system is based on a block-oriented predictive model. The model ensures the stabilization of the required ore particle size distribution. This stabilization is achieved by adjusting the closed-side setting and the eccentric speed. The system is based on 16-bit, low-cost digital signal processors. A prototype of the system was tested in a crushing plant at a metallurgical enterprise.

Inertial stabilization systems are designed to maintain the angular orientation of an optical system or other device in inertial space. Applications include surveillance, target tracking, flight control, weapon pointing, navigation, communication and others. Typically, some variation of a closed loop control system is employed which uses feedback from a gyro. The object of this paper is to consider the potential benefits and some approaches to adaptive control algorithms. Ideally, an adaptive control system would adjust itself to achieve "optimal performance" with respect to some criteria in the presence of changing plant characteristics, changing noise characteristics and a changing disturbance environment. Potentially, such a design could provide robust control for a variety of system configurations, mission conditions and applications resulting in significant reductions in both development and production costs as well as improved performance. First, the general stabilization problem and some conventional control system designs are briefly reviewed. Then a variety of adaptive techniques are surveyed. Finally, the current status and results of a joint research project between Texas Instruments and the University of Texas at Arlington whose goal is to develop an adaptive stabilization control system is discussed.

This paper explores how applying a basic management science principle to air traffic management operations can lead to revised roles and responsibilities that allow operations to be handled by the most appropriate participants. Previous research that applied the principle to local departure and arrival management is reviewed; the application is then expanded to regional and national air traffic management. The paper examines the operational and engineering implications of the resulting concept, contrasted with current operations and tools, and identifies where additional research or development is needed. Examples are provided that illustrate the resulting activities at the various air traffic management facilities across a broad range of look-ahead timeframes. I. Introduction HE High-Density Area Departure and Arrival Management (HDDAM) concept was developed in the context of arrival and departure air traffic management in high-density airspace such as Metroplex areas. The management science principles underlying HDDAM appear to be applicable to National Airspace System (NAS) operations at any level, including all phases of planning and flight. This paper explores some operational and engineering implications of such an application to local, regional, and NAS-wide air traffic operations. As described elsewhere, 1-3 HDDAM redefines the decision making processes within the Air Route Traffic Control Center (ARTCC), the Terminal Radar Approach Control (TRACON), and multiple Air Traffic Control Towers (ATCTs) for high-density area departure/arrival traffic management. The decision making authority proposed for each facility reflects the information available to each decision maker and the impact of the decision on their operating environment. Specifically, each facility is responsible for defining the capacity of its air traffic management resources (such as airports, airspace, airways) and requesting resources for flights to use. As shown in Fig. 1 for a single Metroplex, the TRACON has a central role in these interactions, serving as a “broker” between the facilities with the resources and the facilities with requests for use of those resources that are not within their scope of control, while also accounting for the TRACON’s ability to deliver the flights to the resources in question. ATCTs are responsible for requesting resources for departing flights and the ARTCC for requesting resources for arriving flights, as they each possess the best information regarding the status of these flights. Because of the uncertainties present in predicting individual flight departure readiness and inbound air traffic arrival times, the TRACON does not assign specific departure and arrival slots to individual flights. Instead, the TRACON allocates slots to the airports (for departures) and ARTCC (for arrivals) so they can make flight-specific assignments as deemed best for their individual operating environments. This effectively decouples the decisions of the individual ATCTs and the ARTCC, giving each facility increased flexibility to handle situations dynamically as they develop. Air traffic management operations are most effective when the decision makers work as a team. The underlying principle of HDDAM is that this can be accomplished best when all facilities’ roles and responsibilities are based on the management science principle that allows the appropriate level of autonomy at each facility. The principle states that decisions should be assigned to those who are already performing other tasks with the relevant data—those who know the most about the factors affecting the decision—and will be most directly affected by the consequences of 1 Lead Multi-Discipline System Engineer, TFM System Engineering and Evolution, 7515 Colshire Drive, Mailstop

A transportation control system maintains the flow of traffic according to a schedule by implementing various policies (e.g. procedures, rules, priorities, etc.). In a conventional control system the schedule is fixed and the policies are deterministic. An adaptive control system, on the other hand, has an internal mechanism for altering its policies which, in turn, adjust the schedule in response to demand and system status. An adaptive control system combines five basic functions: (1) surveillance, to detect traffic; (2) communications, to relay surveillance data and control signals; (3) performance evaluation, to compare the difference between the desired and current operation; (4) on-line data processing, to determine the control signals and scheduling; and (5) overall system operation, i.e., the functional summation of (1), (2), (3) and (4). An ultimate system would also generate predictions of future demand which would be factored into the control adaptation process. This paper summarizes recent progress in the implementation of adaptive control systems in transportation. The applications discussed include control of freeway ramps, urban street traffic, air traffic, and urban rapid transit.