Gabriel Gomes

CONGESTED FREEWAY MICROSIMULATION MODEL USING VISSIM

A procedure for constructing and calibrating a detailed model of a freeway by using VISSIM is presented and applied to a 15-mi stretch of I-210 West in Pasadena, California. This test site provides several challenges for microscopic modeling: a high-occupancy vehicle (HOV) lane with an intermittent barrier, a heavy freeway connector, 20 metered on-ramps with and without HOV bypass lanes, and three interacting bottlenecks. Field data used as input to the model were compiled from two separate sources: loop detectors on the on-ramps and main line (PeMS) and a manual survey of on-ramps and off-ramps. Gaps in both sources made it necessary to use a composite data set, constructed from several typical days. FREQ was used as an intermediate tool to generate a set of origin-destination matrices from the assembled boundary flows. The model construction procedure consists of (1) identification of important geometric features, (2) collection and processing of traffic data, (3) analysis of the main-line data to identify recurring bottlenecks, (4) VISSIM coding, and (5) calibration based on observations from Step 3. A qualitative set of goals was established for the calibration. These were met with relatively few modifications to VISSIMs driver behavior parameters.

TOPL: TOOLS FOR OPERATIONAL PLANNING OF TRANSPORTATION NETWORKS

TOPL is a suite of software tools for specifying freeway operational improvement strategies, such as ramp metering, demand and incident management, and for quickly estimating the benefits of such improvements. TOPL is based on the macroscopic cell transmission model. The paper summarizes the theory of the cell transmission model and describes the procedure to carry out a TOPL application. The procedure is illustrated for the 26-mile long I-210W freeway in California, whose model is calibrated using loop detector measurements of volume and speed. The measurements show that congestion originates in a bottleneck and moves upstream, as predicted by the theory. The simulations show that appropriate ramp metering can dramatically reduce total congestion delay and mainline travel time.Copyright

Bandwidth Maximization Using Vehicle Arrival Functions

We revisit the offset optimization problem for maximization of two-way progression bands. A new formulation is proposed relying on the concepts of relative offset and vehicle arrival functions. Vehicle arrival functions represent the probability that a vehicle reaches a given intersection at a given time. Relative offsets are the displacement of the arrival functions with respect to a moving coordinate frame. An explicit formula for the bandwidth is derived based on these two quantities. The bandwidth maximization problem is then formulated as an unconstrained nonlinear program. The cases of pulse and Gaussian arrivals are considered in detail. Numerical techniques are proposed for both that return globally optimal solutions with small computational cost.

A study of two onramp metering schemes for congested freeways

We investigate the stability of a nonlinear (piecewise linear and possibly discontinuous) model of a freeway onramp, controlled by two popular onramp metering schemes: alinea and percent-occupancy. The freeway model is based on Daganzos cell-transmission model and can be understood as a hybrid system switching among several discrete-time linear dynamics equations. It is shown, under conditions placed on the upstream mainline demand and on the controller parameters, that both of these controllers are capable of rejecting congestion near the onramp. In addition, we illustrate how the use of downstream measurements allows alinea to robustly drive the freeway to a predetermined uncongested desired state.

Estimation of highway traffic from sparse sensors: Stochastic modeling and particle filtering

Traffic control is essential for the achievement of a sustainable and safe mobility. Monitoring systems deployed over the roads collect a great amount of traffic data that must be efficiently processed by statistical methods to draw traffic macroparameters that are needed for control operations. In this paper we propose a particle filtering approach to estimate the density over a road network starting from noisy and sparse measurements provided by road-embedded sensors. We propose a new Bayesian framework based on the link-node cell transmission model to take into account the stochastic behavior of traffic and the hysteresis phenomenon that are typically observed in real data. Numerical tests show that the estimation method is able to reliably reconstruct the traffic field even in case of very sparse sensor deployments.

Globally optimal solutions to the on-ramp metering problem - Part 1

A mathematical programming approach to the freeway on-ramp metering problem is formulated. The objective function is a linear combination of mainline and on-ramp flows, termed the generalized total travel time. The underlying freeway model - the asymmetric cell transmission model (ACTM) - is similar to the original cell transmission model (CTM), except that the merge law of the CTM has been replaced with additional terms weighted by the influence parameters. It is shown that an appropriate selection of the model parameters and boundary conditions guarantees a physically reasonable evolution of the ACTM. It is also shown that the resulting nonlinear optimization problem can be solved globally, by solving an equivalent linear program, whenever the cost weights are generated by a proposed numerical algorithm.

Expert Level Control of Ramp Metering Based on Multi-Task Deep Reinforcement Learning

This paper shows how the recent breakthroughs in reinforcement learning (RL) that have enabled robots to learn to play arcade video games, walk, or assemble colored bricks, can be used to perform other tasks that are currently at the core of engineering cyberphysical systems. We present the first use of RL for the control of systems modeled by discretized non-linear partial differential equations (PDEs) and devise a novel algorithm to use non-parametric control techniques for large multi-agent systems. Cyberphysical systems (e.g., hydraulic channels, transportation systems, the energy grid, and electromagnetic systems) are commonly modeled by PDEs, which historically have been a reliable way to enable engineering applications in these domains. However, it is known that the control of these PDE models is notoriously difficult. We show how neural network-based RL enables the control of discretized PDEs whose parameters are unknown, random, and time-varying. We introduce an algorithm of mutual weight regularization (MWR), which alleviates the curse of dimensionality of multi-agent control schemes by sharing experience between agents while giving each agent the opportunity to specialize its action policy so as to tailor it to the local parameters of the part of the system it is located in. A discretized PDE, such as the scalar Lighthill–Whitham–Richards PDE can indeed be considered as a macroscopic freeway traffic simulator and which presents the most salient challenges for learning to control large cyberphysical system with multiple agents. We consider two different discretization procedures and show the opportunities offered by applying deep reinforcement for continuous control on both. Using a neural RL PDE controller on a traffic flow simulation based on a Godunov discretization of the San Francisco Bay Bridge, we are able to achieve precise adaptive metering without model calibration thereby beating the state of the art in traffic metering. Furthermore, with the more accurate BeATS simulator, we manage to achieve a control performance on par with ALINEA, a state-of-the-art parametric control scheme, and show how using MWR improves the learning procedure.

Offset optimization for a network of signalized intersections via semidefinite relaxation

We consider the problem of coordinating the traffic signals in a network of signalized intersections to reduce accumulated queues of vehicles throughout the network. We assume that all signals have a common cycle time and a fixed actuation plan, and we propose an approach for optimizing the relative phase offsets. Unlike existing techniques, our approach accommodates networks with arbitrary topology and scales well. This is accomplished by proposing a sinusoidal approximation of the queueing processes in the network, which enables a semidefinite relaxation of the offset optimization problem that is easily solved. We demonstrate the result in a case study of a traffic network in Arcadia, California.

Optimal desired traffic flow patterns for automated highway systems

The design of optimal desired traffic flow patterns for multiple lane automated highway systems (AHSs) is analyzed. A highway network model, which is based on the notion of activity and a principle of vehicles conservation, is proposed. The traffic flow pattern for the network of highways is found in such a way that the total entry flow to the AHS network is maximized and the constraints related to the dynamic highway model and the AHS capacity are simultaneously satisfied.

Arterial bandwidth maximization via signal offsets and variable speed limits control

The problem of maximizing bandwidth along an arterial is here addressed by use of two combined control actions: traffic lights offsets and variable speed limits. The optimization problem has been enriched in order to account for traffic energy consumption and network travel time, thus avoiding impractical or undesirable solutions. A traffic microscopic simulator has been used to assess the performance of the proposed technique in terms of energy consumption, travel time, idling time, and number of stops. The theoretical bandwidth proves to be well correlated with idling time and number of stops, while the variable speed limits control shows interesting advantages in terms of energy consumption without penalizing the travel time. An analysis of the Pareto optimum has been carried out to help the designer choose a trade-off in the multi-objective optimization.