Vulnerable road users (VRUs) face high collision risks in mixed traffic, yet most existing safety systems prioritize driver or vehicle assistance over direct VRU support. This paper presents ARCAS, a real-time augmented reality (AR) collision avoidance system that provides personalized spatial alerts to VRUs via wearable AR headsets. By fusing roadside 360° 3D LiDAR with SLAM-based headset tracking and an automatic 3D calibration procedure, ARCAS accurately overlays world-locked 3D bounding boxes and directional arrows onto approaching hazards in the user's passthrough view. The system also enables multi-headset coordination through shared world anchoring. Evaluated in real-world pedestrian interactions with e-scooters and vehicles (180 trials), ARCAS nearly doubles pedestrians' time to collision and increases counterparts' reaction margins by up to 4x compared to unaided eye conditions. Results validate the feasibility and effectiveness of LiDAR-driven AR guidance and highlight the potential of wearable AR as a promising next generation safety tool for urban mobility.

This paper addresses the problem of traffic state estimation (TSE) in the presence of heterogeneous sensors which include both fixed and moving sensors. Traditional fixed sensors are expensive and cannot be installed throughout the highway. Moving sensors such as Connected Vehicles (CVs) offer a relatively cheap alternative to measure traffic states across the network. Moving forward it is thus important to develop such models that effectively use the data from CVs. One such model is the nonlinear second-order Aw-Rascle-Zhang (ARZ) model which is a realistic traffic model, reliable for TSE and control. A state-space formulation is presented for the ARZ model considering junctions in the formulation which is important to model real highways with ramps. A Moving Horizon Estimation (MHE) implementation is presented for TSE using a linearized ARZ model. Various state-estimation methods used for TSE in the literature along with the presented approach are compared with regard to accuracy and computational tractability with the help of a numerical study using the VISSIM traffic simulation software. The impact of various strategies for querying CV data on the estimation performance is also considered. Several research questions are posed and addressed with a thorough analysis of the results.

This article proposes a new approach for computing a semiexplicit form of the solution to a class of traffic flow problems encoded by a Hamilton–Jacobi (HJ) partial differential equation (PDE), with time-switched Hamiltonian. Using a characterization of the problem derived from viability theory, we show that the solution associated with the problem can be formulated as a minimization problem involving the trajectory of an auxiliary dynamical system. A generalized Lax–Hopf formula for the switched Hamiltonian problem is derived, which enables us to compute the solution associated with affine initial or boundary conditions as a linear program involving the control function of the auxiliary dynamical system. This formulation allows us to compute the solution to the original problem exactly, unlike dynamic programming methods. In addition, this method allows one to very efficiently recompute the boundary conditions associated with an initial condition problem, allowing large-scale variable speed limit traffic control problems to be solved.Note to Practitioners—Most dynamic speed limit control techniques used to manage traffic flow on highways rely on discretizations of partial differential equations, which require one to compute the solution on a computational grid. This article focuses on an alternate solution method that does not require the solution to be found on all grid points, potentially saving computational time on large-scale problems.

Traffic control is at the core of research in transportation engineering because it is one of the best practices for reducing traffic congestion. It has been shown in recent years that the traffic control problem involving Lighthill-Whitham-Richards (LWR) model can be formulated as a Linear Programming (LP) problem given that the corresponding initial conditions and the model parameters in the fundamental diagram are fixed. However, the initial conditions can be uncertain when studying actual control problems. This paper presents a stochastic programming formulation of the boundary control problem involving chance constraints, to capture the uncertainty in the initial conditions. Different objective functions are explored using this framework, and the proposed model is validated by conducting case studies for both a single highway link and a highway network. In addition, the accuracy of relaxed optimal results is proved using Monte Carlo simulation.

The effects of model parameter uncertainty on traffic flow control problems have recently drawn research attention. While the uncertainty in fundamental diagram related parameters has been investigated in the past, few articles have focused on network parameters uncertainty, including turning ratio uncertainty. To fill this gap, this article proposes a robust control model to deal with the uncertainties in the turning ratio by using distributionally robust chance constraints. The model allows one to compute the optimal control action that maximizes some objective, under all possible distributions of network parameters. We then apply this robust control framework to both a freeway network and an urban network, and evaluate the impact of uncertainty on optimal control inputs, over the test networks. The case studies show that compared to non-robust control, the proposed robust model can reduce congestion brought by the uncertainties and improve the overall throughput.

This paper investigates the practical engineering problem of traffic sensors placement on stretched highways with ramps. Since it is virtually impossible to install bulky traffic sensors on each highway segment, it is crucial to find placements that result in optimized network-wide, traffic observability. Consequently, this results in accurate traffic density estimates on segments where sensors arenotinstalled. The substantial contribution of this paper is the utilization of control-theoretic observability analysis—jointly with integer programming—to determine traffic sensor locations based on the nonlinear dynamics and parameters of traffic networks. In particular, the celebrated asymmetric cell transmission model is used to guide the placement strategy jointly with observability analysis of nonlinear dynamic systems through Gramians. Thorough numerical case studies are presented to corroborate the proposed theoretical methods and various computational research questions are posed and addressed. The presented approach can also be extended to other models of traffic dynamics.

This paper presents a novel optimization formulation to solve the problem of variable speed limit control on road networks modeled by the Lighthill-Whitham-Richards (LWR) partial differential equation. It also presents some mathematical rules that allow for a reduction in the size and computational time of the optimization problem. Using the analytical solutions to the LWR model, an optimization problem is formulated for the variable speed limit and ramp metering control of traffic on highway networks using the Lax-Hopf algorithm. The resulting problem, which is non-linear in the decision variables, is transformed into a Mixed Integer Linear Program. An example is presented to show the effectiveness of the approach, including its application to a real-world highway network with multiple ramp connections. The possibility of linear relaxation of integer variables in the problem is also considered. Lastly, the method is compared to a classical Link Transmission Model formulation of the variable speed limit control problem.

This paper presents an algorithmic framework for the distributed on-line source seeking, termed as DoSS, with a multi-robot system in an unknown dynamical environment. Our algorithm, building on a novel concept called dummy confidence upper bound (D-UCB), integrates both estimation of the unknown environment and task planning for the multiple robots simultaneously, and as a result, drives the team of robots to a steady state in which multiple sources of interest are located. Unlike the standard UCB algorithm in the context of multi-armed bandits, the introduction of D-UCB significantly reduces the computational complexity in solving subproblems of the multi-robot task planning. This also enables our DoSS algorithm to be implementable in a distributed on-line manner. The performance of the algorithm is theoretically guaranteed by showing a sub-linear upper bound of the cumulative regret. Numerical results on a real-world methane emission seeking problem are also provided to demonstrate the effectiveness of the proposed algorithm.

Monitoring and control of traffic networks represent alternative, inexpensive strategies to minimize traffic congestion. As the number of traffic sensors is naturally constrained by budgetary requirements, real-time estimation of traffic flow in road segments that are not equipped with sensors is of significant importance - thereby providing situational awareness and guiding real-time feedback control strategies. To that end, firstly we build a generalized traffic flow model for stretched highways with arbitrary number of ramp flows based on the Lighthill Whitham Richards (LWR) flow model. Secondly, we characterize the function set corresponding to the nonlinearities present in the LWR model, and use this characterization to design real-time and robust state estimators (SE) for stretched highway segments. Specifically, we show that the nonlinearities from the derived models are locally Lipschitz continuous by providing the analytical Lipschitz constants. Thirdly, the analytical derivation is then incorporated through a robust SE method given a limited number of traffic sensors, under the impact of process and measurement disturbances and unknown inputs. The estimator is based on deriving a convex semidefinite optimization problem. Finally, numerical tests are given showcasing the applicability, scalability, and robustness of the proposed estimator for large systems under high magnitude disturbances, parametric uncertainty, and unknown inputs.

Better machine understanding of pedestrian behaviors enables faster progress in modeling interactions between agents such as autonomous vehicles and humans. Pedestrian trajectories are not only influenced by the pedestrian itself but also by interaction with surrounding objects. Previous methods modeled these interactions by using a variety of aggregation methods that integrate different learned pedestrians states. We propose the Social Spatio-Temporal Graph Convolutional Neural Network (Social-STGCNN), which substitutes the need of aggregation methods by modeling the interactions as a graph. Our results show an improvement over the state of art by 20% on the Final Displacement Error (FDE) and an improvement on the Average Displacement Error (ADE) with 8.5 times less parameters and up to 48 times faster inference speed than previously reported methods. In addition, our model is data efficient, and exceeds previous state of the art on the ADE metric with only 20% of the training data. We propose a kernel function to embed the social interactions between pedestrians within the adjacency matrix. Through qualitative analysis, we show that our model inherited social behaviors that can be expected between pedestrians trajectories. Code is available at https://github.com/abduallahmohamed/Social-STGCNN.

Most probe vehicle data is generated using satellite navigation systems, such as the Global Positioning System (GPS), Globalnaya navigatsionnaya sputnikovaya Sistema (GLONASS), or Galileo systems. However, because of their high cost, relatively high position uncertainty in cities, and low sampling rate, a large quantity of satellite positioning data is required to estimate traffic conditions accurately. To address this issue, we introduce a new type of traffic monitoring system based on inexpensive inertial measurement units (IMUs) as probe sensors. IMUs as traffic probes pose unique challenges in that they need to be precisely calibrated, do not generate absolute position measurements, and their position estimates are subject to accumulating errors. In this paper, we address each of these challenges and demonstrate that the IMUs can reliably be used as traffic probes. After discussing the sensing technique, we present an implementation of this system using a custom-designed hardware platform, and validate the system with experimental data.

In this paper, a new sensing device that can simultaneously monitor traffic congestion and urban flash floods is presented. This sensing device is based on the combination of passive infrared sensors (PIRs) and ultrasonic rangefinder, and is used for real-time vehicle detection, classification, and speed estimation in the context of wireless sensor networks. This framework relies on dynamic Bayesian Networks to fuse heterogeneous data both spatially and temporally for vehicle detection. To estimate the speed of the incoming vehicles, we first use cross correlation and wavelet transform-based methods to estimate the time delay between the signals of different sensors. We then propose a calibration and self-correction model based on Bayesian Networks to make a joint inference by all sensors about the speed and the length of the detected vehicle. Furthermore, we use the measurements of the ultrasonic and the PIR sensors to perform vehicle classification. Validation data (using an experimental dual infrared and ultrasonic traffic sensor) show a 99% accuracy in vehicle detection, a mean error of 5 kph in vehicle speed estimation, a mean error of 0.7m in vehicle length estimation, and a high accuracy in vehicle classification. Finally, we discuss the computational performance of the algorithm, and show that this framework can be implemented on low-power computational devices within a wireless sensor network setting. Such decentralized processing greatly improves the energy consumption of the system and minimizes bandwidth usage.

Probe vehicles consist in mobile traffic sensor networks that evolve with the flow of vehicles, transmitting velocity and position measurements along their path, generated using GPSs. To address the urban positioning issues of GPSs, we propose to replace them with inertial measurement units onboard vehicles, to estimate vehicle location and attitude using inertial data only. While promising, this technology requires one to carefully calibrate the orientation of the device inside the vehicle to be able to process the acceleration and rate gyro data. In this article, we propose a scheme that can perform this calibration automatically by leveraging the kinematic constraints of ground vehicles, and that can be implemented on low-end computational platforms. Preliminary testing shows that the proposed scheme enables one to accurately estimate the actual accelerations and rotation rates in the vehicle coordinates.

Solar powered wireless sensor networks are very adapted to smart city applications, since they can operate for extended durations with minimal installation costs. Nonetheless, they require energy management schemes to operate reliably, unlike their grid-powered counterparts. Such schemes require the forecasting of future solar power inputs for each wireless sensor node, over a time horizon. They also require the determination of battery energy parameters in real time. To address both requirements, we propose a collaborative solar power forecasting framework combined to a real time battery capacity estimation model, which can be used to optimize the node schedules over the corresponding horizon.

Probe vehicle data is currently generated using satellite navigation systems such as the GPS, GLONASS or Galileo systems. However, because of their high cost and relatively high position uncertainty and low sampling rate, satellite positioning systems have a relatively low penetration rate among users. In addition, such sensors do not provide context in the traffic measurements. To address these issues, we introduce a new traffic monitoring concept based on inexpensive inertial measurement units in conjunction with a wireless sensor network deployed inside a city. After discussing the sensing technique, we present a preliminary implementation of this system using an open source robotic platform. Preliminary results show that this system can be used to generate traffic measurement data.

Reliable and accurate traffic sensing is the basis of Intelligent Transportation Systems (ITS), which mitigate traffic mobility and safety issues. To promote vast adoption of ITS technologies, rapid deployment and auto-calibration of traffic sensing systems are critical. Aiming at the development of an advanced traffic sensing system for construction zones, this poster presents our preliminary results for detecting vehicles and estimating traffic speeds by applying signal processing and machine learning techniques using Passive Infrared (PIR) sensor data.

Floods are the most common type of natural disaster, causing thousands of casualties every year. Among these events, urban flash floods are particularly deadly because of the short timescales on which they occur, and because of the high concentration of population in cities. Since most flash flood casualties are caused by a lack of information, it is critical to generate accurate and detailed warnings of flash floods. However, deploying an infrastructure that solely monitor flash floods makes little economic sense, since the average periodicity of catastrophic flash floods exceeds the lifetime of a typical sensor network. To address this issue, we propose a new sensing device that can simultaneously monitor urban flash floods and another phenomenon of interest (traffic congestion on the present case). This sensing device is based on the combination of an ultrasonic rangefinder with one or multiple remote temperature sensors. We show an implementation of this device, and illustrate its performance in both traffic flow and flash flood sensing. Field data shows that the sensor can detect vehicles with a 99% accuracy, in addition to estimating their speed and classifying them in function of their length. The same sensor can also monitor urban water levels with an accuracy of less than 2 cm. Two of the sensors have been deployed in a flood prone area, where they captured the only (minor) flash flood that occurred over the one-year test period, with no false detection, and an agreement in the estimated water level estimate (during the flash flood event) of about 2 cm.

We propose a new sensing device that can simultaneously monitor urban traffic congestion and another phenomenon of interest (flash floods on the present case). This sensing device is based on the combination of an ultrasonic rangefinder with one or multiple remote temperature sensors. We show an implementation of this device, and illustrate its performance in both traffic flow sensing. Field data shows that the sensor can detect vehicles with a 99% accuracy, in addition to estimating their speed and classifying them in function of their length. The same sensor can also monitor urban water levels with an accuracy of less than 2 cm.

This article describes the implementation of four different machine learning techniques for vehicle classification in a dual ultrasonic/passive infrared traffic flow sensors. Using k-NN, Naive Bayes, SVM and KNN-SVM algorithms, we show that KNN-SVM significantly outperforms other algorithms in terms of classification accuracy. We also show that some of these algorithms could run in real time on the prototype system.