Infrastructure-based cooperative perception has been researched for several years, but few automotive warning or control applications using this information have been published. Infrastructure sensing, such as with cameras or lidars, and a communication system, allows connected vehicles to receive information about all observed objects. An SAE standard, “V2X Sensor-Sharing for Cooperative and Automated Driving” (J3224), released in 2022, introduces the Sensor Data Sharing Message (SDSM) as the standard communication message for cooperative perception. This paper investigates the use of the SDSM for a vehicle application to provide warnings of potential collisions with vulnerable road users who will cross the street at the intersection. The application was tested in CARLA simulation under various roadside detection errors and communication conditions to assess the impact on the on-board application and estimate the minimum detection and communication requirements for effective use. In addition, the system was implemented and evaluated at the Mcity test facility. The results demonstrate that the proposed warning system can accurately and promptly warn the driver, given specific communication conditions, and show that the SDSM is viable for real-time on-board usage.

Roadside perception has become a critical component for connected and automated vehicles (CAVs), enhancing safety and offering a comprehensive view of the traffic environment that onboard detection systems alone cannot provide. By supplementing the limitations of onboard sensors, roadside perception systems improve the accuracy and reliability of detecting and localizing vehicles and pedestrians in challenging locations. Currently, a variety of cameras, including fisheye and regular cameras, are deployed along roadsides for surveillance purposes. These sensors have significant potential to improve vehicle and pedestrian detection. This paper extends our previous work on single image sensor vehicle detection by developing a comprehensive multiple sensor fusion framework. We take advantage of the complementary strengths of multiple fisheye and regular cameras to enhance the accuracy and robustness of the perception system. The proposed system has been extensively tested in Mcity, a controlled urban testing environment, through numerous field tests. The results demonstrate the effectiveness of our approach, showcasing promising improvements in vehicle and pedestrian detection and tracking accuracy.

Vehicle behavior prediction in complex urban scenarios with traffic signals and interactive agents is an important yet complicated task for autonomous vehicles (AVs). In this work, a hierarchical vehicle behavior prediction framework is proposed to incorporate the traffic signal information and model the interaction between vehicles. The framework predicts vehicle behaviors in two stages, discrete intention prediction and continuous trajectory prediction. In the discrete intention prediction stage, Bayesian network is adopted to provide a high-level behavior prediction of the principle other vehicle. The discrete prediction results are forwarded to the second stage, where a continuous trajectory is predicted with maximum entropy inverse reinforcement learning and potential game. The framework is designed to be able to capture the difference among human drivers with parameterized driver characteristics. The proposed predictor is validated in two scenarios: the yellow light running scenario and the right-turn scenario. The trajectory prediction average displacement error of the yellow light running scenario is 0.695m for a 3-second prediction interval, and the prediction accuracy of the right-turn vehicle in the right-turn scenario is 0.51m for a 2-second prediction interval.

We propose a novel and pragmatic framework for traffic scene perception with roadside cameras. The proposed framework covers a full-stack of roadside perception pipeline for infrastructure-assisted autonomous driving, including object detection, object localization, object tracking, and multi-camera information fusion. Unlike previous vision-based perception frameworks rely upon depth offset or 3D annotation at training, we adopt a modular decoupling design and introduce a landmark-based 3D localization method, where the detection and localization can be well decoupled so that the model can be easily trained based on only 2D annotations. The proposed framework applies to either optical or thermal cameras with pinhole or fish-eye lenses. Our framework is deployed at a two-lane roundabout located at Ellsworth Rd. and State St., Ann Arbor, MI, USA, providing$7\times 24$real-time traffic flow monitoring and high-precision vehicle trajectory extraction. The whole system runs efficiently on a low-power edge computing device with all-component end-to-end delay of less than 20ms.

Intelligent Traffic Signal Control (ITSC) systems have attracted the attention of researchers and the general public alike as a means of alleviating traffic congestion. Recently, the vehicular wireless technologies have enabled a cost-efficient way to achieve ITSC by detecting vehicles using Vehicle to Infrastructure (V2I) wireless communications. Traditional ITSC algorithms, in most cases, assume that every vehicle is detected, such as by a camera or a loop detector, but a V2I implementation would detect only those vehicles equipped with wireless communications capability. We examine a family of transportation systems, which we will refer to as `Partially Detected Intelligent Transportation Systems'. An algorithm that can perform well under a small detection rate is highly desirable due to gradual increasing penetration rates of the underlying technologies such as Dedicated Short Range Communications (DSRC) technology. Reinforcement Learning (RL) approach in Artificial Intelligence (AI) could provide indispensable tools for such problems where only a small portion of vehicles are detected by the ITSC system. In this paper, we report a new RL algorithm for Partially Detected Intelligent Traffic Signal Control (PD-ITSC) systems. The performance of this system is studied under different car flows, detection rates, and types of the road network. Our system is able to efficiently reduce the average waiting time of vehicles at an intersection, even with a low detection rate, thus reducing the travel time of vehicles.

With the rapid advances in vehicle-to-vehicle (V2V) communications, interest for leveraging V2V communications for different applications has also grown exponentially. Leader selection is an important task required in a number of V2V communications related applications. In this paper, a distributed leader selection algorithm is introduced for vehicular ad-hoc networks (VANET) over unreliable V2V communications. The algorithm is simple, lightweight, and tightly integrated with SAE 2735 protocol for vehicular networks. The goal of the algorithm is to provide a robust leader selection method for a group of vehicles to determine a temporary leader in a short time, which could benefit several newly proposed applications based on V2V in traffic control and autonomous driving related areas. Simulation results have verified the excellent convergence time, robustness, and other aspects of the algorithm.

Traffic congestion in major cities around the globe is a daunting problem that is getting worse as the speed of urbanization keeps increasing. The role of traffic lights (TLs) at intersections in regulating flows cannot be underestimated. Even though there are a variety of actuated traffic signals based on cameras or loop detectors, the vast majority of existing TLs in the world employ a timer-based decision logic which is clearly not very effective. In this paper, we present a new scheme for controlling traffic at intersections, which is known as dedicated short-range communications (DSRCs)-actuated traffic control. The proposed approach leverages the presence of DSRC radios in vehicles and gives priority (by displaying green light) to approaches (roads) that include DSRC-equipped vehicles (such as 10% or 20% of vehicles having DSRC radios). Using this priority mechanism, it is shown that the average waiting time at each TL can be significantly reduced. This, in turn, can reduce the average commute time of urban workers during rush hours substantially. One of the great advantages of the presented approach is that it can function well with even a low percentage of DSRC-equipped vehicles. Given that many industry forecasts predict a gradual penetration rate for the DSRC technology, this is a very attractive feature. It is also shown that the proposed new approach leads to a cost-effective solution for urban traffic control since the hardware and software platforms needed for its implementation are low cost.

Partially Detected Intelligent Traffic Signal Control(PD-ITSC) systems that can optimize traffic signals based on limited detected information could be a cost-efficient solution for mitigating traffic congestion in the future. In this paper, we focus on a particular problem in PD-ITSC - adaptation to changing environments. To this end, we investigate different reinforcement learning algorithms, including Q-Learning, Proximal Policy Optimization (PPO), Advantage Actor-Critic (A2C), and Actor-Criticwith Kronecker-Factored Trust-Region (ACKTR). Our findings suggest that RL algorithms can find optimal strategies under partial vehicle detection; however, policy-based algorithms can adapt to changing environments more efficiently than value-based algorithms. We use these findings to draw conclusions about the value of different models for PD-ITSC systems.

As traffic congestion becomes a huge problem for most developing and developed countries across the world, intelligent transportation systems (ITS) are becoming a hot topic that is attracting attention of researchers and the general public alike. In this paper, we demonstrate a specific implementation of an ITS system whereby traffic lights are actuated by DSRC radios installed in vehicles. More specifically, we report the design of prototype of a DSRC-Actuated Traffic Lights (DSRC-ATL) system. It is shown that this system can reduce the travel time and commute time significantly, especially during rush hours. Furthermore, the results reported in this paper do NOT assume or require all vehicles to be equipped with DSCR radios. Even with low penetration ratios, e.g., when only 20% of all vehicles in a city are equipped with DSRC radios, the overall performance of the designed system is superior to the current traffic control systems.

Traffic congestion is a daunting problem that is affecting the daily lives of billions of people across the world. Recently, a promising new traffic control scheme known as Virtual Traffic Lights (VTL) has been proposed for mitigating traffic congestion. VTL is an infrastructure free traffic control scheme that leverages the presence of Vehicle-to-Vehicle (V2V) communications. Such infrastructure free scheme has several benefits, such as alleviating traffic congestion; reducing the large cost of traffic lights and traffic control systems; reducing carbon emission, etc. This paper reports a DSRC-based prototype design effort on VTL using Dedicated Short Range Communications (DSRC) technology. The experiments performed show the feasibility of implementing VTL with DSRC technology. Preliminary results of the field tests conducted in Pittsburgh with vehicles using VTL equipment indicate that VTL is capable of coordinating traffic at intersections and reducing the commute time of people.

Modern vehicles are equipped with more and more sophisticated computer modules, which need to periodically download files from the cloud, such as security certificates, digital maps, system firmwares, etc. Collaborative content distribution utilizes V2V communication to distribute large files across the vehicular networks. It has the potential to significantly reduce the cost of cellular-based communication such as 4G LTE. In this report, we have conducted a simulation study to verify the feasibility of a hybrid cellular and V2V collaborative content distribution network. In our simulation, a small portion of the simulated vehicles download the file directly from the cloud via cellular communication, while other vehicles receive the file via collaborative V2V communications. Our simulation results show that, with only 1% of vehicles enabled with cellular communication, it takes less than 24 hours to distribute a file to 90% of the vehicles in a metropolitan area, and around 48 to 72 hours to distribute to 99%. The results are very promising for many delay-tolerant content distribution applications in vehicular networks.