Unconnected Vehicles Research Articles

Energy-Efficient Connected and Automated Vehicles: Real-Time Traffic Prediction-Enabled Co-Optimization of Vehicle Motion and Powertrain Operation

Connected and automated vehicles (CAVs) can bring energy, mobility, and safety benefits to transportation. Energy savings can be achieved by solving a mathematical optimization problem for a lookahead horizon using previewed traffic information enabled by connectivity. However, it is challenging to predict shortterm traffic, especially for mixed-traffic scenarios, where both connected and unconnected vehicles are on the road.

Awareness Assessment of Connected Vehicles in Highway Driving: A Perceived Safety Approach

This article showcases a perceived safety analysis framework to assess the awareness of connected vehicles (CVs) of surrounding safety-critical vehicles. We study two classes of messages that a CV can transmit: 1) messages containing information about the transmitter only [e.g., standardized basic safety messages (BSMs) and cooperative awareness messages (CAMs)], and 2) messages that aggregate information about the transmitter and surrounding objects detected by their onboard sensors [e.g., collective perception messages (CPMs)]. We show how the proposed framework allows one to identify safety-critical vehicles and the effect of the type of transmitted messages on the awareness of these critical vehicles. To evaluate the performance, we use experimental data with mixed traffic of unconnected vehicles and CVs at different penetration ratios. Results show that CPMs are significantly more effective at providing awareness of safety-critical vehicles at low-to-mid-connectivity penetrations. At high-connectivity penetrations, messages with only information about the transmitter are sufficient to provide full awareness without burdening the wireless channel.

Road Boundary-Enhanced Automatic Background Filtering for Roadside Lidar Sensors

The roadside-deployed lidar sensor provides a solution to obtain the real-time, high-resolution micro traffic data (HRMTD) of all road users in the mixed traffic situation (connected vehicles and unconnected vehicles both exist on the roads). Background filtering is a necessary and important step for the HRMTD collection to serve the connected vehicle. Without excluding the background points, the accuracy of Euclidean-based object clustering and tracking algorithms can be reduced. The widely used method-3D-density-statistic filtering (3D-DSF) for roadside lidar background filtering can effectively exclude the background points for free-flow conditions. However, the performance of 3D-DSF can be greatly influenced by congested traffic conditions. This article presents a revised 3D-DSF algorithm to automatically extract background points by involving the road-boundary information. This new method is named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">road-boundary-enhanced, 3D-density statistic filtering</i> ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3D-DSFRB</i> ). This algorithm involves the boundary of the historical trajectories of road users as the region of interest (ROI) to enhance the accuracy of background filtering. A revised grid-based method was developed for road-boundary ID. The 3D-DSF was only applied for the area outside of the ROI. Within the ROI, only ground surface was excluded. Case studies were conducted to evaluate the effectiveness of the 3D-DSFRB algorithm. The results showed that the 3D-DSFRB can filter background points for both free-flow conditions and congested traffic conditions. The time cost of the 3D-DSFRB was also reduced compared to the 3D-DSF. Compared to the state of the art, the 3D-DSFRB improved the accuracy of background filtering.

Automatic Vehicle Tracking with LiDAR-Enhanced Roadside Infrastructure

Abstract Vehicle tracking technology is a prerequisite for the connected-vehicle (CV) system. However, a mixture of CV and unconnected vehicles will be under normal conditions on roads in the near future. How to obtain the real-time traffic status of unconnected vehicles remains a challenge for traffic engineers. The roadside Light Detection and Ranging (LiDAR) sensor provides a solution for collecting real-time high-resolution micro traffic data of all road users (CV and unconnected vehicles). This article developed a systematic procedure for vehicle tracking using the roadside LiDAR sensors. The procedure can be divided into five major parts: point registration, background filtering, point clustering, object classification, and vehicle tracking. For each step, the corresponding data processing algorithms were provided. A field test was conducted to evaluate the performance of the proposed method. Compared to the state-of-the-art method, the proposed methods can track vehicles with higher accuracy and lower computation loads.

Cooperative Adaptive Cruise Control With Unconnected Vehicle in the Loop

To improve the usability of cooperative adaptive cruise control (CACC) in the mixed traffic, a CACC algorithm with unconnected vehicle in the loop (CACCu) is proposed. Unlike the traditional CACC that requires a connected preceding vehicle or otherwise degrades to adaptive cruise control (ACC), CACCu aims to closely follow an unconnected preceding vehicle utilizing the information from the further (connected) preceding vehicle. Moreover, CACCu can robustly maintain string stability given various behaviors of unconnected preceding vehicles, without requiring identification process or extra information on the unconnected vehicles. For the sake of simplicity, this paper starts with CACCu in the three-vehicle sandwich scenario (i.e., one unconnected vehicle is in between of two connected vehicles), but derivatively, this control design is extended and evaluated in multiple-unconnected-vehicle cases. It is proven that by attaching a filter of ``virtual preceding vehicle'' to the original feedforward filter, the CACCu vehicle can stay string-stable at a gap significantly shorter than that required by ACC, given almost all kinds of car-following behaviors of the unconnected vehicle. At last, the favorable properties of CACCu are validated in high-fidelity simulations using real vehicle trajectory data and a physics-based vehicle dynamics model. The results show that CACCu outperforms existing ACC and acceleration-based connected cruise control (CCC) in string stability, ride comfort, safety maintenance, and fuel consumption.

A real-time network-level traffic signal control methodology with partial connected vehicle information

This paper presents two algorithms to estimate traffic state in urban street networks with a mixed traffic stream of connected and unconnected vehicles and incorporates them in a real-time and distributed traffic signal control methodology. The first algorithm integrates connected vehicles (CV) and loop detector data to estimate the trajectory of unconnected vehicles based on car-following concepts. The second algorithm converts the temporal point vehicle detections to a spatial vehicle distribution on a link. The signal control methodology utilizes either algorithm to estimate traffic state on all network links at a time, optimizes the signal timing parameters over a prediction period constituting several time steps, implements the optimal decisions in the next time step, and continues this process until the end of the study period. We applied the methodology to a real-world case study network simulated in Vissim. The results show that both algorithms are effective under a wide range of CV market penetration rates in all tested demand patterns: at 0% market penetration rate, the proposed methodology reduced travel time by 2% to 10% and average delay by 7% to 20% compared to the existing signal timing parameters and traffic demand. At a 40% penetration rate, the proposed algorithms reduced travel time by 27% to 33%and average delay by 50% to 61% compared to the existing signal and demand pattern in the case study network. Similar trends were found for all other demand patterns tested in this study.

Building a Lane Merge Coordination for Connected Vehicles Using Deep Reinforcement Learning

This article presents a data-driven framework for trajectory recommendation in automated and cooperative driving. The considered cooperative driving maneuver is lane-merge coordination, and while the trajectory recommendation can only be communicated to the connected vehicles, in computation of those recommendations both connected and unconnected vehicles are taken into account. The data-driven framework is implemented centrally, comprising of two main components of a traffic orchestrator (TO) and data fusion (DF). The TO predicts the safest trajectories for connected vehicles involved in the lane-merge maneuver. The DF incorporates camera detected vehicles in order to map all vehicles, including connected and unconnected. To this end, the recommendations are built using various state-of-the-art machine learning (ML) techniques, including deep reinforcement learning and dueling deep Q-network. Our evaluations are conducted using the real-system deployed in the test track, with a mix of connected and unconnected vehicles. The results demonstrate the precision of predicted trajectories, and the percentage of successful lane merge achieved deploying different ML techniques.

An automatic lane identification method for the roadside light detection and ranging sensor

The roadside Light Detection and Ranging (LiDAR) sensor can provide the high-resolution micro traffic data (HRMTD) of all road users by collecting real-time point clouds in three-dimensional (3D) space. The HRMTD collected by the roadside LiDAR provides a solution to fill the data gap under the mixed situation (both connected vehicles and unconnected vehicles exist on the roads) for connected vehicle technologies. Lane identification is important information in HRMTD. The current lane identification algorithms are mainly developed for autonomous vehicles, which could not be directly used to process roadside LiDAR data. This article provides an innovative algorithm to automatically identify traffic lanes for the roadside LiDAR data. The proposed lane identification algorithm includes five major steps: background filtering, point clustering, object classification, frame aggregation, and traversal search. The parameters used in the algorithm are selected by balancing the time cost and the accuracy. With the GPS information, the location of the lane can be transferred into the GoogleEarth and be compared with the location of the lane in real world. The testing results showed that the average distance error (ADE) compared to the real location in Google Earth was less than 0.1 m. This robust lane identification can release engineers from the manual lane identification task and avoid any error caused by manual work. The extracted lane locations can be used for researchers and practitioners to locate the vehicles precisely in different applications.

Automatic Lane Identification Using the Roadside LiDAR Sensors

How to collect the real-time information of unconnected vehicles has been a challenge for connected vehicle technologies. The LiDAR sensors deployed along the roadside and at intersections provide a solution to fill the data gap during the transition from the traditional traffic to the full connected traffic. The roadside LiDAR sensors can record the movement of all road users with a relative long detection range. The lane detection serves as a fundamental but important step for LiDAR data processing. The location (which lane is occupied) of vehicles can be used for lane changing detection, vehicle departure warning and wrong-way alerts. But currently, there is not an effective method to identify the boundary of lanes using roadside LiDAR sensors. This paper presents a systematic procedure for lane detection based on the trajectories of vehicles collected on the road with the roadside LiDAR sensor. The whole procedure includes two major parts: background filtering and road boundary identification. This robust procedure can release engineers from the manual lane identification task and can avoid any error caused by manual work. Two case studies confirmed the effectiveness of the proposed method. Compared to previous lane detection methods, this procedure is not affected by the existence of pedestrians. This method can also detect the boundaries of lanes from the roads having curves with the limited time cost.

Lane change identification and prediction with roadside LiDAR data

Lane change identification and lane change prediction are important tasks for the Connected-Vehicle (CV) technologies. Since both connected vehicles and non-connected vehicles may exist on the roads for a long time, the real-time information of the unconnected traffic could not be obtained by the current CV network. Therefore, lane change identification and lane change prediction could not be achieved with the missing traffic information of the unconnected vehicles. The roadside Light Detection and Ranging (LiDAR) provides a solution to fill the data gap under the mixed traffic situation. This paper developed the methods of lane change identification and prediction based on the vehicle trajectories extracted from the roadside LiDAR data. Lane boundaries were used to enhance the accuracy of lane change identification. The proposed method was evaluated using real-world data. The results showed that the proposed method can achieve the relatively high accuracy. The lane change information can be used to develop the lane-change warning system for the CV network.

Automatic Ground Points Identification Method for Roadside LiDAR Data

Roadside light detection and ranging (LiDAR) provides a solution to fill the data gap under mixed traffic situations. The real-time high-resolution micro traffic data (HRMTD) of all road users from the roadside LiDAR sensor provides a new opportunity to serve the connected-vehicle system during the transition period from unconnected vehicles to connected vehicles. Ground surface identification is the basic data processing step for HRMTD collection. The current ground points identification algorithms based on airborne and mobile LiDAR do not work for roadside LiDAR. A novel algorithm is developed in this paper to identify and exclude ground points based on the features of LiDAR, terrain, and point density in the space. The scan feature of different beams is used to search ground points. The whole procedure can be divided into four major parts: points clustering in each beam, slope-based filtering, shape-based filtering, and ground points matrix extraction. The proposed algorithm was evaluated using the real-world LiDAR data collected at different scenarios. The results showed that this algorithm can be used for ground points exclusion under different situations (differing terrain types, weather situations, and traffic volumes) with high accuracy. This algorithm was compared with previously developed algorithms. The overall performance of the proposed algorithm is superior. The low computational load guarantees this method may be applied for real-time data processing.

Connected Vehicle as a Mobile Sensor for Real Time Queue Length at Signalized Intersections.

With the development of intelligent transportation system (ITS) and vehicle to X (V2X), the connected vehicle is capable of sensing a great deal of useful traffic information, such as queue length at intersections. Aiming to solve the problem of existing models’ complexity and information redundancy, this paper proposes a queue length sensing model based on V2X technology, which consists of two sub-models based on shockwave sensing and back propagation (BP) neural network sensing. First, the model obtains state information of the connected vehicles and analyzes the formation process of the queue, and then it calculates the velocity of the shockwave to predict the queue length of the subsequent unconnected vehicles. Then, the neural network is trained with historical connected vehicle data, and a sub-model based on the BP neural network is established to predict the real-time queue length. Finally, the final queue length at the intersection is determined by combining the sub-models by variable weight. Simulation results show that the sensing accuracy of the combined model is proportional to the penetration rate of connected vehicles, and sensing of queue length can be achieved even in low penetration rate environments. In mixed traffic environments of connected vehicles and unconnected vehicles, the queuing length sensing model proposed in this paper has higher performance than the probability distribution (PD) model when the penetration rate is low, and it has an almost equivalent performance with higher penetration rate while the penetration rate is not needed. The proposed sensing model is more applicable for mixed traffic scenarios with much looser conditions.

Tracking Multi-Vehicles With Reference Points Switches at the Intersection Using a Roadside LiDAR Sensor

Obtaining real-time trajectories with high accuracy and high resolution of connected and unconnected vehicles with roadside LiDAR (Light Detecting and Ranging) sensors can highly benefit connected vehicle (CV) systems. In order to track vehicles with a roadside LiDAR sensor, the vehicle-corner point with the shortest distance to the sensor is usually used as the reference point since only parts of the vehicle can be scanned, but trajectory interruptions and speed errors caused by neglecting reference point switch were observed. With the movement of a vehicle, the reference point may switch from one corner point to another, especially at the intersection where it may switch more than once when turning left/right. Moreover, the vehicles with various lengths will increase the impacts of reference point switch on tracking. This paper proposes a tracking method considering reference point switch and occlusions for multi-vehicles at the intersection based on a roadside LiDAR sensor. In particular, reference point switch patterns are deeply explored and trajectory prediction for occlusions based on Kalman filtering method is developed. Then they are integrated into a global nearest neighbor (GNN) method for pairing reference points between frames. At last, the proposed method was validated by LiDAR data collected by a 32-channel 360-degree LiDAR sensor at the intersection of McCarran Blvd and Evans Ave in the city of Reno, Nevada, U.S. The new approach correctly captured switches of vehicle reference points and solved short-term occlusion issues to avoid trajectory interruptions, speed errors, and corner point misrecognitions.

LiDAR-Enhanced Connected Infrastructures Sensing and Broadcasting High-Resolution Traffic Information Serving Smart Cities

Connected-vehicle system is an important component of smart cities. The complete benefits of connected-vehicle technologies need the real-time information of all vehicles and other road users. However, the existing connected-vehicle deployments obtain the real-time status of connected vehicles, but without knowing the unconnected traffic since there are still many unconnected vehicles and pedestrians on the roads. Therefore, it is urgent to find an approach to collect the high-resolution real-time status of unconnected road users. When it is difficult for all vehicles, pedestrians, and bicyclists to broadcast their real-time status in the near future, enhancing the traffic infrastructures to actively sense and broadcast each road user's status is an intuitive solution to fill the data gap. This paper introduces a new-generation LiDAR-enhanced connected infrastructures that can actively sense the high-resolution status of surrounding traffic participants with roadside LiDAR sensors and broadcast connected-vehicle messages through DSRC roadside units. The system architecture, the LiDAR data processing procedure, the data communication, and the first pilot implementation at an intersection in Reno, Nevada are included in this paper. This research is the start of the new-generation connected infrastructures serving connected/autonomous vehicles with the roadside LiDAR sensors. It will accelerate the deployment of the connected network for the smart cities to improve traffic safety, mobility, and fuel efficiency.

Road-Speed Profile for Enhanced Perception of Traffic Conditions in a Partially Connected Vehicle Environment

Anticipative driving of vehicles, considering the microscopic dynamics of the preceding traffic, can bring great improvement in the traffic flows in a connected vehicle environment (CVE), where 100% vehicles frequently share their states using vehicle-to-vehicle communication technology. This paper addresses a partially CVE, where unconnected (manually driven) vehicles are mixed in the traffic, and proposes a novel method of comprehending traffic conditions that can be used for realizing highly anticipative driving. More specifically, we refer to anticipative driving as the predictive control of a host vehicle considering its preceding traffic conditions in an extended view. For enhanced perception of the traffic conditions on the road, a road-speed profile is proposed that concisely describes the mean speed in each small segment or cell of the road by effectively extracting information from traffic big data, i.e., broadcasted data from all surrounding vehicles to the host vehicle. This process of dynamically approximating the road-speed profile is performed in two steps. First, a conditional persistence prediction model is proposed to estimate the future states of the connected vehicles. Such predicted states can sufficiently compensate missing data from any unconnected vehicles. Second, the predicted time, position, and speed of the vehicles are then mapped onto the road cells, and subsequently, the corresponding cell speed is tuned by employing the weighted-moving average technique. Accuracy of both the persistence prediction model and the road-speed profile are empirically evaluated for different penetration of the connected vehicles. Finally, an anticipative driving scheme in a model predictive control framework is developed by incorporating the proposed road-speed profile, and performance of the anticipative driving is compared with the existing scheme that needs the CVE.

3-D Data Processing to Extract Vehicle Trajectories from Roadside LiDAR Data

High-resolution vehicle data including location, speed, and direction is significant for new transportation systems, such as connected-vehicle applications, micro-level traffic performance evaluation, and adaptive traffic control. This research developed a data processing procedure for detection and tracking of multi-lane multi-vehicle trajectories with a roadside light detection and ranging (LiDAR) sensor. Different from existing methods for vehicle onboard sensing systems, this procedure was developed specifically to extract high-resolution vehicle trajectories from roadside LiDAR sensors. This procedure includes preprocessing of the raw data, statistical outlier removal, a Least Median of Squares based ground estimation method to accurately remove the ground points, vehicle data clouds clustering, a principle component-based oriented bounding box method to estimate the location of the vehicle, and a geometrically-based tracking algorithm. The developed procedure has been applied to a two-way-stop-sign intersection and an arterial road in Reno, Nevada. The data extraction procedure has been validated by comparing tracking results and speeds logged from a testing vehicle through the on-board diagnostics interface. This data processing procedure could be applied to extract high-resolution trajectories of connected and unconnected vehicles for connected-vehicle applications, and the data will be valuable to practices in traffic safety, traffic mobility, and fuel efficiency estimation.

Evaluating Connected Vehicles and Their Applications

This article presents evaluation results of connected vehicles and their applications. Vehicle-to-vehicle communication (V2V) and vehicle-to-infrastructure communication (V2I) can enable a new paradigm of vehicle applications. The connected vehicle applications could significantly improve vehicle safety, mobility, energy savings, and productivity by utilizing real-time vehicle and traffic information. In the foreseeable future, connected vehicles need to operate alongside unconnected vehicles. This makes the evaluation of connected vehicles and their applications challenging. The hardware-in-the-loop (HIL) testbed can be used as a tool to evaluate the connected vehicle applications in a safe, efficient, and economic fashion. The HIL testbed integrates a traffic simulation network with a powertrain research platform in real time. Any target vehicle in the traffic network can be selected so that the powertrain research platform will be operated as if it is propelling the target vehicle. The HIL testbed can also be connected to a living laboratory where actual on-road vehicles can interact with the powertrain research platform.