Efficient Data Collection and Accurate Travel Time Estimation in a Connected Vehicle Environment Via Real-Time Compressive Sensing

Abstract

Connected vehicles (CVs) can capture and transmit detailed data such as vehicle position and speed through vehicle-tovehicle and vehicle-to-infrastructure communications. The wealth of CV data provides new opportunities to improve safety and mobility of transportation systems, which can overburden storage and communication systems. To mitigate this issue, we propose a compressive sensing (CS) approach that allows CVs to capture and compress data in real-time and later recover the original data accurately and efficiently. We evaluate our approach using two case studies. In the first study, we use our approach to recapture 10 million CV basic safety message (BSM) speed samples as well as other BSM variables. The results show that we can recover the original speed data with root-mean-squared error as low as 0.05 MPH. In the second study, a freeway traffic simulation model is built to evaluate the impact of our approach on travel time estimation. Multiple scenarios with various CV market penetration rates, On-board unit (OBU) capacities, compression ratios, arrival rate patterns, and data capture rates are simulated for our experiments. As a result, our approach provides more accurate estimation than conventional data collection methods by achieving up to 65% relative reduction in travel time estimation error. With a low compression ratio, our approach can still provide accurate estimation, therefore reducing OBU hardware costs. Lastly, our approach can improve travel time estimation accuracy when CVs are in traffic congestion as it provides a broader spatial-temporal coverage of traffic conditions and can accurately and efficiently recover the original CV data.

Long Short-Term Memory-Based Human-Driven Vehicle Longitudinal Trajectory Prediction in a Connected and Autonomous Vehicle Environment

“…This suggests that it may not be necessary to include all the information of the CAVs in communication range for the trajectory prediction. The proposed attention mechanism can potentially be useful for developing CAV communication protocols, for example, reducing CAV data or prioritizing CAV data transmission (14,15).…”

“…V2V and V2I can enable applications like cooperative collision warning, providing traffic signal status information in real time, and so on (13). CV applications require low-latency and high-reliability communications; therefore, efficient CV data capture and transmittal are of paramount importance (14,15).…”

“…In this study, the attention mechanism is used to combine historical trajectories of the target HDV and the relevant CAVs. The learned attention weights can indicate CAVs having larger impacts on the predictions, which help to understand human driving behaviors and potentially reduce the CAV data transmission burden (14,15). The dataset used in this study is the Next Generation Simulation (NGSIM) data which has been widely used in previous studies (3, 21-23, 26, 27).…”

Traffic Flow Density Model and Dynamic Traffic Congestion Model Simulation Based on Practice Case with Vehicle Network and System Traffic Intelligent Communication

“…The main goal is to present real solutions and show how important a traffic management system is based on hybrid communications like DSRC, V2X, V2V, and the newer VLC [25][26][27], transforming and improving the prohibitions and behavior of vehicles in the vicinity of the area. Thus, some cars can avoid the area if they are not conditioned by a certain problem, using an alternative route, a temporary way to transit the congested road sector.…”

Improving Probe-Based Congestion Performance Metrics Accuracy by Using Change Point Detection

“…In 2003, Bell and Lida defined travel time reliability as the probability of on-time arrival (Bell and Iida 2003). Lei Lin and his colleagues compared travel times calculated from connected vehicles to those from road sensors (Lin et al 2018(Lin et al , 2019. In addition, Lomax et al in the same year introduced travel time reliability as a variability of travel time that commuters experience and as a consistency of a specific mode during a certain period of time (Lomax et al 2003a, b).…”