Detecting Imminent Lane Change Maneuvers in Connected Vehicle Environments

Self Cite

Lane changing is one of the main contributors to car crashes in the U.S. The complexity of the decision-making process associated with lane changing makes such maneuvers prone to driving errors, and hence, increases the possibility of car crashes. Thus, researchers have been investigating ways to model and predict lane changing maneuvers for optimally designed crash avoidance systems. Such systems rely on the accuracy of detecting the onset of lane-change maneuvers, which requires comprehensive vehicle trajectory data. Connected Vehicles (CV) data provide opportunities for accurate modeling of lane changing maneuvers, especially with the variety of advanced tools available nowadays. The review of the literature indicates that most of the implemented modeling tools do not achieve reliable accuracy for such critical safety application of lane-change prediction. Recently, eXtreme Gradient Boosting (XGB) became a well-recognized algorithm among the computer science community in solving classification problems due to its accuracy, scalability, and speed. This study implements the XGB in predicting the onset of lane changing maneuvers using CV trajectory data. The performance of XGB is compared to three other tree-based algorithms namely, decision trees, gradient boosting, and random forests. The Next Generation SIMulation trajectory data are used to represent the high-resolution CV data. The results indicate that XGB is superior to the other algorithms with a high accuracy value of 99.7%. This outstanding accuracy is achieved when considering vehicle trajectory data two seconds prior to a potential lane change maneuver. The findings of this study are promising for detection of lane change maneuvers in CV environments.

Section: Step 4: Evaluation Of Models' Performancementioning

confidence: 66%

mentioning

confidence: 99%

A Comparative Analysis of Tree-Based Ensemble Methods for Detecting Imminent Lane Change Maneuvers in Connected Vehicle Environments

Mousa

Bakhit

Osman

et al. 2018

Self Cite

“…Application of NGSIM data (US-101, I-80, and I-395) for analyzing lane change dynamics is significant in number because all the freeway sites contain multiple ramps. Most studies have focused on analyzing the lane changes microscopically in relation to duration, speed, acceleration and deceleration patterns, and key exogenous variables that might affect the lane change intent decisions ( 7 – 9 ).…”

Section: Literature Reviewmentioning

confidence: 99%

Lane Change Rates at Freeway Weaving Sites: Trends in HCM6 and from NGSIM Trajectories

Ahmed

Rouphail

et al. 2019

Concerns have been raised about the HCM6 weaving method’s lack of sensitivity to weaving segment length. This study explores the trends in HCM6 as they relate to lane change estimates and their impact on the segment speed and level of service (LOS). The study also compares HCM6 estimates of lane changes against empirical data from an NGSIM weaving site. Thus, the objectives of this study are twofold: ( a) critically investigate the effect of weaving length on lane change and associated speed model estimates in HCM6, and ( b) analyze trends in lane changes against congestion levels using detailed NGSIM trajectory data, comparing against HCM6 estimates. For ( a) it was found that the lack of sensitivity to weave length is because of the absence of this parameter in the nonweaving lane change and speed models. For ( b), a comparison of HCM6 lane change rates with NGSIM, US-101 data confirmed that the HCM6 estimates for weaving vehicles are fully consistent with those at the NGSIM site, controlling for density. In contrast, nonweaving lane change estimates in HCM6 did not deliver the expected trends, with more discretionary lane changes predicted as congestion increased. Finally, analysis of lane change patterns at the NGSIM site revealed a tendency for early merging for freeway to ramp traffic and uniform merging for ramp to freeway traffic over the length of the weave. Interestingly, a speed analysis showed that in most cases, a higher frequency of discretionary lane changes yielded lower travel times for drivers executing them.

“…Such data enable algorithmic development of in-vehicle systems. With the aid of vehicle connectivity, these systems can improve freeway traffic control (1-7), intersection traffic control (8)(9)(10)(11)(12)(13)(14), and safety (15)(16)(17)(18), and enable effective networklevel control and management (19-23).…”

mentioning

confidence: 99%

Application of Deep Learning for Characterization of Drivers’ Engagement in Secondary Tasks in In-Vehicle Systems

Osman

Rakha

2020

Self Cite

Distracted driving (i.e., engaging in secondary tasks) is an epidemic that threatens the lives of thousands every year. Data collected from vehicular sensor technologies and through connectivity provide comprehensive information that, if used to detect driver engagement in secondary tasks, could save thousands of lives and millions of dollars. This study investigates the possibility of achieving this goal using promising deep learning tools. Specifically, two deep neural network models (a multilayer perceptron neural network model and a long short-term memory networks [LSTMN] model) were developed to identify three secondary tasks: cellphone calling, cellphone texting, and conversation with adjacent passengers. The Second Strategic Highway Research Program Naturalistic Driving Study (SHRP 2 NDS) time series data, collected using vehicle sensor technology, were used to train and test the model. The results show excellent performance for the developed models, with a slight improvement for the LSTMN model, with overall classification accuracies ranging between 95 and 96%. Specifically, the models are able to identify the different types of secondary tasks with high accuracies of 100% for calling, 96%–97% for texting, 90%–91% for conversation, and 95%–96% for the normal driving. Based on this performance, the developed models improve on the results of a previous model developed by the author to classify the same three secondary tasks, which had an accuracy of 82%. The model is promising for use in in-vehicle driving assistance technology to report engagement in unlawful tasks or alert drivers to take over control in level 1 and 2 automated vehicles.