Scenario Classes in Naturalistic Driving: Autoencoder-based Spatial and Time-Sequential Clustering of Surrounding Object Trajectories

This paper develops a methodology for simultaneously modeling lane-changing and car-following behavior of automated vehicles on freeways. Naturalistic driving data from the Safety Pilot Model Deployment (SPMD) program are used. First, a framework to process the SPMD data is proposed using various data analytics techniques including data fusion, data mining, and machine learning. Second, pairs of automated host vehicle and their corresponding front vehicle are identified along with their lane-change and car-following relationship data. Using these data, a lane-changing-based car-following (LCCF) model, which explicitly considers lane-change and car-following behavior simultaneously, is developed. The LCCF model is based on Gaussian-mixture-based hidden Markov model theory and is disaggregated into two processes: LCCF association and LCCF dissociation. These categories are based on the result of the lane change. The overall goal is to predict a driver’s lane-change intention using the LCCF model. Results show that the model can predict the lane-change event in the order of 0.6 to 1.3 s before the moment of the vehicle body across the lane boundary. In addition, the execution times of lane-change maneuvers average between 0.55 and 0.86 s. The LCCF model allows the intention time and execution time of driver’s lane-change behavior to be forecast, which will help to develop better advanced driver assistance systems for vehicle controls with respect to lane-change and car-following warning functions.

Download Full-text

Built environment, driving errors and violations, and crashes in naturalistic driving environment

Accident Analysis & Prevention ◽

10.1016/j.aap.2021.106158 ◽

2021 ◽

Vol 157 ◽

pp. 106158

Author(s):

Numan Ahmad ◽

Behram Wali ◽

Asad J. Khattak ◽

Eric Dumbaugh

Keyword(s):

Built Environment ◽

Naturalistic Driving

Download Full-text

Autonomous Vehicles’ Car-Following Drivability Evaluation Based on Driving Behavior Spectrum Reference Model

Transportation Research Record Journal of the Transportation Research Board ◽

10.1177/0361198121994857 ◽

2021 ◽

pp. 036119812199485

Author(s):

Xiao Qi ◽

Ying Ni ◽

Yiming Xu ◽

Ye Tian ◽

Junhua Wang ◽

...

Keyword(s):

Autonomous Vehicles ◽

Reference Model ◽

Numerical Test ◽

Safety Evaluation ◽

Driving Behavior ◽

Car Following ◽

Driving Behaviors ◽

Human Driver ◽

Normal Human ◽

Naturalistic Driving

A large portion of the accidents involving autonomous vehicles (AVs) are not caused by the functionality of AV, but rather because of human intervention, since AVs’ driving behavior was not properly understood by human drivers. Such misunderstanding leads to dangerous situations during interaction between AV and human-driven vehicle (HV). However, few researches considered HV-AV interaction safety in AV safety evaluation processes. One of the solutions is to let AV mimic a normal HV’s driving behavior so as to avoid misunderstanding to the most extent. Therefore, to evaluate the differences of driving behaviors between existing AV and HV is necessary. DRIVABILITY is defined in this study to characterize the similarity between AV’s driving behaviors and expected behaviors by human drivers. A driving behavior spectrum reference model built based on human drivers’ behaviors is proposed to evaluate AVs’ car-following drivability. The indicator of the desired reaction time (DRT) is proposed to characterize the car-following drivability. Relative entropy between the DRT distribution of AV and that of the entire human driver population are used to quantify the differences between driving behaviors. A human driver behavior spectrum was configured based on naturalistic driving data by human drivers collected in Shanghai, China. It is observed in the numerical test that amongst all three types of preset AVs in the well-received simulation package VTD, the brisk AV emulates a normal human driver to the most extent (ranking at 55th percentile), while the default AV and the comfortable AV rank at 35th and 8th percentile, respectively.

Download Full-text

Machine Learning Approach for Predicting Lane-Change Maneuvers using the SHRP2 Naturalistic Driving Study Data

Transportation Research Record Journal of the Transportation Research Board ◽

10.1177/03611981211003581 ◽

2021 ◽

pp. 036119812110035

Author(s):

Anik Das ◽

Mohamed M. Ahmed

Keyword(s):

Machine Learning ◽

Prediction Accuracy ◽

Machine Learning Algorithms ◽

Support Vector ◽

Lane Change ◽

Adaptive Boosting ◽

Extreme Gradient Boosting ◽

Naturalistic Driving Study ◽

Naturalistic Driving ◽

Change Prediction

Accurate lane-change prediction information in real time is essential to safely operate Autonomous Vehicles (AVs) on the roadways, especially at the early stage of AVs deployment, where there will be an interaction between AVs and human-driven vehicles. This study proposed reliable lane-change prediction models considering features from vehicle kinematics, machine vision, driver, and roadway geometric characteristics using the trajectory-level SHRP2 Naturalistic Driving Study and Roadway Information Database. Several machine learning algorithms were trained, validated, tested, and comparatively analyzed including, Classification And Regression Trees (CART), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), Support Vector Machine (SVM), K Nearest Neighbor (KNN), and Naïve Bayes (NB) based on six different sets of features. In each feature set, relevant features were extracted through a wrapper-based algorithm named Boruta. The results showed that the XGBoost model outperformed all other models in relation to its highest overall prediction accuracy (97%) and F1-score (95.5%) considering all features. However, the highest overall prediction accuracy of 97.3% and F1-score of 95.9% were observed in the XGBoost model based on vehicle kinematics features. Moreover, it was found that XGBoost was the only model that achieved a reliable and balanced prediction performance across all six feature sets. Furthermore, a simplified XGBoost model was developed for each feature set considering the practical implementation of the model. The proposed prediction model could help in trajectory planning for AVs and could be used to develop more reliable advanced driver assistance systems (ADAS) in a cooperative connected and automated vehicle environment.

Download Full-text

Tracking by Deblatting

International Journal of Computer Vision ◽

10.1007/s11263-021-01480-w ◽

2021 ◽

Author(s):

Denys Rozumnyi ◽

Jan Kotera ◽

Filip Šroubek ◽

Jiří Matas

Keyword(s):

High Speed ◽

High Performance ◽

Motion Blur ◽

Velocity Estimation ◽

High Speed Camera ◽

Trajectory Function ◽

Novel Approach ◽

Blind Deblurring ◽

Object Trajectories ◽

Complex Trajectories

AbstractObjects moving at high speed along complex trajectories often appear in videos, especially videos of sports. Such objects travel a considerable distance during exposure time of a single frame, and therefore, their position in the frame is not well defined. They appear as semi-transparent streaks due to the motion blur and cannot be reliably tracked by general trackers. We propose a novel approach called Tracking by Deblatting based on the observation that motion blur is directly related to the intra-frame trajectory of an object. Blur is estimated by solving two intertwined inverse problems, blind deblurring and image matting, which we call deblatting. By postprocessing, non-causal Tracking by Deblatting estimates continuous, complete, and accurate object trajectories for the whole sequence. Tracked objects are precisely localized with higher temporal resolution than by conventional trackers. Energy minimization by dynamic programming is used to detect abrupt changes of motion, called bounces. High-order polynomials are then fitted to smooth trajectory segments between bounces. The output is a continuous trajectory function that assigns location for every real-valued time stamp from zero to the number of frames. The proposed algorithm was evaluated on a newly created dataset of videos from a high-speed camera using a novel Trajectory-IoU metric that generalizes the traditional Intersection over Union and measures the accuracy of the intra-frame trajectory. The proposed method outperforms the baselines both in recall and trajectory accuracy. Additionally, we show that from the trajectory function precise physical calculations are possible, such as radius, gravity, and sub-frame object velocity. Velocity estimation is compared to the high-speed camera measurements and radars. Results show high performance of the proposed method in terms of Trajectory-IoU, recall, and velocity estimation.

Download Full-text