Repeated Route Naturalistic Driving Dataset (R2ND2)

Citation Author(s):
Bikram
Adhikari
George Mason University
Zoran
Duric
George Mason University
Duminda
Wijesekera
George Mason University
Bo
Yu
George Mason University
Submitted by:
Bikram Adhikari
Last updated:
Mon, 01/06/2025 - 17:29
DOI:
10.21227/8z6x-e369
Data Format:
Research Article Link:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

Repeated Route Naturalistic Driving Dataset (R2ND2) is a dual-perspective dataset for driver behavior analysis constituent of vehicular data collected using task-specific CAN decoding sensors using OBD port and external sensors, and (b) gaze-measurements collected using industry-standard multi-camera gaze calibration and collection system. Our experiment is designed to consider the variability associated with driving experience that depends on the time of day and provides valuable insights into the correlation of these additional metrics on driver behavior. The data is collected among 10 participants with varying driving expertise. Each driver drive through highway and secondary route mapped in Route map section highlighted in our website: https://bikram11.github.io/Website_R2ND2/ ,  in morning, day and evening. The research is one of many efforts from Mason Living Innovation Lab towards safe driving practices and intelligent transportation systems

Instructions: 

The documentation files have been uploaded along with the dataset file in the zipped folder.

Welcome to R2ND2 Dataset repo.
_____________________________________________________________________
The folder structure follows for each participant:

-->Morning

    ---->Highway

        ------>Canbus
            ----> Canbus folder consists of Vehicular Kinematics data from OBD-scanner in the format {Participant_ID}_{Route_Type}_{Time_of_Day}.csv

        ------>IMU
            ----> IMU folder consists of Vehicular position data from IMU sensor in the format {Participant_ID}_{Route_Type}_{Time_of_Day}_IMU_DATA_YYYYMMDDHHmmSS.csv

        ------>SmartEye (Zipped Folder)
            ----> SmartEye folder is the main zipped content relating to driver gaze which is composed of:
                ---->Transforms folder with calibration file inside that represents the 9-point calibration for 3D gaze points to transform it to 2D image plane of external camera
                
                ---->Cam{000/001}_withGaze.mp4 is the external video recording with the gaze data mapped to the scene and also the frame number associated with data rows in the participant specific                  csv file.
                
                ---->Cam{000/001}_withGaze.txt is the details on the frame number and corresponding timestamp for each frame of video recordings which corresponds to numeric data elements in the csv                      file
        
                ---->Participant specific gaze measurement data in csv, the details regarding the column names and functions have been provided in a separate documentation.

    ---->Secondary

-->Day

-->Evening

_________________________________________________________________________________________________________________________________
In case of any confusion or if you observe any inconsistency with the data provided, kindly reach out to us at badhika5@gmu.edu