README for "ATMA for Work Zone Safety" dataset.
Strengthening Mobility and Revolutionizing Transportation (SMART) Program, U.S. Department of Transportation (USDOT)
2025-10-28

----------------------------------------------------------------
LINKS TO DATASET
----------------------------------------------------------------

A. Dataset archive link: https://doi.org/10.21949/53ca-8v96
B. Data Management Plan DOI: https://doi.org/10.48321/D1A9B14294


----------------------------------------------------------------
SUMMARY OF DATASET
----------------------------------------------------------------
We collected and archived operational log messages from ATMA systems deployed in Colorado, Wisconsin, Minnesota, and Oklahoma. The log files are automatically generated by each ATMA’s onboard control computer and record detailed information on system behavior, vehicle dynamics, and navigation status during deployment. The dataset totals approximately 1.4 GB and includes around 3,800 CSV files organized by state and date of collection.



----------------------------------------------------------------
TABLE OF CONTENTS
----------------------------------------------------------------

A. General Information
B. Sharing/Access & Policies Information
C. Data and Related File Overview
D. Methodological Information
E. Data-Specific Information for: [dataset title here]
F. Update Log


----------------------------------------------------------------
A. GENERAL INFORMATION
----------------------------------------------------------------

0. Title of Dataset: "ATMA for Work Zone Safety Dataset"


1. Description of Dataset: We collected and archived operational log messages from ATMA systems deployed in Colorado, Wisconsin, Minnesota, and Oklahoma. The log files are automatically generated by each ATMA’s onboard control computer and record detailed information on system behavior, vehicle dynamics, and navigation status during deployment. The dataset totals approximately 1.4 GB and includes around 3,800 CSV files organized by state and date of collection.

   

2. Dataset archive link: https://doi.org/10.21949/53ca-8v96


3. Authorship Information: "Add more authors and contributors as needed"
   Principal Data Creator or Data Manager Contact Information
      Name: Xianbiao Hu
      ORCID: 0000-0002-0149-1847
      Institution: Pennsylvania State University 
      Address: 282 ECoRE building, University Park, PA, 16801
      Email: xbhu@psu.edu

   Associate Data Creator or Data Manager Contact Information
      Name: Heather Pickering-Hilgers
      ORCID: 0009-0002-9449-1463
      Institution: Colorado Department of Transportation
      Address: 2829 W. Howard Place, Denver CO 80204
      Email: heather.pickeringhilgers@state.co.us
	   
	   
4. Date of data collection and update interval: 2024-2025; monthly;
   

5. Geographic location of data collection: United States of America


6. Information about funding sources that supported the collection of the data:
This dataset package was funded through the USDOT Strengthening Mobility and Revolutionizing Transportation (SMART) Program. The grant number for this project is: SMARTFY22N1P1G16



----------------------------------------------------------------
B. SHARING/ACCESS & POLICIES INFORMATION 
----------------------------------------------------------------

0. Recommended citation for the data: 
   Hu, Xianbiao, Pickering-Hilgers, Heather (2025). ATMA for Work Zone Safety. https://doi.org/10.21949/53ca-8v96.


1. Licenses/restrictions placed on the data:
   These data are in the Public Domain.


2. Was data derived from another source?:
   No.
   
   
3. This dataset and its documentation was created and shared to meet the requirements enumerated in the U.S. Department of Transportation's "Plan to Increase Public Access to the Results of Federally-Funded Scientific Research" Version 1.1 << https://www.transportation.gov/sites/dot.gov/files/docs/Official%20DOT%20Public%20Access%20Plan%20ver%201.1.pdf >> and guidelines suggested by the DOT Public Access website << https://ntl.bts.gov/publicaccess/ >>, in effect and current as of April 10, 2019.



----------------------------------------------------------------
C. DATA & RELATED FILE OVERVIEW
----------------------------------------------------------------

1. File List for the USDOT 2023 SMART Project Dataset.zip collection      
        
   A. Filename: yyyy-MM-dd_hh-mm-ss_log.csv ; 
          
        Short description: Each cvs file records the operational information of ATMA during one run.         
         
        


----------------------------------------------------------------
D. METHODOLOGICAL INFORMATION
----------------------------------------------------------------

1. Description of methods used for collection/generation of data: The log files are automatically generated by the ATMA’s onboard control computer and record detailed information about system behavior, vehicle dynamics, and navigation status during deployment. 
     


2. Instrument- or software-specific information needed to interpret the data: The csv files can be opened with common software such as Microsoft excel and programming software such as python. 
   


----------------------------------------------------------------
E. DATA-SPECIFIC INFORMATION  
----------------------------------------------------------------

1. yyyy-MM-dd_hh-mm-ss_log.csv

A. Number of variables (columns): 32


B. Number of cases/rows: varies in each file, depending on the trip duration
   

C. Each row represents: one ATMA data point 
  

D. Data Dictionary/Variable List: 
At the top of the data log file, there are two headers. The first header is for Follower-Vehicle information and is described in Table I below. A second header is used to depict the Electronic Crumb (eCrumb) information for the Leader-Vehicle and is described in Table II below.

Table I – System Data Log Headers for the Follower-Vehicle
VEH                         Vehicle Identification (ID)
STATE                       Current vehicle operation state (IDLE = Operator in manual control, RUN = Autonomous mode, ROLLOUT = Ready for rollout)
NAV_STATE                   Current navigation availability state (INITIALIZING = initializing navigation, READY = navigation ready including deadreckoning, DEADRECKONING = currently deadreckoning, DEADRECKONING_MERGE = merging out of deadreckoning)
STAMP                       UTC time stamp generated by Global Positioning System (GPS) in Binary Coded Decimal (BCD format)
CRUMB                       eCrumb ID
NEXT_CRUMB                  ID of closest eCrumb to the follower vehicle
TOTAL_CRUMBS                Total number of eCrumbs in process
GPS_LAT                     GPS Latitude (degrees)
GPS_LON                     GPS Longitude (degrees)
CENTER_LAT                  GPS Center Latitude (degrees) (between 2 antennas)
CENTER_LON                  GPS Center Longitude (degrees) (between 2 antennas)
NAV_LAT                     Navigation Latitude (degrees) (including deadreckoning)
NAV_LON                     Navigation Longitude (degrees) (including deadreckoning)
GPS_S_LAT                   GPS Sensor Latitude (degrees)
GPS_S_LON                   GPS Sensor Longitude (degrees)
LATERAL_OFFSET(FT)          Current lateral offset of the follower (feet)
LATERAL_OFFSET_CMD(FT)      Commanded lateral offset of the follower (feet)
ALT                         Altitude (meters)
#SATS                       Number of satellites GPS is tracking
GPS_FIX                     GPS Fixtype (-1 = NONE, 0 = NORMAL, 1 = RTCM DIFFERENTIAL, 2 = RTK FLOAT, 3 = RTK FIXED, 5 = DEAD RECKONING, 6 = FORCED DEAD RECKONING, 9 = SBAS DIFFERENTIAL)
COURSE                      Course heading (track) (degrees)
HEADING                     Vehicle current heading (degrees)
HDG (Desired)               Desired heading (degrees); this is the heading vehicle would try to get to
VELOCITY                    Speed (miles per hour)
VEL (Desired)               Desired speed (miles per hour); target speed to get to
GAP                         Current gap (meters)
GAP (Desired)               Desired gap (meters); target gap distance to get to
CTE                         Cross track error (CTE) (meters); how far off from leader path
ACCEL                       Accelerator or brake percent (positive = acceleration, negative = braking)
STEER                       Steering turn percent (positive = turn right, negative = turn left)
NOTES                       Warnings, system errors, and other system notes (each entry ends with ###; there may be none, one, or multiple entries)

Table II – System Data Log Header for Leader-Vehicle eCrumb Information
LCB                         Vehicle ID for eCrumb (ECB = artificial eCrumbs, LDR = leader generated)
STATE                       Current vehicle operation state (IDLE = Operator in manual control, RUN = Autonomous mode, ROLLOUT = Ready for rollout)
NAV_STATE                   Current navigation availability state (INITIALIZING = initializing navigation, READY = navigation ready including deadreckoning, DEADRECKONING = currently deadreckoning, DEADRECKONING_MERGE = merging out of deadreckoning)
STAMP                       UTC time stamp generated by GPS in BCD format
CRUMB                       eCrumb ID (if this is not an eCrumb, it will be 0)
NEXT_CRUMB                  ID of closest eCrumb to the follower vehicle
TOTAL_CRUMBS                Total number of eCrumbs in process
GPS_LAT                     GPS Latitude (degrees)
GPS_LON                     GPS Longitude (degrees)
CENTER_LAT                  GPS Center Latitude (degrees) (between 2 antennas)
CENTER_LON                  GPS Center Longitude (degrees) (between 2 antennas)
NAV_LAT                     Navigation Latitude (degrees) (including deadreckoning)
NAV_LON                     Navigation Longitude (degrees) (including deadreckoning)
GPS_S_LAT                   GPS Sensor Latitude (degrees)
GPS_S_LON                   GPS Sensor Longitude (degrees)
LATERAL_OFFSET(FT)          Current lateral offset of the follower (feet)
LATERAL_OFFSET_CMD(FT)      Commanded lateral offset of the follower (feet)
ALT                         Altitude (meters)
#SATS                       Number of satellites GPS is tracking
GPS_FIX                     GPS Fixtype (-1 = NONE, 0 = NORMAL, 1 = RTCM DIFFERENTIAL, 2 = RTK FLOAT, 3 = RTK FIXED, 5 = DEAD RECKONING, 6 = FORCED DEAD RECKONING, 9 = SBAS DIFFERENTIAL)
COURSE                      Course heading (track) (degrees)
HEADING                     Vehicle current heading (degrees)
VELOCITY                    Speed (miles per hour)



E. Missing data codes: empty




----------------------------------------------------------------
F. UPDATE LOG
----------------------------------------------------------------

This ATMA for Work Zone Safety V1.0 file was originally created on 2025-10-28 by Xianbiao Hu, 0000-0002-0149-1847, Associate Professor of Pennsylvania State University, xbhu@psu.edu

Update Log:
2025-10-28: Original file created




