Connected Eco-Driving, Fort Collins 2019: Synchronized Vehicle, ADAS, V2V and Traffic-Signal (V2I) Data for Velocity Prediction (DOE EE0008468)

Provider
Colorado State University and Western Michigan University (Rabinowitz, Gaikwad, White, Bradley, Asher)
License
CC-BY-4.0 (source)
Size
129 files
Format
PNG, CSV (in sampled files)
Stored at
Hugging Face (https://huggingface.co/datasets/AD-Assurance-Lab/connected-eco-driving-doe-ee0008468)
Access
Free and public. No account with the data provider is needed.
Category
Robotics
Source
https://doi.org/10.4271/2020-01-0736

About this dataset

Real-world connected-vehicle data from urban drives in Fort Collins, Colorado, in 2019, collected for vehicle velocity prediction and predictive energy management under U.S. Department of Energy Vehicle Technologies Office project DE-EE0008468 (Colorado State University with NREL, the cities of Fort Collins and Denver, and Western Michigan University). An instrumented Chevrolet Malibu drove arterial loops with a Mobileye 6 camera, Bosch mid-range radars, a ZED stereo camera and a CAN/OBD logger; volunteer cars with Freematics GPS/IMU/OBD loggers stood in for vehicle-to-vehicle (V2V) messages, and the city supplied traffic-signal phase and timing (SPaT) and BlueTOAD segment travel times (vehicle-to-infrastructure, V2I). The speed-prediction/ folder holds ML-ready tables, one row per distance step, with ego speed and position, the next five signals' phase and distance, segment speeds and V2V speed statistics, loadable with Hugging Face datasets. raw/ holds Vector BLF ADAS logs with MATLAB/CSV decodes and logger CSVs; processed/ holds synchronized MATLAB structures; results/, maps/ and a ZED stereo SVO video are included. About 14 GB (measured 2026-11-21). CC BY 4.0, copyright Colorado State University and Western Michigan University; cite Rabinowitz et al., SAE Technical Paper 2020-01-0736.

How to load this dataset in Python

import pandas as pd
df = pd.read_csv("hf://datasets/AD-Assurance-Lab/connected-eco-driving-doe-ee0008468/processed/nn-training/D01Cleaned.csv")
df.head()

Data structure

File types in sampled files: PNG, CSV

Files

Example file: processed/nn-training/D01Cleaned.csv

Analyze this dataset without downloading it

On Scigantic, Connected Eco-Driving, Fort Collins 2019: Synchronized Vehicle, ADAS, V2V and Traffic-Signal (V2I) Data for Velocity Prediction (DOE EE0008468) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Robotics datasets