Infrastructure-Enabled Energy-Efficient Autonomous Vehicles (DOE EEMS116): Radar Retroreflector, Smart Pavement Marker, HD-Map and Weather Sensing Recordings

Provider
AD Assurance Lab, Western Michigan University, with Oak Ridge National Laboratory, NCAR and DriveU.auto
License
CC-BY-4.0 (source)
Size
1,685 files
Format
CSV (in sampled files)
Stored at
Hugging Face (https://huggingface.co/datasets/AD-Assurance-Lab/infrastructure-sensing-doe-eems116)
Access
Free and public. No account with the data provider is needed.
Category
Robotics
Source
https://github.com/AD-Assurance-Lab/infrastructure-sensing--doe-eems116--main

About this dataset

Recordings from a U.S. Department of Energy Vehicle Technologies Office project at Western Michigan University (2021-2024, award DE-EE0009657, project EEMS116) that tested ways for the road itself to give a self-driving car its perception, so the car can carry fewer sensors and less computing, and measured the energy saved. Folders: cerpm/ has drives past Chip-Enabled Raised Pavement Markers that radio their lane position, with Piksi RTK GNSS and ZED 2i camera; radar-retroreflectors/ has runs past Van Atta radar retroreflectors with Aptiv ESR radar tracks and raw radar-bus frames, Ouster OS1-64 lidar, camera and vehicle data, including the DOE demonstration route; weather-ncar/ has Ouster lidar, RTK, Delphi ESR radar and Mobileye in clear weather and rain recorded with NCAR; hd-maps/ has 1,631 front-camera frames from WMU's Parkview campus loop used for HD-map lane projection plus a raw 65 s mapping run; compute-load/ has chassis dynamometer power-analyzer logs over UDDS cycles. All bags are ROS 1 (read with ROS Noetic or the rosbags Python package). About 37 GB (measured 2026-11-21). The project GitHub states data are CC BY 4.0; cite Asher et al., DOE VTO Annual Merit Review EEMS116, 2024.

How to load this dataset in Python

import pandas as pd
df = pd.read_csv("hf://datasets/AD-Assurance-Lab/infrastructure-sensing-doe-eems116/compute-load/dyno-2024-01/power-analyzer/dyno_test_baseline_1.28.2024.csv")
df.head()

Data structure

File types in sampled files: CSV

Files

Example file: compute-load/dyno-2024-01/power-analyzer/dyno_test_baseline_1.28.2024.csv

Analyze this dataset without downloading it

On Scigantic, Infrastructure-Enabled Energy-Efficient Autonomous Vehicles (DOE EEMS116): Radar Retroreflector, Smart Pavement Marker, HD-Map and Weather Sensing Recordings 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