United States Department of Transportation
i
Radar and LiDAR Fusion for Scaled Vehicle Sensing [supporting dataset]
-
2022-03-30
-
Details:
-
Creators:
-
Corporate Creators:
-
Corporate Contributors:
-
Subject/TRT Terms:
-
Publication/ Report Number:
-
DOI:
-
Resource Type:
-
Geographical Coverage:
-
Corporate Publisher:
-
Abstract:Scaled test beds are popular tools to develop and physically test algorithms for advanced driving systems, but they often lack automotive-grade radars in their sensor suites. To overcome resolution issues when using a radar at small scale, a high-level radar and automotive-grade LiDAR sensor fusion approach that effectively leveraged the higher spatial resolution of LiDAR was proposed. First, radar tracking software (RTS) was developed to track a maneuvering full-scale vehicle using an extended Kalman filter (EKF) and a popular data association technique. Second, a 1/5th scaled vehicle performed the same vehicle maneuvers but scaled to approximately 1/5th the distance and speed. When considering the scaling factor, the RTS’s positional error at small scale was over 5 times higher on average than in the full-scale trials. Third, LiDAR object tracks were generated for the small-scale trials using a second EKF implementation and then combined with the radar objects in a high-level track fusion algorithm. The fused tracks demonstrated a 30% increase in positional accuracy for a majority of the small-scale trials when compared to tracks using just the radar or just the LiDAR. The proposed track fuser could allow scaled test beds to incorporate automotive radars into their sensor suites more effectively by augmenting the radar output with LiDAR, overcoming the resolution issues that afflict radar when operating at small scale.
The total size of the described zip file is 933.85MB. The ZIP file for this dataset contains files with the following files extensions: PDFs are used to display text and images and can be opened with any PDF reader or editor. Files that end in .bag are uncompressed data files. These files can be opened with software such as rosbag or be converted into many .csv files.
-
Content Notes:As this dataset is preserved in a repository outside U.S. DOT control, as allowed by the U.S. DOT’s Public Access Plan (https://doi.org/10.21949/1503647) Section 7.4.2 Data, the NTL staff has performed NO additional curation actions on this dataset. The current level of dataset documentation is the responsibility of the dataset creator. NTL staff last accessed this dataset at https://dataverse.vtti.vt.edu/dataset.xhtml?persistentId=doi:10.15787/VTT1/BQJRFN on 2022-09-29. If, in the future, you have trouble accessing this dataset at the host repository, please email NTLDataCurator@dot.gov describing your problem. NTL staff will do its best to assist you at that time.
-
Format:
-
Funding:
-
Collection(s):
-
Main Document Checksum:
Related Documents
-
[PDF - 2.13 MB]
