Live Road Assessment Custom Dataset (LiRA-CD)

Live Road Assessment Custom Dataset (LiRA-CD) is an open-source dataset for road condition modeling and research. The aim of this dataset is to provide researchers and pavement engineers with a vehicle dataset that is open-source and suitable for developing large-scale road condition monitoring methods. Specifically, this dataset focuses on linking in-vehicle sensor data collected by regular cars to standard road condition parameters utilized by public road agencies (i.e., parameters used as input for planning and management of road networks).

The LiRA-CD contains 1796 km of road data from highway and urban roads in the Copenhagen area collected during the LiRA project (see e.g., Pettinari et al. (2020) and Levenberg et al. (2021). It includes more than 50 in-vehicle sensors signals from Renault Zoe electric cars operated by GreenMobility (GM) and 92 road condition parameters collected with standard vehicles operated by the Danish Road Directorate (DRD). 

The LiRA-CD is a collection of three selected datasets from the LiRA project:

#1 Data subset for road condition modelling - car sensor data. This subset includes the in-vehicle sensor data (.hdf5) collected with an AutoPi Telematics Unit (3rd generation) connected to the vehicle's controller area network (CAN) bus. This unit includes a single-board Raspberry Pi computer with added GPS and accelerometer modules. Moreover, the subset includes a MATLAB® script for accessing and visualizing hdf5-file data. 

#2 Data subset for road condition modelling - reference data. This subset includes the reference data, i.e., the standard road condition parameters, collected by vehicles operated by the Danish Road Directorate (DRD). The datasets are divided into subsets, i.e., road elevation data from the P79 vehicle (‘..zp…csv’), International Roughness Index (IRI), Mean Profile Depth (MPD) and wheelpath rut depth from the P79 vehicle (..iri_mpd_rut…csv’), friction data from the VIAFRIK vehicle (‘..fric…csv’), road condition data from the ARAN vehicle (‘...aran…csv’). 

#3 Data subset for road condition modelling - platoon friction test. This subset includes data from an additional measurement campaign involving a car driving behind the VIAFRIK vehicle. The data are divided into several subsets, i.e., friction data from the VIAFRIK vehicle (‘..fric_custom…csv’) and car sensor data from the AutoPi and the vehicle CAN bus (‘task_7505…txt’).

The raw data has not been aligned or structured, hence several pre-processing steps may be required by users before further analysis can be performed. Recommended pre-processing steps include: (i) re-orientation of the AutoPi accelerometer axes to align with the principal car axes; (ii) map-matching – where the GPS routes are corrected using the reference measurements; (iii) interpolation – where GPS coordinates are assigned to all sensor readings; and (iv) structuring of data – where sensor readings are re-sampled to ensure consistency between car- and reference data across all sensors.