Last modified on March 6, 2024

Available software components or frameworks (2021)

This information was compiled by the ARCADE project in 2021.

Comma.ai

Comma.ai is a start-up that has built advanced neural network components that enable ADAS functionality. They have open sourced their software code. They sell dashcam components that go together with the software. Users can submit data and earn community points (https://my.comma.ai, accessed 19 April 2021). A small dataset to train algorithms is available at https://research.comma.ai (accessed 19 April 2021).

ASAM OpenDRIVE and OpenScenario

The ASAM OpenDRIVE format is a standard for describing road networks using an XML-based syntax. The road descriptions can be used in various simulation tools. OpenDRIVE roads can be either manually created using visual editors or converted from existing map data. The standardized format supports cost-efficient development and testing of ADAS and automated driving. The standard is freely accessible. More information from https://www.asam.net/standards/detail/opendrive (accessed 16 September 2021).

The ASAM OpenSCENARIO is a standardized file format for describing traffic scenarios for simulation purposes. The format enables to describe storylines for various traffic participants, for example, a vehicle changing lane once it reaches a specific position. The configurations can be parametrized, so that one file can support varying the scenario. The description includes details of environment conditions, as well. Scenario simulation is an essential part of testing new driver support and automated driving features. More information from https://www.asam.net/standards/detail/openscenario (accessed 16 September 2021).

L3pilot common data format

The European research project L3Pilot had a focus on large-scale piloting of SAE Level 3 functions, running from 2017-2021. Its 34 partners were running tests and collecting data in ten countries. All log data from test vehicles was converted into a Common Data Format (CDF), a file format that the project created and now promotes for open collaboration. The format has been made available at https://github.com/l3pilot/l3pilot-cdf  (accessed 16 September 2021).

The L3Pilot-CDF builds on HDF5, a hierarchical data format developed by the HDF Group. Using HDF5 as a basis ensures that a variety of data tools and programming languages can readily interface the files. The interoperability is the main advantage of HDF5: the joint computation framework in L3Pilot was built on MATLAB, but many vehicle owners’ data conversion scripts and advanced image processing frameworks use e.g. Python. HDF5 also offers efficient compression and metadata features.

Feedback form

Have feedback on this section??? Let us know!

Send feedback

Feedback

Please add your feedback in the field below.

Your feedback has been sent!
Thank you for your input.

An error occured...
Please try again later.