ScenarioNet
Open-source platform for large-scale traffic scenario modeling and simulation
From 2022.3 to present. UCLA Prof Bolei-Zhou’s group.
- Latest news: The work has been accept by
NeuralIPS 2023 track on Datasets and Benchmarks
! Camera-ready paper will be released shortly.
ScenarioNet is an open-sourced platform for large-scale traffic scenario modeling and simulation.
![ScenarioNet Structure](/assets/img/snet.jpg)
ScenarioNet consists of the data layer, system layer, and application layer. Various datasets are unified into an internal scenario description. The system layer then provides a set of tools to operate on data efficiently, such as filtering, merging, sanity-check, splitting and so on. Once the database is ready, it can be loaded into MetaDrive for large-scale simulation and supports applications.