scenario_runner
A traffic scenario definition and execution engine for the CARLA autonomous driving simulator.
What is scenario_runner?
ScenarioRunner is a traffic scenario definition and execution engine for the CARLA autonomous driving simulator. It allows researchers and developers to create, manage, and run complex driving scenarios to test and evaluate autonomous vehicle agents. The tool supports both a Python interface and the OpenSCENARIO standard for scenario description.
Autonomous driving researchers, engineers, and students using the CARLA simulator who need to test and validate their driving algorithms under reproducible and complex traffic conditions.
It provides a standardized and flexible framework for scenario-based testing that is tightly integrated with CARLA, supports industry standards, and is essential for preparing agents for the CARLA Challenge.
Overview
Traffic scenario definition and execution engine
Use Cases
Best For
- Defining reproducible traffic scenarios for autonomous vehicle testing
- Evaluating driving agents for the CARLA Autonomous Driving Challenge
- Creating complex driving tests using the OpenSCENARIO standard
- Programmatically generating custom scenarios with Python
- Benchmarking autonomous driving algorithms in a simulated environment
- Integrating scenario-based testing into CARLA-based research pipelines
Not Ideal For
- Projects using autonomous driving simulators other than CARLA, such as AirSim or LGSVL
- Teams requiring a graphical user interface for scenario design without coding
- Scenarios needing real-time, dynamic adaptation beyond pre-scripted events
- Environments where strict version matching between tools is impractical due to frequent updates
Pros & Cons
Pros
Supports both OpenSCENARIO and OpenSCENARIO 2.0 standards, enabling interoperability with industry-standard scenario descriptions, as stated in the README.
Tightly coupled with CARLA simulator versions, allowing direct execution of scenarios within the simulation environment, with specific release compatibility detailed in the version list.
Provides a Python interface for defining and customizing traffic scenarios programmatically, offering flexibility for researchers, as highlighted in the features.
Enables simulation of official CARLA Challenge scenarios, essential for preparing and evaluating autonomous agents, with documentation linking to the leaderboard.
Cons
Requires exact version matching with CARLA, as detailed in the extensive compatibility list, making upgrades and maintenance complex and error-prone.
Exclusively designed for CARLA simulator, not adaptable to other simulation platforms, limiting its use in multi-simulator workflows or broader research.
No graphical tools; all scenarios must be defined via Python or OpenSCENARIO files, requiring programming expertise and increasing initial setup time.
Frequently Asked Questions
Related Projects
GitHub repositoryOpen source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
GitHub repositoryOpen-source simulator for autonomous driving research.
WebotsWebots Robot Simulator
DrakeModel-based design and verification for robotics.
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.