> For the complete documentation index, see [llms.txt](https://qiqiqi.gitbook.io/mixed-traffic/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://qiqiqi.gitbook.io/mixed-traffic/overview/relevant-simulation-platforms.md).

# Relevant Simulation Platforms

## Simulation Platforms/Tools

 

<table data-header-hidden data-full-width="true"><thead><tr><th></th><th></th><th></th></tr></thead><tbody><tr><td><strong>Simulation Platforms/Tools</strong></td><td><strong>Features</strong></td><td><strong>Applications</strong></td></tr><tr><td><a href="https://sumo.dlr.de/docs/index.html">SUMO</a></td><td>Open source, highly portable, microscopic, and continuous multi-modal traffic simulation package</td><td><p>Microscopic simulation; Multimodal Traffic; Automated Driving with Transition of Control;</p><p>Vehicle Communication; Traffic Management</p></td></tr><tr><td><a href="https://www.myptv.com/en-us/mobility-software/ptv-vissim">PTV Vissim</a></td><td>Multimodal traffic simulation software (none open source)</td><td>Traffic simulation; Mobility Trends; Transportation Planning; Modelling; Operation</td></tr><tr><td> </td><td></td><td></td></tr><tr><td><a href="https://carla.org/">CARLA</a></td><td>Open-source simulator; Flexible API with sensor suite; ROS integration; Maps generation</td><td>Training, and validation of autonomous driving systems</td></tr><tr><td><a href="https://paperswithcode.com/dataset/summit">SUMMIT</a></td><td>Simulator built as an extension of CARLA for urban driving in massive mixed traffic;</td><td>Testing of crowd-driving algorithms;  perception, vehicle control, planning, and end-to-end learning</td></tr><tr><td><a href="https://github.com/lgsvl/simulator-2019.05-obsolete">LGSVL Simulator</a></td><td>Unity-based multi-robot simulator for autonomous vehicle; integrated with the <a href="https://github.com/lgsvl/duckietown2">Duckietown</a>, TierIV's <a href="https://github.com/lgsvl/Autoware">Autoware</a>, and Baidu's <a href="https://github.com/lgsvl/apollo">Apollo </a>platforms; can generate HD maps</td><td>Testing Autonomous Vehicle</td></tr><tr><td><a href="https://microsoft.github.io/AirSim/">AirSim</a></td><td>A simulator for drones, cars and more, built on <a href="https://www.unrealengine.com/">Unreal Engine</a>; open-source, cross platform, and supports software-in-the-loop simulation</td><td>Experiment with deep learning, computer vision and reinforcement learning algorithms for autonomous vehicles</td></tr><tr><td><a href="https://deepdrive.io/">Deepdrive</a></td><td>A simulator for self-driving; Baseline agent available; Modifiable source; Enable up to eight cameras with depth</td><td>Experiment with self-driving AI</td></tr><tr><td><a href="https://github.com/metadriverse/metadrive">MetaDrive</a></td><td>A driving simulator with key features of : Compositional: generating infinite scenes; Lightweight: it can run up to 300 FPS on a standard PC; Realistic: Accurate physics simulation and multiple sensory input, top-down semantic map</td><td>For the research of generalizable reinforcement learning; Single Agent and Multi-Agent simulation</td></tr><tr><td><a href="https://waymo.com/research/waymax/">Waymax</a></td><td>A data-driven simulation platform based on <a href="https://waymo.com/open/">Waymo Open Dataset</a>. Default simulation is 10Hz. Support two models for other agents: log playback and an IDM-based route-following model; Direct state-based control, and control via the kinematic bicycle model; Provide adapters to common RLs.</td><td><p>Motion Planning using control theory, data-driven, or reinforcement learning-based methods.</p><p>Single agent and multi-agent behavior prediction research.</p></td></tr><tr><td><a href="https://commonroad.in.tum.de/">CommonRoad</a></td><td>A collection of composable benchmarks for motion planning on roads. The benchmarks consist of a scenario with a planning problem, a vehicle dynamics model, vehicle parameters, and a cost function composing a unique ID.</td><td>Research on Motion Planning. Evaluating motion planning algorithms in different scenarios and against different benchmarks.</td></tr><tr><td><a href="https://github.com/Farama-Foundation/HighwayEnv">Highway-env</a></td><td>A light version of collection of simulated environments for autonomous driving; Based on <a href="https://github.com/openai/gym">OpenAI gym</a></td><td>Experiment with autonomous driving and tactical decision-making tasks on: Highway driving; Merging; Roundabout driving; Parking; Intersection; and  Racetrack</td></tr><tr><td><a href="https://github.com/ucla-mobility/OpenCDA#readme">OpenCDA</a></td><td>CARLA + SUMO co-simulation environment providing a rich library for Cooperative Driving Automation;</td><td>Automated driving components (e.g., perception, localization, planning, control); Connectivity and Cooperation; Full-stack Simulation; CDA Evaluation</td></tr></tbody></table>