Relevant Simulation Platforms
Selected relevant simulation platforms, and automated driving developement software tools.
Last updated
Selected relevant simulation platforms, and automated driving developement software tools.
Last updated
Simulation Platforms/Tools
Features
Applications
Open source, highly portable, microscopic, and continuous multi-modal traffic simulation package
Microscopic simulation; Multimodal Traffic; Automated Driving with Transition of Control;
Vehicle Communication; Traffic Management
Multimodal traffic simulation software (none open source)
Traffic simulation; Mobility Trends; Transportation Planning; Modelling; Operation
Open-source simulator; Flexible API with sensor suite; ROS integration; Maps generation
Training, and validation of autonomous driving systems
Simulator built as an extension of CARLA for urban driving in massive mixed traffic;
Testing of crowd-driving algorithms; perception, vehicle control, planning, and end-to-end learning
Unity-based multi-robot simulator for autonomous vehicle; integrated with the , TierIV's , and Baidu's platforms; can generate HD maps
Testing Autonomous Vehicle
A simulator for drones, cars and more, built on ; open-source, cross platform, and supports software-in-the-loop simulation
Experiment with deep learning, computer vision and reinforcement learning algorithms for autonomous vehicles
A simulator for self-driving; Baseline agent available; Modifiable source; Enable up to eight cameras with depth
Experiment with self-driving AI
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
For the research of generalizable reinforcement learning; Single Agent and Multi-Agent simulation
A data-driven simulation platform based on . 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.
Motion Planning using control theory, data-driven, or reinforcement learning-based methods.
Single agent and multi-agent behavior prediction research.
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.
Research on Motion Planning. Evaluating motion planning algorithms in different scenarios and against different benchmarks.
A light version of collection of simulated environments for autonomous driving; Based on
Experiment with autonomous driving and tactical decision-making tasks on: Highway driving; Merging; Roundabout driving; Parking; Intersection; and Racetrack
CARLA + SUMO co-simulation environment providing a rich library for Cooperative Driving Automation;
Automated driving components (e.g., perception, localization, planning, control); Connectivity and Cooperation; Full-stack Simulation; CDA Evaluation