Open Source Simulation Software

AirSim is an open-source, cross platform simulator for drones, cars and more vehicles, built on Unreal Engine with an experimental Unity release in the works. It supports software-in-the-loop simulation with popular flight controllers such as PX4 & ArduPilot and hardware-in-loop with PX4 for physically and visually realistic simulations. It is developed as an Unreal plugin that can simply be dropped into any Unreal environment. AirSim's development is oriented towards the goal of creating a platform for AI research to experiment with deep learning, computer vision and reinforcement learning algorithms for autonomous vehicles. For this purpose, AirSim also exposes APIs to retrieve data and control vehicles in a platform independent way. AirSim is fully enabled for multiple vehicles. This capability allows you to create multiple vehicles easily and use APIs to control them.

CARLA has been developed from the ground up to support development, training, and validation of autonomous driving systems. In addition to open-source code and protocols, CARLA provides open digital assets (urban layouts, buildings, vehicles) that were created for this purpose and can be used freely. The simulation platform supports flexible specification of sensor suites, environmental conditions, full control of all static and dynamic actors, maps generation and much more. Multiple clients in the same or in different nodes can control different actors. CARLA exposes a powerful API that allows users to control all aspects related to the simulation, including traffic generation, pedestrian behaviors, weathers, sensors, and much more. Users can configure diverse sensor suites including LIDARs, multiple cameras, depth sensors and GPS among others. Users can easily create their own maps following the OpenDrive standard via tools like RoadRunner.

Neuroph is lightweight Java Neural Network Framework which can be used to develop common neural network architectures. Small number of basic classes which correspond to basic NN concepts, and GUI editor makes it easy to learn and use.

Brax is a fast and fully differentiable physics engine for large-scale rigid body simulations, built on JAX. It is designed for research in reinforcement learning and robotics, enabling efficient simulations and gradient-based optimization.

The Distributed Genetic Programming Framework is a scalable Java genetic programming environment. It comes with an optional specialization for evolving assembler-syntax algorithms. The evolution can be performed in parallel in any computer network.

Robosuite is a modular and extensible simulation framework for robotic manipulation tasks, built on top of MuJoCo. Developed by the ARISE Initiative, Robosuite offers a set of standardized benchmarks and customizable environments designed to advance research in robotic manipulation, control, and imitation learning. It emphasizes realistic simulations and ease of use for both single-task and multi-task learning.

The Mars Simulation Project is an open source Java project to create a simulation of future human settlement on the planet Mars. See https://github.com/mars-sim/mars-sim for the LATEST issues/wiki/code change

mujoco-py is a Python wrapper for MuJoCo, a high-performance physics engine widely used in robotics, reinforcement learning, and AI research. It allows developers and researchers to run detailed rigid body simulations with contacts directly from Python, making MuJoCo easier to integrate into machine learning workflows. The library is compatible with MuJoCo version 2.1 and supports Linux and macOS, while Windows support has been deprecated. It provides utilities for loading models, running simulations, and accessing simulation states in real time, along with visualization tools for rendering environments. The project also includes interactive examples showcasing collision handling, texture randomization, state resetting, and robot control. By bridging MuJoCo with Python, mujoco-py enables rapid prototyping, training, and evaluation of AI agents in physics-rich environments.

JGAP is a Genetic Algorithms and Genetic Programming package written in Java. It is designed to require minimum effort to use, but is also designed to be highly modular. JGAP features grid functionality and a lot of examples. Many unit tests included. Legal notice/Impressum: Klaus Meffert An der Struth 25 D-65510 Idstein sourceforge <at> klausmeffert.de

Java based portable simulator to visualize and understand the Robot Localization, Path planning, Path Smoothing and PID controller concepts. It is very flexible and easy to use. It supports multiple platforms. The source code is available on Github where you can find latest development and up-to-date documentation. Source : https://github.com/habsoft/robosim Blog : https://robosimblog.wordpress.com Note : Use jre 1.7 to run it. 1.Histogram Filter 2.Histogram Filter with Sonar Range Finder (Experimental) 3.Kalman Filter 4.Particles Filter 5.Path Planning 6.Path Smoothing 7.PID Controller Path Planning Algorithms 1.BFS 2.DFS 3.A Star 4. Dynamic Programming Heuristics i. Euclidean Distance ii. Euclidean Distance(+) iii. Euclidean Distance(*) iv. Euclidean Distance Squared v. Manhattan Distance vi. Chebyshev Distance

The GNNPCSAFT Web App is an implementation of our project that focuses on using Graph Neural Networks (GNN) to estimate the pure-component parameters of the Equation of State PC-SAFT. We developed this app so the scientific community can access the model's results easily. In this app, the estimated pure-component parameters can be used to calculate thermodynamic properties and compare them with experimental data from the ThermoML Archive. More info on github repository.

The GNNPCSAFT Chat is an implementation of our project that focuses on using Graph Neural Networks (GNN) to estimate the pure-component parameters of the Equation of State PC-SAFT. We developed this app so the scientific community can access the model's results easily. In this app, you can chat with LLM models (Gemini or Ollama) with GNNPCSAFT tools, allowing you to ask questions about the PC-SAFT parameters of various compounds, predict thermodynamic properties, and get insights into the GNNPCSAFT's performance.

VLE is a multi-modeling and simulation environment to study complex dynamic systems. VLE is based on the discrete event specification DEVS. and it implements the DSDE formalism (A merge of Dynamic Structure DEVS, DSDEVS, with Parallel DEVS, PDEVS). VLE provides a complete set of C++ libraries, called VFL (VLE Foundation Libraries), to develop DEVS models, to gets results of simulations, to launch simulation on cluster. The models can be developed with the DEVS formalism or with the classical mathematical formalism: Ordinary Differential Equation with Euler, Range-Kutta or QSS integrator, Finite state automaton (FDDEVS, UML State chart, Hybrid Petri net). The VLE environment provides an IDE to develop C++ models, DEVS coupled models. VLE have also three ports to use the VFL with Python, Java and R programming languages.

MATSim is a framework for building multi-agent transport simulations. MATSim has moved to GitHub: https://github.com/matsim-org/matsim Source code and newer releases are now hosted at GitHub!

JASA allows researchers in agent-based computational economics to write high-performance trading simulations using a number of different auction protocols. The software also provides base classes for implementing simple adaptive trading agents.

Laputa is a research tool and a sandbox environment for simulating the attainment of knowledge in social networks, such as scientific departments, editorial boards, expert groups, and the general public. It was developed at the philosophy department at the university of Lund.

A-Life CAD is a toolkit providing a graphical interface for designing autonomous agents that can be linked against an AI game engine. Though it focuses on creating boid-like behaviours, it can also be used for physical simulation or swarm optimisation.

ABSim is an Agent-Object-Relationship (AOR) simulation system based on a Java program library. The development of ABSim has terminated. Its successor is <a href="http://oxygen.informatik.tu-cottbus.de/aor/?q=node/2">AOR-JSim </a>

A platform for setting up autonomic services in a distributed environment. Provides service discovery, service provisioning / usage, autonomic adaptation to the context, mobility, support for supervision and service aggregation, and more.

This project about providing run-time support for developing Decentralized Autonomic Computing systems (Eclipse Innovation Grand). Currently the project contains a automatic guided vehicle (AGV) simulator and an editor and visualisation as eclipse plugin

This is a framework to develop Contexts and Agents and a Container to run them. The Container lets each Agent interact with the Context and other Agents. The agents are deployed in jar files and each one runs in an exclusive sandbox.

The Automatic Model Optimization Reference Implementation, AMORI, is a framework that integrates the modelling and the optimization processes by providing a plug-in interface for both. A genetic algorithm and Markov simulations are currently implemented.

The ART testbed program allows researchers to compare their work from a practical point of view in the modelling of trust in agent societies.

A demonstration of the result of using an agent based approach in software. Shows a swarm of icons representing agents that follow user selected rules.