ir-sim

Intelligent Robot Simulator (IR-SIM)

Documentation: https://ir-sim.readthedocs.io/en

IR-SIM is an open-source, Python-based, lightweight robot simulator designed for navigation, control, and learning. It provides a simple, user-friendly framework with built-in collision detection for modeling robots, sensors, and environments. Ideal for academic and educational use, IR-SIM enables rapid prototyping of robotics and AI algorithms in custom scenarios with minimal coding and hardware requirements.

Features

• Simulate robot platforms with diverse kinematics, sensors, and behaviors (support).
• Quickly configure and customize scenarios using straightforward YAML files. No complex coding required.
• Visualize simulation outcomes using a naive visualizer matplotlib for immediate debugging.
• Support collision detection and behavior control for each object.

Demonstrations

Scenarios	Description
	In scenarios involving multiple circular differential robots, each robot employs Reciprocal Velocity Obstacle (RVO) behavior to avoid collisions. See Usage - collision avoidance
	A car-like robot controlled via keyboard navigates a binary map using a 2D LiDAR sensor to detect obstacles. See Usage - grid map
	A car-like robot controlled via keyboard navigates a grid map generated from 3D habitat spaces datasets like HM3D, MatterPort3D, Gibson, etc. See Usage - grid map hm3d
	Each robot employing RVO behavior is equipped with a field of view (FOV) to detect other robots within this area. See Usage - fov
	A car-like robot navigates through the randomly generated and moving obstacles. See Usage - dynamic random obstacles

Prerequisite

• Python: >= 3.9

Installation

• Install this package from PyPi:

pip install ir-sim

This does not include dependencies for all features of the simulator. To install additional optional dependencies, use the following pip commands:

# install dependencies for keyboard control
pip install ir-sim[keyboard]

# install dependencies for testing
pip install ir-sim[test]

# install all optional dependencies
pip install ir-sim[all]  

• Or if you want to install the latest main branch version (which is more up-to-date than the PyPI version) from the source code:

git clone https://github.com/hanruihua/ir-sim.git    
cd ir-sim   
pip install -e .  

Usage

Quick Start

import irsim

env = irsim.make('robot_world.yaml') # initialize the environment with the configuration file

for i in range(300): # run the simulation for 300 steps

    env.step()  # update the environment
    env.render() # render the environment

    if env.done(): break # check if the simulation is done
        
env.end() # close the environment

YAML Configuration: robot_world.yaml

world:
  height: 10  # the height of the world
  width: 10   # the width of the world
  step_time: 0.1  # 10Hz calculate each step
  sample_time: 0.1  # 10 Hz for render and data extraction 
  offset: [0, 0] # the offset of the world on x and y 

robot:
  kinematics: {name: 'diff'}  # omni, diff, acker
  shape: {name: 'circle', radius: 0.2}  # radius
  state: [1, 1, 0]  # x, y, theta
  goal: [9, 9, 0]  # x, y, theta
  behavior: {name: 'dash'} # move toward to the goal directly 
  color: 'g' # green

Advanced Usage

The advanced usages are listed in the irsim/usage

Support

Currently, the simulator supports the following features. Further features, such as additional sensors, behaviors, and robot models, are under development.

Category	Features
Kinematics	Differential Drive mobile Robot Omni-Directional mobile Robot Ackermann Steering mobile Robot
Sensors	2D LiDAR FOV detector
Geometries	Circle Rectangle Polygon linestring Binary Grid Map
Behaviors	dash (Move directly toward the goal) rvo (Move toward the goal using Reciprocal Velocity Obstacle behavior)

Projects Using IR-SIM

• Academic Projects:

  • rl-rvo-nav: [RAL & ICRA2023] A Reinforcement Learned based RVO behavior for multi-robot navigation.
  • RDA_planner: [RAL & IROS2023] An Accelerated Collision Free Motion Planner for Cluttered Environments.
  • NeuPAN: [T-RO 2025] Direct Point Robot Navigation with End-to-End Model-based Learning.

• Deep Reinforcement Learning Projects:

  • DRL-robot-navigation-IR-SIM
  • AutoNavRL

Contributing

This project is under development. I appreciate and welcome all contributions. Just open an issue or a pull request. Here are some simple ways to start contributing:

• Read the IR-SIM source code and improve the documentation, api, or address TODO list.
• Enhance the website documentation.
• Polish the usages and add new usage examples or test cases.
• Fix bugs and issues.

Code style: black

Acknowledgement

• PythonRobotics