Welcome to IR-SIM’s documentation!

IR-SIM is an open-source, lightweight Python robot simulator for navigation, control, and learning. It pairs a simple, user-friendly framework with built-in collision detection for modeling robots, sensors, and environments — so you can prototype robotics and AI algorithms in custom scenarios with minimal code and hardware.

🚀 Get Started

Get Started

📚 User Guide

User Guide

⚙️ Configuration

YAML Configuration Syntax

🔧 API Reference

API Reference

⭐ GitHub

https://github.com/hanruihua/ir-sim

See IR-SIM in action

Multi-Robot RVO Collision Avoidance

200-Agent ORCA via pyrvo

Social Force Model (SFM)

Ackermann Robot with 2D LiDAR

Field-of-View Detection

HM3D / MatterPort3D Grid Map

Dynamic Random Obstacles

Mouse Control

Keyboard Control

Key Features

• Simulate a wide range of robot platforms with diverse kinematics, sensors, and behaviors

• Quickly configure and customize simulation scenarios using straightforward YAML files, with no complex coding required

• Visualize simulation outcomes in real time for immediate feedback and analysis using matplotlib

• Support collision detection and behavior control for each object in the simulation

• Suitable for multi-agent and robot learning research

Capabilities

Kinematics	Differential drive · Omnidirectional · Omnidirectional (angular) · Ackermann steering
Sensors	2D LiDAR · 2D FMCW LiDAR · FOV detector
Geometries	Circle · Rectangle · Polygon · LineString · Binary grid map
Behaviors	dash · RVO · ORCA · SFM (Social Force Model)

Installation

Install the latest release from PyPI:

pip install ir-sim

Prefer conda or uv? Pick your installation method:

Recommended

📦 pip

Quick installation with pip

Install

Popular

🐍 conda

Installation in conda environment

Install

Fast

⚡ uv

Lightning-fast installation

Install

Projects using IR-SIM

Academic Publications

• rl-rvo-nav (RAL & ICRA2023) - Reinforcement learning-based RVO behavior for multi-robot navigation.

• RDA_planner (RAL & IROS2023) - Accelerated collision-free motion planner for cluttered environments.

• NeuPAN (T-RO 2025) - Direct point robot navigation with end-to-end model-based learning.

Community Projects

• DRL-robot-navigation-IR-SIM - Deep reinforcement learning for robot navigation.

• AutoNavRL - Autonomous navigation using reinforcement learning.

• IRSIM-3DGS-Bridge - A closed-loop bridge from 3D Gaussian Splatting scenes to IR-SIM planning/following and back to Habitat-GS trajectory playback.

Citation

If you find IR-SIM useful, please consider starring ⭐ the project on GitHub and citing our paper:

@article{han2026ir,
  title={IR-SIM: A Lightweight Skill-Native Simulator for Navigation, Learning, and Benchmarking},
  author={Han, Ruihua and Wang, Shuai and Li, Chengyang and Gao, Rui and Wang, Xinyi and Liu, Zhe and Li, Guoliang and Lu, Yupu and Hao, Qi and Pan, Jia and Zhao, Hengshuang},
  journal={arXiv preprint arXiv:2606.08729},
  year={2026}
}