IR-SIM
A lightweight, YAML-configured Python robot simulator for navigation, control and learning research, with built-in collision detection for robots, sensors and environments.
IR-SIM is a lightweight Python robot simulator aimed at navigation, control and learning research, providing a simple framework with built-in collision detection for modeling robots, sensors and environments. Scenarios are configured through straightforward YAML files rather than complex code, letting robotics and learning algorithms be prototyped quickly with minimal coding and hardware requirements.
It can simulate diverse robot kinematics, sensors and behaviors, supports customizable collision-detection and behavior policies for each object, and is suited to multi-agent and robot-learning research, rendering results with a lightweight Matplotlib-based renderer for quick debugging. Demonstrations in the project include multi-robot collision avoidance, an Ackermann robot with 2D LiDAR, and dynamic random obstacles.
IR-SIM requires Python 3.10 or newer, installs through pip with an optional extras set for keyboard control, or can be built from a source checkout with pip or uv, and is released under the MIT license.