IR-SIM: A Lightweight Skill-Native Simulator for Navigation, Learning, and Benchmarking

2026-06-07

AI Summary

This work addresses the limitations of existing robotic simulators, which rely on custom code or complex interfaces that hinder rapid prototyping with large language models (LLMs). The authors propose IR-SIM, a lightweight, skill-native navigation simulator that unifies the definition of kinematics, LiDAR perception, collision detection, behavioral policies, and visualization through YAML configuration. For the first time, this framework enables fully reproducible simulations driven solely by natural language prompts, requiring no coding to generate or modify navigation scenarios. IR-SIM facilitates training of obstacle avoidance strategies and benchmarking of social navigation behaviors, while demonstrating seamless transferability to high-fidelity simulators and physical robot platforms.

Abstract

Simulation plays a key role in automated robotics research supported by large language models (LLMs). However, existing simulators often require custom code or complex interfaces, creating a barrier to rapid prototyping and automated algorithm development. To this end, we propose the Intelligent Robot Simulator (IR-SIM), a lightweight skill-native navigation simulator designed for rapid scenario construction, benchmarking, and robot learning. In IR-SIM, scenarios are entirely defined by YAML configuration files that specify mobile robot kinematics, geometric collision checking, LiDAR sensing, visualization, and behavior modules. This design makes robotic simulation fully describable and reproducible, allowing scenarios to be generated and modified from text prompts through the proposed IR-SIM agent skills. The resulting scenarios can be used for automated benchmarking of navigation algorithms and for automated generation of training data for learning methods. Furthermore, IR-SIM provides bridges to high fidelity simulators and real world deployment, allowing users to validate their algorithms in more realistic settings after prototyping without extra coding. The experiments showcase the convenience and versatility of IR-SIM in multiple tasks: constructing navigation scenarios from natural language, training a collision avoidance policy, benchmarking social navigation policies, and bridging to high fidelity simulators and real world deployment. The project website is available at https://github.com/hanruihua/ir-sim.

Problem

• robot simulation
• rapid prototyping
• automated algorithm development
• LLM-based robotics
• navigation benchmarking

Innovation

• skill-native simulation
• YAML-based scenario definition
• LLM-driven robot prototyping
• automated benchmarking
• lightweight navigation simulator