HuNavSim 2.0

2025-07-23

AI Summary

To address the limitations of simplistic human behavior modeling and insufficient simulation fidelity in human-robot coexistence scenarios, this paper proposes and open-sources a modular human navigation simulator built on ROS 2. Methodologically, it innovatively extends the action-condition composition mechanism of Behavior Trees to enable flexible, context-aware construction of diverse navigation strategies—including collision avoidance, leader-following, and group-level interactions. The system is compatible with mainstream simulation platforms such as Gazebo and NVIDIA Isaac Sim, supporting scalable multi-agent co-simulation. Experimental evaluation demonstrates substantial improvements in behavioral expressiveness and scene realism compared to prior approaches. The framework provides an efficient, reproducible, and extensible benchmark for developing and evaluating human-aware robot navigation algorithms, facilitating rigorous validation under realistic human motion dynamics and social interaction constraints.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Intelligent Robots: Human-Robot Interaction

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

This work presents a new iteration of the Human Navigation Simulator (HuNavSim), a novel open-source tool for the simulation of different human-agent navigation behaviors in scenarios with mobile robots. The tool, programmed under the ROS 2 framework, can be used together with different well-known robotics simulators such as Gazebo or NVidia Isaac Sim. The main goal is to facilitate the development and evaluation of human-aware robot navigation systems in simulation. In this new version, several features have been improved and new ones added, such as the extended set of actions and conditions that can be combined in Behavior Trees to compound complex and realistic human behaviors.

Problem

• Simulate human-agent navigation behaviors with mobile robots
• Facilitate human-aware robot navigation system development
• Enhance Behavior Trees for complex human behaviors

Innovation

• ROS 2 framework for human-agent navigation simulation
• Integration with Gazebo and NVidia Isaac Sim
• Behavior Trees for complex human behaviors