AS2FM: Enabling Statistical Model Checking of ROS 2 Systems for Robust Autonomy

2025-08-26

AI Summary

To address the challenge of verifying robustness of autonomous robots in unknown environments during design, this paper proposes a formal verification method integrating ROS 2 and behavior trees. The approach models the system using an extended SCXML language that uniformly represents both ROS 2 nodes and behavior tree components. An automated toolchain, AS2FM, is developed to translate such models into the JANI standard format. Verification leverages statistical model checking (SMC) for efficient, scalable property validation. Evaluated on consumer-grade hardware, the method achieves sub-second verification times, with runtime scaling linearly—rather than exponentially—with model size, outperforming existing approaches. Crucially, it successfully identified previously unknown defects in the ROS 2 middleware during case studies, thereby significantly strengthening robustness assurance at the design stage.

Technology Category

• Intelligent Robots: State Estimation
• Natural Language Processing: Safety and Robustness
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Designing robotic systems to act autonomously in unforeseen environments is a challenging task. This work presents a novel approach to use formal verification, specifically Statistical Model Checking (SMC), to verify system properties of autonomous robots at design-time. We introduce an extension of the SCXML format, designed to model system components including both Robot Operating System 2 (ROS 2) and Behavior Tree (BT) features. Further, we contribute Autonomous Systems to Formal Models (AS2FM), a tool to translate the full system model into JANI. The use of JANI, a standard format for quantitative model checking, enables verification of system properties with off-the-shelf SMC tools. We demonstrate the practical usability of AS2FM both in terms of applicability to real-world autonomous robotic control systems, and in terms of verification runtime scaling. We provide a case study, where we successfully identify problems in a ROS 2-based robotic manipulation use case that is verifiable in less than one second using consumer hardware. Additionally, we compare to the state of the art and demonstrate that our method is more comprehensive in system feature support, and that the verification runtime scales linearly with the size of the model, instead of exponentially.

Problem

• Verifying autonomous robot system properties using Statistical Model Checking
• Translating ROS 2 and Behavior Tree models into formal verification format
• Identifying problems in robotic systems through scalable model checking

Innovation

• Extends SCXML format for ROS 2 modeling
• Develops AS2FM tool for JANI translation
• Enables statistical model checking with standard tools