A Unified Experimental Architecture for Informative Path Planning: from Simulation to Deployment with GuadalPlanner

2026-02-11

AI Summary

This work addresses the limitations of existing informative path planning algorithms for autonomous vehicles, which are often hindered by fragmented evaluation pipelines and difficulties in transferring solutions from simulation to real-world deployment. To overcome these challenges, the authors propose a modular and unified architecture that decouples high-level decision-making from low-level control through standardized interfaces, enabling seamless integration of planning, perception, and execution modules. Built upon ROS 2, MAVLink, and MQTT, the framework supports discrete graph-based environments, multiple planning strategies, and both software- and hardware-in-the-loop configurations. Notably, it enables consistent deployment of the same algorithm across simulation, in-the-loop testing, and physical platforms without code modifications. The approach is validated on a real-world water-surface autonomous vehicle performing water quality monitoring, demonstrating its cross-platform consistency, generality, and practical utility.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Multiagent Systems: Multiagent Planning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

The evaluation of informative path planning algorithms for autonomous vehicles is often hindered by fragmented execution pipelines and limited transferability between simulation and real-world deployment. This paper introduces a unified architecture that decouples high-level decision-making from vehicle-specific control, enabling algorithms to be evaluated consistently across different abstraction levels without modification. The proposed architecture is realized through GuadalPlanner, which defines standardized interfaces between planning, sensing, and vehicle execution. It is an open and extensible research tool that supports discrete graph-based environments and interchangeable planning strategies, and is built upon widely adopted robotics technologies, including ROS2, MAVLink, and MQTT. Its design allows the same algorithmic logic to be deployed in fully simulated environments, software-in-the-loop configurations, and physical autonomous vehicles using an identical execution pipeline. The approach is validated through a set of experiments, including real-world deployment on an autonomous surface vehicle performing water quality monitoring with real-time sensor feedback.

Problem

• informative path planning
• autonomous vehicles
• simulation-to-reality transfer
• algorithm evaluation
• execution pipeline

Innovation

• informative path planning
• unified architecture
• simulation-to-deployment
• modular robotics
• autonomous vehicles