From Sketch Prior to Trajectories: A Mission-Oriented Coordinated Navigation Framework for Indoor UAV Swarm

Jul 16, 2026

Indoor UAV swarms for inspection, security patrol, and logistics often follow mission-defined visit sequences rather than exploration goals. The framework leverages pre-deployment sketch-map priors like floor plans, CAD layouts, and evacuation diagrams, exploiting the layered flight nature where transitions are largely planar. Onboard sensing performs topological alignment, fuses aligned priors with online observations to build mission-oriented traversability, then uses layered 2D guidance plus 3D trajectory optimization. Simulations and real experiments verify performance in structured multi-room environments under both communication and communication-loss cases.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages8

Reading Time20 min

Introduction

Mission-oriented vs exploration-oriented indoor UAV operation

Sketch-map priors and the conversion challenge

Layered 2D–3D structure for coordinated navigation

From Sketch Prior to Trajectories: A Mission-Oriented Coordinated Navigation Framework for Indoor UAV Swarm Xinhang Xu∗ , Ruiyang Liu∗ , Haotian Jin∗ , Yi Wang, Hongming Shen, Jianping Li Member, IEEE, Lihua Xie1 , Fellow, IEEE arXiv :2607 . 11386v1 [ cs .RO] 13 Jul 2026 Abstract—UAV swarm for applications, such as indoor inspection, security patrol, and logistics delivery, are often mission-oriented rather than exploration-oriented. In these tasks, UAVs are required to visit task-relevant regions in a prescribed sequence, and such region-level mission information can often be obtained from pre-deployment sketch-map priors, such as floor plans, CAD layouts, or evacuation diagrams. Although these tasks are executed in three-dimensional space, UAVs usually fly within a specific altitude layer or a nearly fixed altitude range on each floor, making mission-level region transitions mainly governed by planar connectivity. Based on these observations, this paper proposes a mission-oriented coordinated navigation framework that exploits sketch-map priors for multi-UAV indoor operations. Onboard observations are used to perform topological alignment, and the aligned prior is fused with online observations to construct a mission-oriented traversability representation. A layered 2D–3D coordinated navigation framework is further developed, where 2D guided path planning generates mission-oriented guide paths and guide-driven 3D trajectory optimization produces dynamically feasible and collision-free trajectories. Simulation and realworld experiments validate the effectiveness of the proposed framework in structured multi-room indoor environments and further demonstrate its coordinated navigation capability under both communication-available and communication-loss conditions. Multi-floor simulation results show the scalability of the system to layered indoor structures. I. INTRODUCTION Multi-UAV systems have demonstrated significant potential in indoor inspection, emergency response, security patrol, and logistics operations. Recent advances in aerial autonomy have substantially enhanced the motion capability of individual platforms, enabling even precise and aggressive maneuvers in confined spaces [1] . By leveraging cooperative execution, heterogeneous sensing capabilities, and complementary payload configurations, multiple UAVs can accomplish mission objectives that are difficult for a single platform to achieve. However, practical indoor environments are usually GNSS-denied and contain interconnected rooms, corridors, stairwells, and functional spaces, making efficient and coordinated multi-UAV mission execution challenging. Existing UAV navigation research is primarily environmentally centric. Exploration-related methods [2]–[6] focus on recovering unknown environmental structures through frontier-based planning, information-gain maximization, and cooperative mapping. Coverage-related methods [7]–[11] ∗Equal Contribution. All authors are with the School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore. 1 Corresponding author. Email: [elxie@ntu.edu.sg](elxie@ntu.edu.sg). aim to visit all reachable regions for applications such as cleaning, inspection, and environmental monitoring. Although these methods have achieved substantial progress in environmental reconstruction and scene understanding, they primarily aim to achieve completeness in environment covering. In many indoor tasks, however, UAVs are not required to reconstruct the entire environment or visit every accessible region. Instead, missions are usually specified by task-relevant regions and execution orders [12]–[14], such as checking designated patrol areas, reaching emergency response locations, or visiting delivery destinations. Directly applying environment-centric methods may therefore introduce task-irrelevant sensing and motion, reducing mission efficiency. Fortunately, many indoor environment

FAQs

What is the core problem this framework addresses for indoor UAV swarms?

Indoor missions require visiting task-relevant regions in a prescribed order, so mission efficiency depends on coordinated region-level navigation rather than environment-wide exploration or coverage.

How does the method use sketch-map priors during execution?

Onboard observations perform topological alignment, then the aligned prior is fused with online sensing to create a mission-oriented traversability representation that can be updated continuously.

What is the layered 2D–3D design and why is it needed?

2D guided path planning handles mission-level reasoning using planar connectivity, while 3D trajectory optimization ensures dynamically feasible, collision-free motion for the UAVs in three-dimensional space.

Jul 16, 2026

Upload by Genevieve