Quality-Adaptive Multi-UAV 3D Reconstruction with Sparse Workload Redistribution
2026-07-27 • Robotics
Robotics
AI summaryⓘ
The authors developed a method for multiple drones (UAVs) to work together and create detailed 3D maps of unknown areas more efficiently. Their approach lets users set how detailed the map should be and helps drones pick good viewpoints based on confidence in their measurements. They also added two ways for the drones to coordinate: encouraging them to spread out locally and fixing imbalances globally only when needed. Tests showed their method is better at covering areas and making accurate maps compared to others. The authors have shared their code so others can use it too.
3D reconstructionUAV (Unmanned Aerial Vehicle)path planningdecentralized decision-makingTruncated Signed Distance Function (TSDF)viewpoint selectioninformation gainclusteringtask assignment
Authors
Benjamin Sportich, Kenza Boubakri, Olivier Simonin, Alessandro Renzaglia
Abstract
3D reconstruction of unknown environments is a key application in robotics but is severely limited by the computational and energy capabilities of current aerial platforms. Deploying multiple UAVs and providing efficient and scalable path planning strategies are common approaches, but effective online coordination among UAVs remains a significant challenge. To address this problem, we propose a quality-adaptive decentralized decision-making strategy to build a 3D map with user-defined degrees of fidelity. The approach integrates a quality-oriented criterion based on TSDF confidence into view generation and information gain estimation to produce viewpoints consistent with the desired fidelity target. Additionally, we employ two levels of coordination: a penalty factor in the viewpoint evaluation to encourage local dispersion among the UAVs and a global imbalance correction mechanism. The latter, based on regularized clustering and optimal task assignment, is only triggered when an unbalanced configuration relative to high-information regions is detected. Simulation results demonstrate that the proposed method improves path efficiency compared to state-of-the-art multi-UAV exploration approaches, while also achieving higher-fidelity reconstructions in terms of coverage and accuracy. We make our code publicly available to the community.