Coverage-Recon: Coordinated Multi-Drone Image Sampling with Online Map Feedback

2025-10-21

AI Summary

To address incomplete coverage, insufficient reconstruction accuracy, and lack of real-time feedback in multi-UAV collaborative 3D reconstruction, this paper proposes a cooperative sampling framework integrated with online map feedback. Methodologically, it introduces, for the first time, the geometric uncertainty estimated by NeuralRecon—a real-time neural reconstruction system—as a key importance metric to dynamically update coverage control weights. A quadratic-programming (QP)-based, orientation-aware coverage controller is combined with motion planning under safety constraints, enabling closed-loop optimization of coordinated flight and multi-view image acquisition. Experiments demonstrate that the proposed approach significantly improves both reconstruction completeness and geometric accuracy, outperforming conventional feedback-free baselines in both simulation and real-world deployments. These results validate the effectiveness of uncertainty-driven, real-time collaborative mapping for multi-UAV systems.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Reasoning under Uncertainty: Uncertainty Representations
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

This article addresses collaborative 3D map reconstruction using multiple drones. Achieving high-quality reconstruction requires capturing images of keypoints within the target scene from diverse viewing angles, and coverage control offers an effective framework to meet this requirement. Meanwhile, recent advances in real-time 3D reconstruction algorithms make it possible to render an evolving map during flight, enabling immediate feedback to guide drone motion. Building on this, we present Coverage-Recon, a novel coordinated image sampling algorithm that integrates online map feedback to improve reconstruction quality on-the-fly. In Coverage-Recon, the coordinated motion of drones is governed by a Quadratic Programming (QP)-based angle-aware coverage controller, which ensures multi-viewpoint image capture while enforcing safety constraints. The captured images are processed in real time by the NeuralRecon algorithm to generate an evolving 3D mesh. Mesh changes across the scene are interpreted as indicators of reconstruction uncertainty and serve as feedback to update the importance index of the coverage control as the map evolves. The effectiveness of Coverage-Recon is validated through simulation and experiments, demonstrating both qualitatively and quantitatively that incorporating online map feedback yields more complete and accurate 3D reconstructions than conventional methods. Project page: https://htnk-lab.github.io/coverage-recon/

Problem

• Coordinated multi-drone image sampling for 3D reconstruction
• Integrating online map feedback to improve reconstruction quality
• Ensuring multi-viewpoint coverage while maintaining safety constraints

Innovation

• Uses QP-based coverage controller for multi-drone coordination
• Integrates NeuralRecon for real-time 3D mesh generation
• Employs mesh changes as feedback to update coverage importance