Guarantee-Driven Mapping: Coordinated LiDAR-Vision Robots for Dense 3D Reconstruction

About the Project

These projects are open to students worldwide, but have no funding attached. Therefore, the successful applicant will be expected to fund tuition fees at the relevant level (home or international) and any applicable additional research costs. Please consider this before applying.

Accurate 3D reconstruction of critical infrastructure—such as power plants, transport networks, and large industrial facilities—as well as agricultural assets is essential for condition monitoring, predictive maintenance, and safety assurance. Yet many inspection workflows still depend on a single sensing modality (vision-only or LiDAR-only), yielding partial, inconsistent, and occlusion-prone reconstructions, especially in cluttered or geometrically complex scenes.

In agriculture, single-drone surveys often cannot cover large fields within narrow weather windows, producing uneven data quality and costly re-flights. More broadly, current aerial and ground systems rarely provide guarantees of map completeness or quality, leading to coverage gaps, drift accumulation, and repeat surveys. These shortcomings reduce situational awareness and mapping reliability precisely where precision and timeliness matter most.

This project introduces a guarantee-driven mapping framework that coordinates two heterogeneous mobile robots equipped with different sensors (e.g. camera-only + 3D-LiDAR-only) to produce dense, globally consistent 3D maps with verifiable coverage guarantees. Building on recent advances in guarantee-based active mapping and multi-robot coordination, the proposed system integrates motion planning, cross-sensor calibration, and uncertainty-aware data fusion to minimize occlusions and drift under realistic battery and time constraints. By combining complementary sensing modalities and enforcing formal coverage guarantees, the framework aims to achieve efficient, drift-free, and occlusion-resilient reconstruction of complex environments, enabling more reliable and cost-effective infrastructure inspections.

To address the principal question “how can a small team of heterogeneous ground robots produce, in a single deployment, a drift resistant, globally consistent 3D map with explicit coverage and fidelity guarantees under tight battery and time budgets?”, this PhD project will be focusing on:

(1)  AI Planning for Coordinated Robot Operations. Develop a SLAM-aware heterogeneous fleet planner that

(i)  schedule inter-agent loop closures to bound drift and

(ii) PPrforms visibility-aware active view planning: when occluded/under-observed regions are detected, it generates and replans complementary viewpoints until map completeness/quality thresholds are met, under kinematic, safety, and battery/time constraints;

(2)  Multi-Agent Multimodal Collaborative SLAM for 3D Dense Mapping. Develop a collaborative LiDAR–vision SLAM pipeline for a heterogeneous team (camera-only + 3D LiDAR-only) that

(i)  performs cross-modal place recognition and inter-agent loop closures,

(ii) robustly handles dynamics via motion segmentation and outlier-resistant pose-graph optimization,

(iii)produces drift-bounded dense reconstructions via volumetric fusion with online time/extrinsic calibration and global consistency checks.

This research will have the potential to demonstrate its practical value on onshore wind turbines and/or agricultural lands. Methodologically, this project introduces visibility-aware multi-agent planners and cross-modal LiDAR–vision fusion with resource-aware scheduling, alongside open benchmarks and ablations that isolate the roles of sensing asymmetry in dense 3D mapping.

Informal enquiries can be made by contacting Dr F Jovan (ferdian.jovan@abdn.ac.uk)

Decisions will be based on academic merit. The successful applicant should have, or expect to obtain, a UK Honours Degree at 2.1 (or equivalent) in Computing Science with basic understanding of Robot Operating System.

We encourage applications from all backgrounds and communities, and are committed to having a diverse, inclusive team.

Application Procedure:

Formal applications can be completed online: https://www.abdn.ac.uk/pgap/login.php.

You should apply for Degree of Doctor of Philosophy in Computing Science to ensure your application is passed to the correct team for processing.

Please clearly note the name of the lead supervisor and project titleon the application form. If you do not include these details, it may not be considered for the project.

Your application must include: A personal statement, an up-to-date copy of your academic CV, and clear copies of your educational certificates and transcripts.

Please note: you do not need to provide a research proposal with this application.

If you require any additional assistance in submitting your application or have any queries about the application process, please don't hesitate to contact us at researchadmissions@abdn.ac.uk

Funding Notes

This is a self-funding project open to students worldwide. Our typical start dates for this programme are February or October.

Fees for this programme can be found here Finance and Funding | Study Here | The University of Aberdeen.

Additional Research costs of £2,000 per annum will be required for this project. These are in addition to tuition fees.