{"paper":{"title":"MonoSpheres: Large-Scale Monocular SLAM-Based UAV Exploration through Perception-Coupled Mapping and Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Monocular SLAM with oversampled free-space mapping and uncertainty-aware planning lets UAVs explore large unstructured 3D outdoor environments.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Martin Saska, Mat\\v{e}j Petrl\\'ik, Tom\\'a\\v{s} Musil","submitted_at":"2025-11-21T15:11:15Z","abstract_excerpt":"Autonomous exploration of unknown environments is a key capability for mobile robots, but it is largely unsolved for robots equipped with only a single monocular camera and no dense range sensors. In this paper, we present a novel approach to monocular vision-based exploration that can safely cover large-scale unstructured indoor and outdoor 3D environments by explicitly accounting for the properties of a sparse monocular SLAM frontend in both mapping and planning. The mapping module solves the problems of sparse depth data, free-space gaps, and large depth uncertainty by oversampling free spa"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"To the best of the authors' knowledge, the proposed method is the first to achieve 3D monocular exploration in real-world unstructured outdoor environments.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the sparse monocular SLAM frontend, when augmented with oversampling and uncertainty tracking, provides sufficiently reliable free-space information for safe planning in textureless or low-parallax regions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MonoSpheres achieves large-scale 3D monocular UAV exploration in unstructured real-world environments by oversampling free space in texture-sparse areas, tracking obstacle uncertainty, and using rapid replanning with perception-aware heading control.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Monocular SLAM with oversampled free-space mapping and uncertainty-aware planning lets UAVs explore large unstructured 3D outdoor environments.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3048f0b49e59e1a58df9bd62160eba9140f6a4b2e863cd84a736011bca18c2a8"},"source":{"id":"2511.17299","kind":"arxiv","version":2},"verdict":{"id":"ba8e9e3a-3476-467d-9cd0-2dc913658340","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T20:42:38.413160Z","strongest_claim":"To the best of the authors' knowledge, the proposed method is the first to achieve 3D monocular exploration in real-world unstructured outdoor environments.","one_line_summary":"MonoSpheres achieves large-scale 3D monocular UAV exploration in unstructured real-world environments by oversampling free space in texture-sparse areas, tracking obstacle uncertainty, and using rapid replanning with perception-aware heading control.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the sparse monocular SLAM frontend, when augmented with oversampling and uncertainty tracking, provides sufficiently reliable free-space information for safe planning in textureless or low-parallax regions.","pith_extraction_headline":"Monocular SLAM with oversampled free-space mapping and uncertainty-aware planning lets UAVs explore large unstructured 3D outdoor environments."},"references":{"count":26,"sample":[{"doi":"","year":2022,"title":"CERBERUS in the DARPA Subterranean Challenge,","work_id":"52196a77-ed63-4516-97ad-76c5bd0ccd8b","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Heterogeneous Ground and Air Platforms, Homogeneous Sensing: Team CSIRO Data61’s Approach to the DARPA Subterranean Challenge,","work_id":"05c61a42-35ea-4efe-8e68-f4710f229ea6","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"UA Vs Beneath the Sur- face: Cooperative Autonomy for Subterranean Search and Rescue in DARPA SubT,","work_id":"6096daee-031f-43e3-99a4-b728d715d4ce","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"From monocular SLAM to autonomous drone exploration,","work_id":"66412039-a520-45b4-8e96-9948f9f9013b","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Monocular 3D Exploration using Lines-of-Sight and Local Maps,","work_id":"5e64b14d-dd1e-4caf-9e0b-0ff68d984da1","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":26,"snapshot_sha256":"14aec9957bd8ece24f74bdfa40c6f7a8cf7059619e99d81996ca8fce9f1e2736","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"cea926c97edc838c1ee53fee77609280f1f4b295a75e898c9e291d97abe93305"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}