Write-Safe Flow Field Mapping under Ambiguous Onboard Sensing and Localization Drift

arXiv:2607.27713v1 Announce Type: new Abstract: Mobile robots can infer local flow structure from onboard sensing, but a locally plausible estimate is not always safe to write into a global map. Similar flow structures may produce ambiguous observations, while localization drift causes predicted patches to be written at incorrect locations. Repeated misregistered updates then accumulate into persistent ghost structures. We address this failure mode with a map-reference-aware conservative fusion framework. The model predicts a local velocity patch and a learned write-safety score that continuously attenuates uncertain map updates while permitting initialization when no reliable map reference is available. Across synthetic jet and crossflow environments, the proposed method reduces average ghost contamination by 42% relative to ungated fusion. A zero-shot hardware replay using real pressure and optical-flow measurements from a thruster wake further reduces ghost contamination by 39% while retaining 81% map coverage. These results show that safe map writing is critical for flow mapping under ambiguous sensing and localization drift.

Related

• Safe Polytope-in-Polytope Motion Planning and Control with Control Barrier Functions
• Fast Expanding Safe Circular Regions for Efficient Local Path Planning
• Online Structure Learning and Planning for Autonomous Robot Navigation using Active Inference
• Collaborative Navigation and Exploration with eta-Sparse Gaussian Processes

Source: arXiv cs.RO | 2026-07-31