When Weak Reports Matter: Staged Anchored Fusion for Cooperative UAV Sensing

2026-10-06

AI Summary

This study addresses the loss of critical weak evidence caused by local multipath suppression in collaborative perception. We propose a staged anchor-recovery method that first retains strongly confirmed targets and then leverages redundant strong anchors to directionally retrieve compatible weak reports. Theoretically, we derive corroboration and bidirectional cost laws and prove the completeness of a lossless residual filtering mechanism. Experimental evaluations across 1,024 five-UAV trials demonstrate that the proposed approach identifies 30 additional matched targets while reducing weak uploads by 97.4% and communication payload by 4.5%. These results confirm that the method achieves high-precision collaborative perception with minimal overhead.

Abstract

Local multipath rejection can erase evidence needed for cooperative sensing. We propose staged anchored recovery: preserve strong-only confirmations, then query compatible weak reports using unused strong anchors. For any number of sensing nodes, we prove lossless residual screening and derive corroboration and bidirectional cost laws. In 1,024 five-UAV drops, recovery adds 30 matched targets and three false outputs over strict consensus, matching one-pass anchored confirmation's detection counts while reducing weak uploads by 97.4%. Equal-sized cue/report records yield 4.5% less payload than uploading all eligible reports. Independent validation recovers four additional targets with no observed false outputs.

Problem

• cooperative UAV sensing
• multipath rejection
• weak reports
• target detection

Innovation

• Cooperative UAV Sensing
• Staged Anchored Fusion
• Multipath Rejection
• Weak Report Recovery
• Lossless Residual Screening