arXiv cs.AI· Yonglong Zhang, Zongwu Xie, Yang Liu·· 13 小时前AI 评分18
基于极性与时间交互及多级可靠性的航天器位姿估计框架
Polarity--Time Interaction and Multi-Level Reliability for Event-Based Spacecraft Pose Estimation
AI 导读
一个可靠性感知框架通过极性—时间定位、几何恢复、事件—CAD 精修与轨迹优化实现航天器位姿估计，在官方 SPADES 挑战测试集上取得 0.0474 的综合位姿分数，比 PASAN+IRIS 低约 5.4%。消融实验显示，完整级联将基础定位加均匀 PnP 的 0.0772 降至 0.0514；在相同单帧观测下，质量加权把常权优化的 0.0549 降至 0.0514。
正文 · 原文
Abstract:Sparse event responses produce uneven keypoint errors whose effects on spacecraft pose depend on correspondence geometry and the reliability of successive observations. We present a reliability-aware framework connecting polarity--time localization, geometric recovery, event--CAD refinement, and trajectory optimization. A three-branch representation combines positive events, negative events, and recent-event timing through cross-branch attention and gating, followed by spatiotemporal aggregation. An ordered semantic-point head estimates relative correspondence precision for geometrically constrained pose recovery. Event-edge and CAD-projection agreement then guide local pose refinement under keypoint-geometry safeguards. At the sequence level, a ten-dimensional descriptor combines heatmap shape, reprojection consistency, and geometric conditioning to set time-aligned observation scales. On the official SPADES challenge test set, the complete system achieves a combined pose score of 0.0474, approximately 5.4\% below PASAN+IRIS. Validation ablations reduce the score from 0.0772 for base localization with uniform PnP to 0.0514 for the complete cascade; on identical single-frame observations, quality weighting reduces the score from 0.0549 with constant-weight optimization to 0.0514.
| Subjects: | Artificial Intelligence (cs.AI); Robotics (cs.RO) |
| Cite as: | arXiv:2610.36625 [cs.AI] |
| (or arXiv:2610.36625v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36625 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yonglong Zhang [view email]
[v1]
Tue, 27 Oct 2026 04:29:19 UTC (464 KB)
来源：arXiv cs.AI · arxiv.org