Event polarity timing improves spacecraft pose estimation accuracy
Polarity--Time Interaction and Multi-Level Reliability for Event-Based Spacecraft Pose Estimation
Artificial IntelligenceRobotics
Summary
Estimating the position and orientation of spacecraft using event-based sensors can be tricky because the sensor data is sparse and uneven. The authors developed a new method that carefully considers the timing and type (polarity) of sensor events, combines this information using special attention mechanisms, and checks the geometry to improve pose accuracy. They also refine the estimated position using a 3D model of the spacecraft and optimize results over time. Their approach performs better than previous methods on a standard spacecraft pose estimation challenge.
What this means in practice
- •For satellite navigation engineers: improve spacecraft orientation tracking by integrating event polarity and timing with geometric and model-based refinement methods
- •For robotics localization teams: enhance pose accuracy in robotic systems using sparse event data by combining event polarity, timing cues, and geometric constraints
Authors
Yonglong Zhang, Zongwu Xie, Yang Liu
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.