AI 中文总结
本研究利用DINOv3基础模型替换小编码器，在仅合成数据训练下，将航天器姿态估计平均旋转误差降至太阳灯1.56°、光箱1.17°，并验证了嵌入式推理可行性。
AI 中文摘要
我们提出对先前航天器姿态估计架构的改进，在SPEED+光箱和太阳灯测试集上，针对已知非合作航天器，实现了我们所知的最低已发表平均旋转误差。通过采用先前建立的基于热图的姿态估计架构，并用大型自监督ViT基础模型（DINOv3）替代先前工作中较小的卷积和ViT编码器，我们展示了姿态估计精度从300M参数提升至840M参数，且尚未观察到饱和现象。我们还在Jetson Orin NX 16GB上评估了840M模型，测得单次网络推理每裁剪块133.8毫秒，板载功耗32.0瓦。这些测量表明，在具有轨道飞行资质的处理器系列上，嵌入式推理是可行的。我们的最终模型在仅使用合成数据训练的情况下，在光箱和太阳灯领域均优于先前模型。我们最佳模型使用DINOv3 840M经LoRA适配作为编码器（秩64，三种子集成，四旋转测试时增强），在太阳灯上平均旋转误差为1.56°，在光箱上为1.17°，而先前我们所知的最佳平均旋转误差分别为EagerNet的2.66°和1.75°。
英文摘要
We present an improvement on previous spacecraft pose estimation architectures that results in the lowest published mean rotation errors we know of on the SPEED+ lightbox and sunlamp test sets for a known, non-cooperative spacecraft. By using a previously established heatmap-based pose estimation architecture and adapting a large self-supervised ViT foundation model (DINOv3) in place of the smaller convolutional and ViT encoders of previous work, we show that pose estimation accuracy improves from 300M to 840M parameters with no saturation yet observed. We also evaluate our 840M model on a Jetson Orin NX 16GB, measuring single-pass network inference at 133.8 ms per crop with a board draw of 32.0 W. These measurements demonstrate embedded inference feasibility on a processor family with orbital flight heritage. Our resulting model outperforms previous models across lightbox and sunlamp domains while training only on synthetic data. Our best model, using DINOv3 840M adapted with LoRA as the encoder (rank 64, three-seed ensemble with four-rotation test-time augmentation), results in $1.56^\circ$ mean rotation error on sunlamp and $1.17^\circ$ on lightbox, compared to the previous best mean rotation errors we know of on these test sets, $2.66^\circ$ and $1.75^\circ$ by EagerNet.
Comments6 pages, 3 figures, 4 tables. A shorter version was accepted to the IROS 2026 Space Robotics Workshop (non-archival)
