通过提示实现视觉语言模型发射后能力扩展用于在轨航天器检测
Post-Launch Capability Expansion of Vision-Language Models via Prompting for On-Orbit Spacecraft Inspection
AI总结：
研究利用提示驱动的视觉语言模型在轨扩展语义能力，无需修改权重即可通过自然语言提示检测新航天器部件，在129张图像上零样本实例分割达到0.385 mAP@0.5。
摘要：
星载检测系统通常在发射前部署感知模型，之后更新模型权重或扩展固定标签集在操作上变得不可行。虽然监督模型可以在飞行前集成，但在轨道上添加新的语义能力需要重新训练和重新上传参数。我们研究提示驱动的视觉语言模型是否能够实现发射后语义扩展，允许通过自然语言提示指定新的航天器部件，而无需修改星载权重。我们在一个包含129张先前未见卫星图像的测试集上，采用严格冻结的单次推理协议，评估了航天器部件的零样本实例分割。在固定全局阈值且无后处理的情况下，SAM3达到0.385 mAP@0.5和0.267 mAP@0.5:0.95。性能强烈依赖于尺度：大型结构元素如航天器主体（0.639 AP@0.50）和太阳翼（0.598 AP@0.5）定位可靠，而相对较小的附件如天线（0.221 AP@0.5）和推进器（0.081 AP@0.5）仍然困难。提示形式影响性能，包含空间和几何描述符的结构化提示相比短类别名称提示提升高达82%。该模型在当代嵌入式GPU的内存和计算范围内运行，表明提示驱动的定位可以为主要航天器结构提供发射后语义扩展的实用机制，同时突显了在轨道域偏移下细粒度部件零样本定位的局限性。
英文摘要：
Spaceborne inspection systems often deploy perception models prior to launch, after which updating model weights or expanding fixed label sets becomes operationally impractical. While supervised models can be integrated pre-flight, adding new semantic capabilities in orbit requires retraining and re-uploading parameters. We investigate whether prompt-driven vision--language models can enable post-launch semantic expansion, allowing new spacecraft components to be specified via natural-language prompts without modifying onboard weights. We evaluate zero-shot instance segmentation of spacecraft components under a strictly frozen, single-pass inference protocol on a test set of $129$ images of previously unseen satellites. Under fixed global thresholds and no post-processing, SAM3 achieves $0.385$ mAP@$0.5$ and $0.267$ mAP@$0.5{:}0.95$. Performance is strongly scale-dependent: large structural elements like spacecraft bodies ($0.639$ AP@$0.50$) and solar arrays ($0.598$ AP@$0.5$) localize reliably, while relatively small appendages like antennas ($0.221$ AP@$0.5$) and thrusters ($0.081$ AP@$0.5$) remain difficult. Prompt formulation influences performance, with structured prompts incorporating spatial and geometric descriptors yielding up to $82%$ improvement over short category-name prompts. The model operates within the memory and compute envelope of contemporary embedded GPUs, suggesting prompt-driven grounding can provide a practical mechanism for post-launch semantic extension of dominant spacecraft structures while highlighting limitations of zero-shot localization for fine-scale components under orbital domain shift.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
