Deep Learning-Based Robust Optical Guidance for Hypersonic Platforms

Sensor-based guidance is required for long-range platforms. To bypass the structural limitation of classical registration on reference image framework, we offer in this paper to encode a stack of images of the scene into a deep network. Relying on a stack is showed to be relevant on bimodal scene (e.g. when the scene can or can not be snowy).

@article{chan-hon-tong2025_2505.06389,
  title={ Deep Learning-Based Robust Optical Guidance for Hypersonic Platforms },
  author={ Adrien Chan-Hon-Tong and Aurélien Plyer and Baptiste Cadalen and Laurent Serre },
  journal={arXiv preprint arXiv:2505.06389},
  year={ 2025 }
}