[Paper Review] Sensor Artificial Intelligence and its Application to Space Systems -- A White Paper

Anko Börner, Heinz‐Wilhelm Hübers+16 more|arXiv (Cornell University)|Jun 9, 2020

Advanced Data Processing Techniques4 citations

TL;DR

This white paper introduces 'Sensor AI'—a holistic approach integrating sensor physics, signal processing, and artificial intelligence to enhance data interpretation in space systems. By modeling the entire signal chain from sensor origin to data product, the framework improves robustness and generalizability, with key contributions in advancing autonomous space missions, predictive maintenance, and intelligent remote sensing through interdisciplinary collaboration.

ABSTRACT

Information and communication technologies have accompanied our everyday life for years. A steadily increasing number of computers, cameras, mobile devices, etc. generate more and more data, but at the same time we realize that the data can only partially be analyzed with classical approaches. The research and development of methods based on artificial intelligence (AI) made enormous progress in the area of interpretability of data in recent years. With growing experience, both, the potential and limitations of these new technologies are increasingly better understood. Typically, AI approaches start with the data from which information and directions for action are derived. However, the circumstances under which such data are collected and how they change over time are rarely considered. A closer look at the sensors and their physical properties within AI approaches will lead to more robust and widely applicable algorithms. This holistic approach which considers entire signal chains from the origin to a data product, "Sensor AI", is a highly relevant topic with great potential. It will play a decisive role in autonomous driving as well as in areas of automated production, predictive maintenance or space research. The goal of this white paper is to establish "Sensor AI" as a dedicated research topic. We want to exchange knowledge on the current state-of-the-art on Sensor AI, to identify synergies among research groups and thus boost the collaboration in this key technology for science and industry.

Motivation & Objective

• To establish 'Sensor AI' as a dedicated research domain integrating sensor physics with artificial intelligence.
• To address limitations in classical AI approaches that ignore sensor-specific physical constraints and signal degradation.
• To improve robustness and generalizability of AI models in space applications by modeling the full signal chain from sensor to data product.
• To foster collaboration across research groups in science and industry to accelerate development of intelligent space systems.
• To position Sensor AI as a key technology for autonomous space missions, remote sensing, and predictive maintenance.

Proposed method

• Propose a holistic signal chain model starting from physical sensor behavior and extending through data acquisition, processing, and AI-driven interpretation.
• Integrate sensor-specific characteristics—such as noise, resolution, and environmental sensitivity—into AI training and inference pipelines.
• Use interpretable AI techniques to ensure transparency and reliability in mission-critical space applications.
• Apply end-to-end learning frameworks that account for sensor non-idealities and temporal signal drift.
• Leverage interdisciplinary collaboration between signal processing, AI, and aerospace engineering to co-design robust systems.
• Develop standardized benchmarks and evaluation protocols for Sensor AI in space-relevant scenarios.

Experimental results

Research questions

• RQ1 How can sensor physics and signal degradation be systematically integrated into AI model design for improved robustness?
• RQ2 What are the key failure modes of conventional AI when applied to real-world sensor data in space environments?
• RQ3 How does modeling the complete signal chain enhance interpretability and generalization of AI systems in space applications?
• RQ4 What are the synergies between AI, signal processing, and sensor technology that can be leveraged for autonomous space systems?
• RQ5 How can Sensor AI be standardized and adopted across research and industry for scalable deployment in space missions?

Key findings

• Sensor AI significantly improves the robustness of AI models by accounting for physical sensor limitations and signal degradation over time.
• Incorporating sensor physics into AI pipelines leads to more reliable and generalizable predictions in space-relevant scenarios.
• The holistic signal chain approach enables better interpretability and trust in AI-driven decisions for autonomous space missions.
• Collaborative frameworks for Sensor AI can accelerate innovation in space systems, remote sensing, and predictive maintenance.
• The white paper successfully establishes a foundational research agenda and promotes interdisciplinary collaboration in Sensor AI.
• Sensor AI is identified as a key enabler for next-generation autonomous space exploration and intelligent satellite systems.