Sylvester Kaczmarek

Secure, Verifiable Onboard Intelligence for Autonomous Space Systems

Hardware can reach new worlds. My work focuses on the secure, verifiable intelligence autonomous systems need to operate safely under uncertainty, constrained computing resources, and cyberattack.

My general fields are advanced artificial intelligence and cybersecurity for safety-critical cyber-physical systems, unified by a focus on first-principles safety, security, and stability. I specialise in architecting secure-by-design, interpretable hybrid AI systems for autonomous space missions.

My work combines centralised safety assurance with distributed edge intelligence across spacecraft, robots, sensors, and computing nodes. These systems use onboard processing, robust planning, hardware-software co-design, and advanced computing architectures to operate under uncertainty, limited communications, constrained energy, and cyberattack.

This approach reflects a proven architectural principle for complex safety-critical systems: centralised command provides strategic coherence and enforceable safety constraints, while decentralised execution provides adaptability and resilience in dynamic environments. It enables increasingly capable autonomous missions without sacrificing control, accountability, or mission assurance.

My work in this domain is actively supported by key national security and space innovation bodies including the UK Space Agency, the UK's National Cyber Security Centre (NCSC, part of GCHQ), and the U.S. Space Force's SDA TAP Lab. Furthermore, my broader contributions to advancing Artificial Intelligence for Space Exploration and Humanity have been recognized with an Award of Merit by the European Space Agency (ESA) and Frontier Development Lab (FDL) Europe. My expertise is also sought at the highest levels of policy, contributing expert analysis and strategic recommendations to the UK Parliament's House of Lords Select Committee on UK Engagement with Space on AI, autonomy, cybersecurity, and governance. This expertise is strengthened by specialised trainings and certifications from organisations such as NATO, The Alan Turing Institute, CISA, FEMA, IAEA, and the Cloud Security Alliance.

My work advances the safety, efficiency, and sustainability of space-based robotic intelligence, cislunar mobility, and autonomous physical-world operations. It draws on modern AI methods including deep reinforcement learning, multimodal large language models (LLMs), graph neural networks (GNNs), self-supervised learning, event-based vision, spiking neural networks (SNNs), and agentic systems, while developing foundational mechanisms to verify, constrain, and control their behaviour. This synthesis of advanced AI, verifiable control, and neuroscience-inspired architectures supports the protection of critical infrastructure through work with organisations including NASA, ESA, UKSA, NATO, The Alan Turing Institute, the European Space Resources Innovation Centre, and the Luxembourg Space Agency. It also advances OS’s robotic intelligence programme and contributes to new standards for autonomous systems that can operate reliably and safely far beyond Earth’s immediate vicinity.

In parallel to these technical pursuits, my approach is aligned with the principles of machine alignment, including the integration of human values such as fairness, responsibility, and sustainability into AI systems. This involves developing systems grounded in verifiable mechanisms derived from first principles, with hard operational constraints enforced at the system's dynamic core. The objective is to create intelligence that remains transparent, amenable to expert knowledge, and subject to meaningful human control.

I also emphasise ethical frameworks and stakeholder engagement throughout the development of advanced AI. Geoffrey Hinton highlighted the urgency of this challenge in his Nobel address, warning that advanced AI systems "are no longer science fiction" and that "we urgently need research on how to prevent these new beings from wanting to take control". This concern resonates strongly with my work. As autonomous intelligence becomes more capable and operates farther from direct human oversight, safety, alignment, and control must be treated as foundational engineering requirements.

Credit: NASA / William Anders, Apollo 8

The "Earthrise" photograph from Apollo 8, often called the most influential environmental photo ever taken. This view of our fragile home is the ultimate "why" for my work. It is a constant reminder that the intelligent systems we build must be embedded with the wisdom and responsibility this perspective demands.

Driving questions such as "How can we build robust and trustworthy AI for complex autonomous systems in space?" define the immediate focus of my work. A broader question also continues to shape my thinking: "When does consciousness emerge from AI's perceptual abilities?"

Through interdisciplinary research and collaboration, I seek to develop AI systems that are safe, secure, interpretable, and beneficial as their capabilities increase. These systems are intended not only for current missions, but also as foundations for a future in which increasingly autonomous intelligence can operate responsibly alongside humanity, including far beyond Earth.

This endeavour continues the challenge articulated by Alan Turing in 1947: "a machine that can learn from experience." It also advances the foundational pursuit defined in the 1955 Dartmouth proposal as "the science and engineering of making intelligent machines," now applied to the critical challenge of building safe, secure, and trustworthy intelligence for humanity's expansion beyond Earth.

The mission is just beginning.