An AI solution which attempts to show regulators and others how autonomous vehicles (AVs) make the decisions they do on the road has been developed by a Samsung-owned spin-off from one of the UK’s top universities and a software firm.
Oxford Semantic Technologies (OST) grew out of the University of Oxford’s computer science department, and was acquired by Samsung in 2024.
It has teamed up with Ignite by Forvia Hella – the software venture of automotive supplier Forvia Hella – which was founded in 2024 and is headquartered in Berlin.
They believe that AV manufacturers at present struggle to move from Level 2 (partial driving automation where the driver is legally responsible) to Level 3 (conditional driving automation where the manufacturer assumes liability) and Level 4 (fully-autonomous driving).
However, the partners think that knowledge-based AI using expert knowledge and logical reasoning to solve complex problems can be applied to AVs.
This is different to machine learning, which uses vast datasets to find patterns, rather than making logical and explainable decisions based on data combined with expert knowledge, the firms suggest.
Their simulation-based software was built using OST’s RDFox, which they say delivers more accurate and reliable results than a large language model (LLM).
Instead, the solution can capture what AVs do in real time, cross-reference it against traffic rules, “ensuring every decision it makes is logical, traceable and compliant”, the companies say.
This should reduce development lead times, helping AV teams move faster toward approval.
“Hella Ignite.Drive applies knowledge-based AI by translating traffic laws, originally written for human interpretation, into machine-readable rule sets,” explains Dr Felix Kortmann, CTO of Ignite by Forvia Hella.
“This enables manufacturers to generate deterministic evidence that demonstrates safe and compliant vehicle behaviour for European type approval.”
OST CEO Peter Crocker adds: “AVs currently use AI to make a whole range of decisions on the road – but at the moment manufacturers are struggling to show why or how these decisions are made.”
“RDFox can help with this major barrier to progress.”
“What knowledge-based AI allows us to do is to collect and map these decisions and apply reasoning. We can see exactly why a vehicle acts in a certain way and use this data to help the vehicle make better decisions in the future.”
Dr Ian Horrocks, Oxford University professor and OST co-founder adds: “A key advantage of the technology is traceability, where decisions can be linked back to the rules and logic that produced them.”
OST says RDFox is already deployed within tens of millions of Samsung’s smartphones worldwide.