Skip to main content
European Commission logo print header

Just-in-time Self-Verification of Autonomous Systems

Project description

Improving the development of autonomous systems

In recent years, engineers and computer scientists have been developing autonomous systems for use in a broad array of environments. They feature in self-driving cars, agricultural robots and unmanned aerial vehicles. But these systems face a serious problem in their development. The challenge for researchers is to find out how to programme them to adapt to special situations. Unfortunately, clearly defining how these systems should deal with each problem before their use is nearly impossible. The EU-funded justITSELF project will impose a paradigm shift which will shift attention away from programming predesigned responses. Instead, this new method will focus on just-in-time verification, a process by which the system will evaluate its next action constantly so as to achieve safety.


Engineers and computer scientists are currently developing autonomous systems whose entire set of behaviors in future, untested situations is unknown: How can a designer foresee all situations that an autonomous road vehicle, a robot in a human environment, an agricultural robot, or an unmanned aerial vehicle will face? Keeping in mind that all these examples are safety-critical, it is irresponsible to deploy such systems without testing all possible situations---this, however, seems impossible since even the most important possible situations are unmanageably many. I propose a paradigm shift that will make it possible to guarantee safety in unforeseeable situations: Instead of verifying the correctness of a system before deployment, I propose just-in-time verification, a new, to-be-developed verification paradigm where a system continuously checks the correctness of its next action by itself in its current environment (and only in it) in a just-in-time manner. Since future autonomous systems will have a tight interconnection of discrete computing and continuous physical elements, also known as cyber-physical systems, I will develop just-in-time verification for this system class. In order to prove correct behavior of cyber-physical systems, I will develop new formal verification techniques that efficiently compute possible future behaviors---subject to uncertain initial states, inputs, and parameters---within a small time horizon. Just-in-time verification will substantially cut development costs, increase the autonomy of systems (e.g. the range of deployment of automated driving systems), and reduce or even eliminate certain liability claims. The results will be implemented in an open-source software framework and will be primarily demonstrated for automated driving. Successful development of just-in-time verification techniques is yet more challenging than offline verification of autonomous systems, but expected to bring even greater rewards.

Host institution

Net EU contribution
€ 1 999 075,00
Arcisstrasse 21
80333 Muenchen

See on map

Bayern Oberbayern München, Kreisfreie Stadt
Activity type
Higher or Secondary Education Establishments
Total cost
€ 1 999 075,00

Beneficiaries (1)