Certified policy synthesis for adaptive CPS/IoT automotive

Posted on

< Project Overview >

Cyber-Physical Systems (CPS) and Internet of Things (IoT) are complex engineering systems encompassing analogue/physical quantities with digital/discrete controllers. Modern CPS and IoT systems utilise learning components which gather data from sensors. These sensors process data through internal functions, then output signals accordingly. This is known as black-box technology.

This project will develop solutions for practical verification issues for complex CPS/IoT systems in the automotive domain, which include black-box learning/adaptive components. The presence of these components renders verification tasks particularly tricky: the certification of black-box components is a core, unmet challenge for safety-critical applications. The focus of the project is on breaking this barrier and on transferring technology via industrial demonstrations.

This project will transfer knowledge from previous research, on new results for certified synthesis of CPS/IoT with adaptive components, to scenarios and demonstrations that are relevant to the cut-edge automotive industry.

In collaboration with ZF [4], a Tier 1 automotive supplier, we will examine issues from use cases around advanced driver assistance systems (ADAS). The automotive industry has a clear need to develop new solutions to the problem of certified learning for autonomous systems in safety-critical environments. We will in particular focus on adaptive cruise control (ACC) scenarios, encompassing various levels of autonomy (ZF is interested in targeting deployment of level-4 solutions within the next few years). We will synthesise certified policies via RL around specific ACC goals, such as platooning or autonomous lane changing/merging. We will leverage ZF simulation software for the above scenarios, and later use a proprietary hardware-in-the-loop implementation. Deployment of the solution in demonstrations will include elements of perception and data fusion, for instance through specific sensors or computational vision components.

Project Lead

Prof Alessandro Abate – University of Oxford