Runtime Interchange for Adaptive Re-use of Intelligent Cyber-Physical System Controllers

Abstract

Cyber-Physical Systems (CPSs) such as those found within autonomous vehicles are increasingly adopting Artificial Neural Network (ANN)-based controllers. To ensure the safety of these controllers, there is a spate of recent activity to formally verify the ANN-based designs. There are two challenges with these approaches: (1) The verification of such systems is difficult and time consuming. (2) These verified controllers are not able to adapt to frequent requirements changes, which are typical in situations like autonomous driving. This raises the question: how can trained and verified controllers, which have gone through expensive training and verification processes, be re-used to deal with requirement changes?This paper addresses this challenge for the first time by proposing a new framework that is capable of dealing with requirement changes at runtime through a mechanism we term runtime interchange. Our approach functions via a continual exchange and selection process of multiple pre-verified controllers. It represents a key step on the way to componentoriented engineering for intelligent designs, as it preserves the behaviours of the original controllers while introducing additional functionality. To demonstrate the efficacy of our approach we utilise an existing autonomous driving case study as well as a set of smaller benchmarks. These show that introduced overheads are extremely minimal and that the approach is very scalable.

Designing Cyber-Physical Systems for Runtime Self-Adaptation: Knowing More about What We Miss ...

“…The latter efforts are justified by the growing need to autonomously detect and manage unanticipated or unknown situations and properly plan adaptation during runtime . The inclusion of learning mechanisms in self-adaptive systems improves not only their flexibility but also their reusability (Pearce et al, 2021). However, current computational learning allows self-adaptive CPSs to change their operation and/or configuration only up to specific limits or inside a goal-defined operational envelope.…”