Environment Imitation: Data-Driven Environment Model Generation Using Imitation Learning for Efficient CPS Goal Verification

TL;DR

This paper introduces a data-driven method using Imitation Learning to automatically generate virtual environment models from limited logs, enabling efficient and low-cost CPS goal verification through simulation.

Contribution

It presents a novel approach for environment model generation from FOT logs using Imitation Learning, addressing the challenge of creating accurate virtual environments for CPS verification.

Findings

Generated environment models accurately replicate real environments

Achieved low-cost virtual environment creation from limited data

Validated approach with a case study on autonomous vehicle lane-keeping

Abstract

Cyber-Physical Systems (CPS) continuously interact with their physical environments through software controllers that observe the environments and determine actions. Engineers can verify to what extent the CPS under analysis can achieve given goals by analyzing its Field Operational Test (FOT) logs. However, it is challenging to repeat many FOTs to obtain statistically significant results due to its cost and risk in practice. To address this challenge, simulation-based verification can be a good alternative for efficient CPS goal verification, but it requires an accurate virtual environment model that can replace the real environment that interacts with the CPS in a closed loop. This paper proposes a novel data-driven approach that automatically generates the virtual environment model from a small amount of FOT logs. We formally define the environment model generation problem and solve it using Imitation Learning (IL) algorithms. In addition, we propose three specific use cases of our approach in the evolutionary CPS development. To validate our approach, we conduct a case study using a simplified autonomous vehicle with a lane-keeping system. The case study results show that our approach can generate accurate virtual environment models for CPS goal verification at a low cost through simulations.