Quantum Bayesian Networks application for automated vehicles safety

Thumbnail Image
Issue Date
Borujeni, Sima E.
Nannapaneni, Saideep

Borujeni, S. E. 2021. Quantum Bayesian Networks application for automated vehicles safety -- In Proceedings: 17th Annual Symposium on Graduate Research and Scholarly Projects. Wichita, KS: Wichita State University


Bayesian Networks (BN) are probabilistic graphical models that are widely used for uncertainty modeling, stochastic prediction and probabilistic inference. A Quantum Bayesian Network (QBN) is the quantum equivalent of Bayesian networks which utilizes the principles of quantum mechanical systems to improve the computational performance of various analyses. In this paper, we experimentally evaluate the performance of a QBN on an IBM quantum computer, "Casablanca", against a Qiskit simulator as well as the classical software, Netica. For this purpose, we consider a 4-node Bayesian network for automated vehicle safety. One of the main concerns regarding automated vehicles involves their interactions with human operated traffic, specifically how they safely merge into traffic. This Bayesian network represents the value proposition of neuro-physiological sensors and driver models, with the goal of optimizing the performance of automated vehicles under safety constraints in mixed traffic situations. We use the gate-based quantum method to construct a quantum circuit for representing this BN in Qiskit. After, we run the circuit on the Casablanca quantum back-end, a seven qubit computer with a Quantum Volume (QV) of 32. We will compare the performance of this device to the results obtained from Qiskit and Netica using the root mean square percentage error (RMSPE). This comparison will be an indication of how accurate current quantum hardware is when performing deep analysis for Bayesian networks.

Table of Content
Presented to the 17th Annual Symposium on Graduate Research and Scholarly Projects (GRASP) held online, Wichita State University, April 2, 2021.
Research completed in the Department of Industrial, Systems and Manufacturing Engineering, College of Engineering