Influence diagrams for the optimization of a vehicle speed profile

TL;DR

This paper demonstrates how influence diagrams can optimize vehicle speed profiles, achieving results comparable to expert test pilots, and explores their potential for complex automotive decision-making.

Contribution

It introduces the application of influence diagrams to vehicle speed profile optimization and presents experimental results validating their effectiveness.

Findings

Optimized lap times closely match test pilot results.

Influence diagrams effectively model complex vehicle decision processes.

Extended models are being tested in real-world automotive scenarios.

Abstract

Influence diagrams are decision theoretic extensions of Bayesian networks. They are applied to diverse decision problems. In this paper we apply influence diagrams to the optimization of a vehicle speed profile. We present results of computational experiments in which an influence diagram was used to optimize the speed profile of a Formula 1 race car at the Silverstone F1 circuit. The computed lap time and speed profiles correspond well to those achieved by test pilots. An extended version of our model that considers a more complex optimization function and diverse traffic constraints is currently being tested onboard a testing car by a major car manufacturer. This paper opens doors for new applications of influence diagrams.