Applications of Probabilistic Graphical Models to Diagnosis and Control of Autonomous Vehicles

Anders L. Madsen, Uffe Bro Kjærulff, Jörg Kalwa, Michel Perrier, Miguel Angel Sotelo

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearch

608 Downloads (Pure)

Abstract

We present the main elements of a distributed architecture supporting diagnosis and control of autonomous robots. The purpose of the architecture is to assist the operator or piloting system in managing fault detection, risk assessment, and recovery plans under uncertainty. The architecture is generic, open, and modular consisting of a set of interacting modules including a decision module (DM) and a set of intelligent modules (IMs). The DM communicates with the IMs to request and obtain diagnosis and recovery action proposals based on data obtained from the robot piloting module. The architecture supports the use of multiple artificial intelligence techniques collaborating on the task of handling uncertainty.
Original languageEnglish
Title of host publicationThe Second Bayesian Modeling Applications Workshop
Publication date2004
Publication statusPublished - 2004
Event20th Conference on Uncertainty in Artificial Intelligence - Banff Park Lodge, Banff, Canada
Duration: 7 Jul 200411 Jul 2004
Conference number: 20th

Conference

Conference20th Conference on Uncertainty in Artificial Intelligence
Number20th
CountryCanada
CityBanff Park Lodge, Banff
Period07/07/200411/07/2004

    Fingerprint

Cite this

Madsen, A. L., Kjærulff, U. B., Kalwa, J., Perrier, M., & Sotelo, M. A. (2004). Applications of Probabilistic Graphical Models to Diagnosis and Control of Autonomous Vehicles. In The Second Bayesian Modeling Applications Workshop