ALARMS: Alerting and Reasoning Management System for Next Generation Aircraft Hazards

Alan Carlin, Nathan Schurr, Janusz Marecki
Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, PMLR R8:101-108, 2010.

Abstract

The Next Generation Air Transportation System will introduce new, advanced sensor technologies into the cockpit. With the introduction of such systems, the responsibilities of the pilot are ex- pected to dramatically increase. In the ALARMS (ALerting And Reasoning Management System) project for NASA, we focus on a key challenge of this environment, the quick and efficient han- dling of aircraft sensor alerts. It is infeasible to alert the pilot on the state of all subsystems at all times. Furthermore, there is uncertainty as to the true hazard state despite the evidence of the alerts, and there is uncertainty as to the effect and duration of actions taken to address these alerts. This paper reports on the first steps in the con- struction of an application designed to handle Next Generation alerts. In ALARMS, we have identified 60 different aircraft subsystems and 20 different underlying hazards. In this pa- per, we show how a Bayesian network can be used to derive the state of the underlying haz- ards, based on the sensor input. Then, we pro- pose a framework whereby an automated sys- tem can plan to address these hazards in coop- eration with the pilot, using a Time-Dependent Markov Process (TMDP). Different hazards and pilot states will call for different alerting automa- tion plans. We demonstrate this emerging ap- plication of Bayesian networks and TMDPs to cockpit automation, for a use case where a small number of hazards are present, and analyze the resulting alerting automation policies.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR8-carlin10a, title = {{ALARMS}: Alerting and Reasoning Management System for Next Generation Aircraft Hazards}, author = {Carlin, Alan and Schurr, Nathan and Marecki, Janusz}, booktitle = {Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence}, pages = {101--108}, year = {2010}, editor = {Grünwald, Peter and Spirtes, Peter}, volume = {R8}, series = {Proceedings of Machine Learning Research}, month = {08--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r8/main/assets/carlin10a/carlin10a.pdf}, url = {https://proceedings.mlr.press/r8/carlin10a.html}, abstract = {The Next Generation Air Transportation System will introduce new, advanced sensor technologies into the cockpit. With the introduction of such systems, the responsibilities of the pilot are ex- pected to dramatically increase. In the ALARMS (ALerting And Reasoning Management System) project for NASA, we focus on a key challenge of this environment, the quick and efficient han- dling of aircraft sensor alerts. It is infeasible to alert the pilot on the state of all subsystems at all times. Furthermore, there is uncertainty as to the true hazard state despite the evidence of the alerts, and there is uncertainty as to the effect and duration of actions taken to address these alerts. This paper reports on the first steps in the con- struction of an application designed to handle Next Generation alerts. In ALARMS, we have identified 60 different aircraft subsystems and 20 different underlying hazards. In this pa- per, we show how a Bayesian network can be used to derive the state of the underlying haz- ards, based on the sensor input. Then, we pro- pose a framework whereby an automated sys- tem can plan to address these hazards in coop- eration with the pilot, using a Time-Dependent Markov Process (TMDP). Different hazards and pilot states will call for different alerting automa- tion plans. We demonstrate this emerging ap- plication of Bayesian networks and TMDPs to cockpit automation, for a use case where a small number of hazards are present, and analyze the resulting alerting automation policies.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T ALARMS: Alerting and Reasoning Management System for Next Generation Aircraft Hazards %A Alan Carlin %A Nathan Schurr %A Janusz Marecki %B Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2010 %E Peter Grünwald %E Peter Spirtes %F pmlr-vR8-carlin10a %I PMLR %P 101--108 %U https://proceedings.mlr.press/r8/carlin10a.html %V R8 %X The Next Generation Air Transportation System will introduce new, advanced sensor technologies into the cockpit. With the introduction of such systems, the responsibilities of the pilot are ex- pected to dramatically increase. In the ALARMS (ALerting And Reasoning Management System) project for NASA, we focus on a key challenge of this environment, the quick and efficient han- dling of aircraft sensor alerts. It is infeasible to alert the pilot on the state of all subsystems at all times. Furthermore, there is uncertainty as to the true hazard state despite the evidence of the alerts, and there is uncertainty as to the effect and duration of actions taken to address these alerts. This paper reports on the first steps in the con- struction of an application designed to handle Next Generation alerts. In ALARMS, we have identified 60 different aircraft subsystems and 20 different underlying hazards. In this pa- per, we show how a Bayesian network can be used to derive the state of the underlying haz- ards, based on the sensor input. Then, we pro- pose a framework whereby an automated sys- tem can plan to address these hazards in coop- eration with the pilot, using a Time-Dependent Markov Process (TMDP). Different hazards and pilot states will call for different alerting automa- tion plans. We demonstrate this emerging ap- plication of Bayesian networks and TMDPs to cockpit automation, for a use case where a small number of hazards are present, and analyze the resulting alerting automation policies. %Z Reissued by PMLR on 04 October 2026.
APA
Carlin, A., Schurr, N. & Marecki, J.. (2010). ALARMS: Alerting and Reasoning Management System for Next Generation Aircraft Hazards. Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R8:101-108 Available from https://proceedings.mlr.press/r8/carlin10a.html. Reissued by PMLR on 04 October 2026.

Related Material