Decentralized learning-based planning for multiagent missions in the presence of actuator failures

N. Kemal Ure, Girish Chowdhary, Yu Fan Chen, Mark Cutler, Jonathan P. How, John Vian

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We consider the problem of high-level learning and decision making to enable multi-agent teams to autonomously tackle complex, large-scale missions, over long time periods in the presence of actuator failures. Agent health, measured by the functionality of its subsystems such as actuators, can change over time in long-duration missions and may depend on environmental states. This variability in agent health leads to uncertainty that can lead to inefficient plans, and in some cases even mission failure. The joint learning-planing problem becomes particularly challenging in a heterogeneous team where each agent may have a different correlation between their individual states and the state of the environment. We present a learning based planning framework for heterogeneous multiagent missions with health uncertainty that uses online learned probabilistic models of agent health. A decentralized incremental Feature Dependency Discovery algorithm is developed to enable agents to collaborate to efficiently learn representations of the uncertainty models across heterogeneous agents. The learned models of actuator failures allow our approach to plan in anticipation of potential health degradation. We show through large-scale planning under uncertainty simulations and flight experiments with state-dependent actuator and fuel-burn-rate uncertainty that our planning approach can outperform planners that do not account for heterogeneity between agents.

Original languageEnglish (US)
Title of host publication2013 International Conference on Unmanned Aircraft Systems, ICUAS 2013 - Conference Proceedings
Pages1125-1134
Number of pages10
DOIs
StatePublished - 2013
Externally publishedYes
Event2013 International Conference on Unmanned Aircraft Systems, ICUAS 2013 - Atlanta, GA, United States
Duration: May 28 2013May 28 2013

Publication series

Name2013 International Conference on Unmanned Aircraft Systems, ICUAS 2013 - Conference Proceedings

Other

Other2013 International Conference on Unmanned Aircraft Systems, ICUAS 2013
CountryUnited States
CityAtlanta, GA
Period5/28/135/28/13

ASJC Scopus subject areas

  • Aerospace Engineering

Fingerprint Dive into the research topics of 'Decentralized learning-based planning for multiagent missions in the presence of actuator failures'. Together they form a unique fingerprint.

Cite this