Drone’s objective inference using policy error inverse reinforcement learning

Simple item page
dc.contributor.authorPerrusquía, Adolfo
dc.contributor.authorGuo, Weisi
dc.date.accessioned2024-01-03T15:42:41Z
dc.date.available2024-01-03T15:42:41Z
dc.date.issued2023-11-22
dc.description.abstractDrones are set to penetrate society across transport and smart living sectors. While many are amateur drones that pose no malicious intentions, some may carry deadly capability. It is crucial to infer the drone’s objective to prevent risk and guarantee safety. In this article, a policy error inverse reinforcement learning (PEIRL) algorithm is proposed to uncover the hidden objective of drones from online data trajectories obtained from cooperative sensors. A set of error-based polynomial features are used to approximate both the value and policy functions. This set of features is consistent with current onboard storage memories in flight controllers. The real objective function is inferred using an objective constraint and an integral inverse reinforcement learning (IRL) batch least-squares (LS) rule. The convergence of the proposed method is assessed using Lyapunov recursions. Simulation studies using a quadcopter model are provided to demonstrate the benefits of the proposed approach.en_UK
dc.identifier.citationPerrusquía A, Guo W. (2023) Drone’s objective inference using policy error inverse reinforcement learning. IEEE Transactions on Neural Networks and Learning Systems. Available online November 2023en_UK
dc.identifier.issn2162-237X
dc.identifier.urihttps://doi.org/10.1109/TNNLS.2023.3333551
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/20595
dc.language.isoenen_UK
dc.publisherIEEEen_UK
dc.rightsAttribution-NonCommercial 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/*
dc.subjectDronesen_UK
dc.subjectinverse reinforcement learning (IRL)en_UK
dc.subjectobjective functionen_UK
dc.subjectonline trajectoriesen_UK
dc.subjectpolicy erroren_UK
dc.subjectweight matricesen_UK
dc.titleDrone’s objective inference using policy error inverse reinforcement learningen_UK
dc.typeArticleen_UK
dcterms.dateAccepted2023-11-13

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Drones_objective_inference-2023.pdf
Size:
1.51 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)