Towards fully autonomous drone tracking by a reinforcement learning agent controlling a pan–tilt–zoom camera

Simple item page
dc.contributor.authorWisniewski, Mariusz
dc.contributor.authorRana, Zeeshan A.
dc.contributor.authorPetrunin, Ivan
dc.contributor.authorHolt, Alan
dc.contributor.authorHarman, Stephen
dc.date.accessioned2024-06-10T10:42:37Z
dc.date.available2024-06-10T10:42:37Z
dc.date.issued2024-05-30
dc.description.abstractPan–tilt–zoom cameras are commonly used for surveillance applications. Their automation could reduce the workload of human operators and increase the safety of airports by tracking anomalous objects such as drones. Reinforcement learning is an artificial intelligence method that outperforms humans on certain specific tasks. However, there exists a lack of data and benchmarks for pan–tilt–zoom control mechanisms in tracking airborne objects. Here, we show a simulated environment that contains a pan–tilt–zoom camera being used to train and evaluate a reinforcement learning agent. We found that the agent can learn to track the drone in our basic tracking scenario, outperforming a solved scenario benchmark value. The agent is also tested on more complex scenarios, where the drone is occluded behind obstacles. While the agent does not quantitatively outperform the optimal human model, it shows qualitative signs of learning to solve the complex, occluded non-linear trajectory scenario. Given further training, investigation, and different algorithms, we believe a reinforcement learning agent could be used to solve such scenarios consistently. Our results demonstrate how complex drone surveillance tracking scenarios may be solved and fully autonomized by reinforcement learning agents. We hope our environment becomes a starting point for more sophisticated autonomy in control of pan–tilt–zoom cameras tracking of drones and surveilling airspace for anomalous objects. For example, distributed, multi-agent systems of pan–tilt–zoom cameras combined with other sensors could lead towards fully autonomous surveillance, challenging experienced human operators.en_UK
dc.description.sponsorshipThis project was funded through the UK Government’s Industrial PhD Partnership (IPPs) Scheme by the Future Aviation Security Solutions Programme (FASS)—a joint Department for Transport and Home Office venture, in collaboration with Aveillant Ltd. and Autonomous Devices Ltd.en_UK
dc.identifier.citationWisniewski M, Rana ZA, Petrunin I, et al., (2024) Towards fully autonomous drone tracking by a reinforcement learning agent controlling a pan–tilt–zoom camera. Drones, Volume 8, Issue 6, May 2024, Article number 235en_UK
dc.identifier.eissn2504-446X
dc.identifier.urihttps://doi.org/10.3390/drones8060235
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/22356
dc.language.isoen_UKen_UK
dc.publisherMDPIen_UK
dc.rightsAttribution 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.subjectdrone detectionen_UK
dc.subjectdrone trackingen_UK
dc.subjectpan–tilt–zoomen_UK
dc.subjectreinforcement learningen_UK
dc.subjectdeep learningen_UK
dc.subjectmachine learningen_UK
dc.subjectdrone surveillanceen_UK
dc.subjectunmanned aerial vehiclesen_UK
dc.subjectairport securityen_UK
dc.subjectartificial intelligenceen_UK
dc.titleTowards fully autonomous drone tracking by a reinforcement learning agent controlling a pan–tilt–zoom cameraen_UK
dc.typeArticleen_UK
dcterms.dateAccepted2024-05-24

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Towards_fully_autonomous_drone_tracking-2024.pdf
Size:
6.17 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)