Return to search

Exploring meaningful human control over drone swarms in forest firefighting

Objective: The challenge of keeping humans in meaningful control of highly automated systems is growing as these systems become more common in high-risk domains like aviation, the military, and emergency services. One suggested method to ensure human control and responsibility is to apply the principles of meaningful human control. This study aimed to explore the applicability of meaningful human control through a case study involving operators interacting with a prototype interface designed for controlling multiple unmanned aerial vehicles fighting forest fires.  Method: A simulated scenario was created and implemented through a prototype interface for human-swarm interaction. Empirical data included screen- and audio recordings of participants engaging with the simulated scenario through the prototype. The Joint Control Framework was used to transcribe and analyze the interaction.  Results: The results indicate that the level of meaningful human control in the interaction between the operator and the unmanned aerial vehicle system is dynamic and context-dependent. It varies based on the type of task, the operator’s level of cognitive control, the level of interaction with the swarm, and the system’s level of autonomy. It is realized through the joint actions performed by the operator and the system.  Conclusion: For meaningful human control to be applicable, it needs to be operationalized as a situated and contextual measure, rather than a binary concept. Future measures of meaningful human control, whether subjective or objective, should reflect this approach.

Identiferoai:union.ndltd.org:UPSALLA1/oai:DiVA.org:liu-205599
Date January 2024
CreatorsHolmgren, Aksel
PublisherLinköpings universitet, Interaktiva och kognitiva system
Source SetsDiVA Archive at Upsalla University
LanguageEnglish
Detected LanguageEnglish
TypeStudent thesis, info:eu-repo/semantics/bachelorThesis, text
Formatapplication/pdf
Rightsinfo:eu-repo/semantics/openAccess

Page generated in 0.0022 seconds