Guiding drones by information gain

Alouette van Hove, Kristoffer Aalstad, Norbert Pirk
Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL}), PMLR 233:89-96, 2024.

Abstract

The accurate estimation of locations and emission rates of gas sources is crucial across various domains, including environmental monitoring and greenhouse gas emission analysis. This study investigates two drone sampling strategies for inferring source term parameters of gas plumes from atmospheric measurements. Both strategies are guided by the goal of maximizing information gain attained from observations at sequential locations. Our research compares the myopic approach of infotaxis to a far-sighted navigation strategy trained through deep reinforcement learning. We demonstrate the superior performance of deep reinforcement learning over infotaxis in environments with non-isotropic gas plumes.

Cite this Paper

BibTeX
@InProceedings{pmlr-v233-hove24a, title = {Guiding drones by information gain}, author = {Hove, Alouette van and Aalstad, Kristoffer and Pirk, Norbert}, booktitle = {Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL})}, pages = {89--96}, year = {2024}, editor = {Lutchyn, Tetiana and Ramírez Rivera, Adín and Ricaud, Benjamin}, volume = {233}, series = {Proceedings of Machine Learning Research}, month = {09--11 Jan}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v233/hove24a/hove24a.pdf}, url = {https://proceedings.mlr.press/v233/hove24a.html}, abstract = {The accurate estimation of locations and emission rates of gas sources is crucial across various domains, including environmental monitoring and greenhouse gas emission analysis. This study investigates two drone sampling strategies for inferring source term parameters of gas plumes from atmospheric measurements. Both strategies are guided by the goal of maximizing information gain attained from observations at sequential locations. Our research compares the myopic approach of infotaxis to a far-sighted navigation strategy trained through deep reinforcement learning. We demonstrate the superior performance of deep reinforcement learning over infotaxis in environments with non-isotropic gas plumes.} }
Endnote
%0 Conference Paper %T Guiding drones by information gain %A Alouette van Hove %A Kristoffer Aalstad %A Norbert Pirk %B Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL}) %C Proceedings of Machine Learning Research %D 2024 %E Tetiana Lutchyn %E Adín Ramírez Rivera %E Benjamin Ricaud %F pmlr-v233-hove24a %I PMLR %P 89--96 %U https://proceedings.mlr.press/v233/hove24a.html %V 233 %X The accurate estimation of locations and emission rates of gas sources is crucial across various domains, including environmental monitoring and greenhouse gas emission analysis. This study investigates two drone sampling strategies for inferring source term parameters of gas plumes from atmospheric measurements. Both strategies are guided by the goal of maximizing information gain attained from observations at sequential locations. Our research compares the myopic approach of infotaxis to a far-sighted navigation strategy trained through deep reinforcement learning. We demonstrate the superior performance of deep reinforcement learning over infotaxis in environments with non-isotropic gas plumes.
APA
Hove, A.v., Aalstad, K. & Pirk, N.. (2024). Guiding drones by information gain. Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL}), in Proceedings of Machine Learning Research 233:89-96 Available from https://proceedings.mlr.press/v233/hove24a.html.

Related Material