Abstract
Adaptive sampling is important in robotic environmental monitoring, allowing a robot to intelligently select sampling locations to build an informative model of a phenomenon of interest. Most adaptive sampling techniques assume the localization noise does not vary with location, or that this variation is negligible, and thus do not model this behavior. In practice, the noise will vary greatly depending on the robot’s trajectory and location. Additionally, prior surveys collected by other means, e.g., satellite or drone imagery, may use different state estimators or parameters. If these are used to drive sampling, this dependence may be significant. We provide a unified framework for adaptively collecting and modeling samples when heteroskedastic noise is present. Our framework is agnostic to the distribution of the noise. Our method outperforms others which do not take into account localization noise, validated by simulated trials and noise from a real state estimator.
This work was supported by the Southern California Coastal Water Research Project Authority under prime funding from the California State Water Resources Control Board on agreement number 19-003-150.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hwang, J., Bose, N., Fan, S.: AUV adaptive sampling methods: a review. Appl. Sci. 9, 3145 (2019)
Popovic, M., Vidal-Calleja, T.A., Chung, J.J., Nieto, J., Siegwart, R.: Informative path planning for active mapping under localization uncertainty. In: Robotics & Automation Letters (2019)
Hollinger, G.A., Sukhatme, G.S.: Sampling-based robotic information gathering algorithms. IJRR 33(9), 1271–1287 (2014)
Manderson, T., Manjanna, S., Dudek, G.: Heterogeneous Robot Teams for Informative Sampling. Workshop on Informative Path Planning and Adaptive Sampling at Robotics Science and Systems, June (2019)
Oliveira, R., Ott, L., Ramos, F.: Bayesian Optimisation Under Uncertain Inputs. In: 2nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019)], February 2019
Girard, A., Rasmussen, C.E., Candela, J.Q., Murray-Smith, R.: Gaussian process priors with uncertain inputs application to multiple-step ahead time series forecasting. In: Advances in Neural Information Processing Systems, vol. 15, pp. 545–552, MIT Press (2003)
Xu, N., Low, K.H., Chen, J., Lim, K.K., Ozgul, E.B.: GP-Localize: Persistent Mobile Robot Localization using Online Sparse Gaussian Process Observation Model. arXiv:1404.5165 [cs, stat], April 2014
Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. MIT press, Cambridge (2006). ISSN: 0129-0657
Guestrin, C., Krause, A., Singh, A.P.: Near-optimal sensor placements in gaussian processes. In: Proceedings of the 22Nd International Conference on Machine Learning, ICML 2005, New York, NY, USA, pp. 265–272. ACM (2005)
Forster, C., Carlone, L., Dellaert, F., Scaramuzza, D.: IMU Preintegration on Manifold for Efficient Visual-Inertial Maximum-a-Posteriori Estimation. in Robotics: Science and Systems (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Denniston, C.E., Kumaraguru, A., Caron, D.A., Sukhatme, G.S. (2021). Incorporating Noise into Adaptive Sampling. In: Siciliano, B., Laschi, C., Khatib, O. (eds) Experimental Robotics. ISER 2020. Springer Proceedings in Advanced Robotics, vol 19. Springer, Cham. https://doi.org/10.1007/978-3-030-71151-1_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-71151-1_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-71150-4
Online ISBN: 978-3-030-71151-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)