Adaptive Sampling of Ocean Processes Using an AUV with a Gaussian Proxy Model

Berget, Gunhild Elisabeth; Fossum, Trygve Olav; Johansen, Tor Arne; Eidsvik, Jo; Rajan, Kanna

doi:10.1016/j.ifacol.2018.09.509

Cited by 16 publications

(13 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method is most commonly used in geostatistics which deals with modeling the spatial aspects of the world. GP has found a huge acceptance in various fields like oceanography, finance and physics [281][282][283][284][285]. With the increasing complexity of the datasets, simple parametric approaches tend to lack in accuracy and effectiveness.…”

Section: Gaussian Process (Gp) and Krigingmentioning

confidence: 99%

Advances in Computational Intelligence of Polymer Composite Materials: Machine Learning Assisted Modeling, Analysis and Design

Sharma

Mukhopadhyay

Rangappa

et al. 2022

Arch Computat Methods Eng

107

View full text Add to dashboard Cite

The superior multi-functional properties of polymer composites have made them an ideal choice for aerospace, automobile, marine, civil, and many other technologically demanding industries. The increasing demand of these composites calls for an extensive investigation of their physical, chemical and mechanical behavior under different exposure conditions. Machine learning (ML) has been recognized as a powerful predictive tool for data-driven multi-physical modeling, leading to unprecedented insights and exploration of the system properties beyond the capability of traditional computational and experimental analyses. Here we aim to abridge the findings of the large volume of relevant literature and highlight the broad spectrum potential of ML in applications like prediction, optimization, feature identification, uncertainty quantification, reliability and sensitivity analysis along with the framework of different ML algorithms concerning polymer composites. Challenges like the curse of dimensionality, overfitting, noise and mixed variable problems are discussed, including the latest advancements in ML that have the potential to be integrated in the field of polymer composites.Based on the extensive literature survey, a few recommendations on the exploitation of various ML algorithms for addressing different critical problems concerning polymer composites are provided along with insightful perspectives on the potential directions of future research.

show abstract

Section: Gaussian Process (Gp) and Krigingmentioning

confidence: 99%

Advances in Computational Intelligence of Polymer Composite Materials: Machine Learning Assisted Modeling, Analysis and Design

Sharma

Mukhopadhyay

Rangappa

et al. 2022

Arch Computat Methods Eng

107

View full text Add to dashboard Cite

show abstract

“…Suryan and Tokekar [44] develop a fast GP regression informative path planning algorithm over spatial fields. Berget et al [45], Fossum and Eidvsik et al [46], and Fossum and Fragoso et al [10] implement GP regression on AUVs and demonstrate the viability of simple IPP algorithms in realworld scenarios. Flaspohler et al [47] introduce a plumefinding algorithm, which locates maxima of phenomena modeled by GPs.…”

Section: Related Workmentioning

confidence: 99%

Gaussian-Dirichlet Random Fields for Inference over High Dimensional Categorical Observations

Soucie

Sosik

Girdhar

2020

2020 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

We propose a generative model for the spatiotemporal distribution of high dimensional categorical observations. These are commonly produced by robots equipped with an imaging sensor such as a camera, paired with an image classifier, potentially producing observations over thousands of categories. The proposed approach combines the use of Dirichlet distributions to model sparse co-occurrence relations between the observed categories using a latent variable, and Gaussian processes to model the latent variable's spatiotemporal distribution. Experiments in this paper show that the resulting model is able to efficiently and accurately approximate the temporal distribution of high dimensional categorical measurements such as taxonomic observations of microscopic organisms in the ocean, even in unobserved (held out) locations, far from other samples. This work's primary motivation is to enable deployment of informative path planning techniques over high dimensional categorical fields, which until now have been limited to scalar or low dimensional vector observations.

show abstract

“…Moreover, the position and shape of the elliptic ice ridges, as well as the altitude, are assumed fully observable. The hyperparameters for the squared-exponential ARD kernel were learned by optimizing the marginal likelihood as shown in (4)…”

Section: Simulation Setupmentioning

confidence: 99%

“…[2] use a chance-constrained Markov decision process formulation for calculating an optimal trajectory for maximizing predictions from a GP for AUVs. [3] and [4] use a GP discretized on a grid for adaptive sampling for AUVs, using a greedy approach for choosing which grid point to sample next.…”

Section: Introductionmentioning

confidence: 99%

Optimization-based planning and control of AUVs applied to adaptive sampling under ice

Bremnes

Devonport

Yin

et al. 2020

2020 IEEE/OES Autonomous Underwater Vehicles Symposium (AUV)(50043)

View full text Add to dashboard Cite

This paper presents a framework for optimization-based informative planning and control with applications to adaptive sampling with AUVs under sea ice. A spatial model of the information of interest is approximated as a Gaussian process (GP), which is learned online from in-situ sensor data. The planner uses a two-layer model predictive control (MPC) scheme on a low-fidelity model of the vehicle for exploration and exploitation of the GP, subject to safety constraints. The planner trajectories are then tracked using a constant bearing based guidance law, aligning the desired orientation of the AUV toward the planned trajectory. The proposed framework enables the vehicle to plan and replan its mission as new data is obtained, while ensuring tracking of the planned trajectories and safety constraint satisfaction. Simulation results of a case study are presented for demonstrating the performance of the proposed method. An AUV is tasked with finding and tracking concentrations of marine biomass in 3D under sea ice while avoiding collisions.

show abstract

Adaptive Sampling of Ocean Processes Using an AUV with a Gaussian Proxy Model

Cited by 16 publications

References 10 publications

Advances in Computational Intelligence of Polymer Composite Materials: Machine Learning Assisted Modeling, Analysis and Design

Advances in Computational Intelligence of Polymer Composite Materials: Machine Learning Assisted Modeling, Analysis and Design

Gaussian-Dirichlet Random Fields for Inference over High Dimensional Categorical Observations

Optimization-based planning and control of AUVs applied to adaptive sampling under ice

Contact Info

Product

Resources

About