Adaptive sampling with an autonomous underwater vehicle in static marine environments

Stankiewicz, Paul G.; Tan, Yew Teck; Kobilarov, Marin

doi:10.1002/rob.22005

Cited by 29 publications

(16 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gaussian process (GP) regression has been widely used in spatial statistics (Cressie, 1993;Rasmussen and Williams, 2006), adaptive sampling (Krause et al, 2008), and autonomous robotic exploration (Thompson, 2008;Kumar et al, 2019). However, most work regarding GPs (especially for AUVs) involves mapping scalar fields such as salinity, temperature, altimetry, or dissolved oxygen measurements (Binney et al, 2010;Flaspohler et al, 2019;Stankiewicz et al, 2021). In contrast, our goal is to learn and map non-scalar data, i.e., high-resolution spectra.…”

Section: Problem Formulationmentioning

confidence: 99%

“…Gaussian process are typically used for mapping scalar values, for example ocean temperature, salinity, altimetry, or dissolved oxygen measurements (Binney et al, 2010;Flaspohler et al, 2019;Stankiewicz et al, 2021). However, our coral reef mapping problem involves multivariate data (i.e., high-resolution spectra).…”

Section: Spatial Regression Of Spectral Featuresmentioning

confidence: 99%

“…Specifically, samples that refine the accuracy and resolution of global remote sensing by adapting to the current state of knowledge of the environment. Currently most works regarding adaptive sampling for marine surveys fail to exploit the power of remote sensing; consequently, they only map simple quantities such as salinity, temperature, altimetry, or dissolved oxygen measurements (Binney et al, 2010;Flaspohler et al, 2019;Stankiewicz et al, 2021). Rao et al (2017) use a deep learning architecture that does not allow for adaptive sampling.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Using Remote Sensing and in situ Measurements for Efficient Mapping and Optimal Sampling of Coral Reefs

et al. 2021

View full text Add to dashboard Cite

Coral reefs are of undeniable importance to the environment, yet little is known of them on a global scale. Assessments rely on laborious, local in-water surveys. In recent years remote sensing has been useful on larger scales for certain aspects of reef science such as benthic functional type discrimination. However, remote sensing only gives indirect information about reef condition. Only through combination of remote sensing and in situ data can we achieve coverage to understand reef condition and monitor worldwide condition. This work presents an approach to global mapping of coral reef condition that intelligently selects local, in situ measurements that refine the accuracy and resolution of global remote sensing. To this end, we apply new techniques in remote sensing analysis, probabilistic modeling for coral reef mapping, and decision theory for sample selection. Our strategy represents a fundamental change in how we study coral reefs and assess their condition on a global scale. We demonstrate feasibility and performance of our approach in a proof of concept using spaceborne remote sensing together with high-quality airborne data from the NASA Earth Venture Suborbital-2 (EVS-2) Coral Reef Airborne Laboratory (CORAL) mission as a proxy for in situ samples. Results indicate that our method is capable of extrapolating in situ features and refining information from remote sensing with increasing accuracy. Furthermore, the results confirm that decision theory is a powerful tool for sample selection.

show abstract

Section: Problem Formulationmentioning

confidence: 99%

Section: Spatial Regression Of Spectral Featuresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Using Remote Sensing and in situ Measurements for Efficient Mapping and Optimal Sampling of Coral Reefs

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The literature is scarce in terms of adaptive replanning methods. Whilst the usual [31], [14] is to provide a linear execution pipeline where the vehicle is stopped for mapping and planning, some authors propose to perform the process of environmental modeling in parallel to the planning process [43], and even start planning in a further location of the current mission path to avoid stopping the vehicle [25]. Furthermore, most relevant strategies, either sampling-based [31] or evolutionary-based [25] do not transfer planning knowledge between consecutive planning iterations.…”

Section: B Related Workmentioning

confidence: 99%

Adaptive Visual Information Gathering for Autonomous Exploration of Underwater Environments

2021

View full text Add to dashboard Cite

This work presents the development and field testing of a novel adaptive visual information gathering (AVIG) framework for autonomous exploration of benthic environments using AUVs. The objective is to adapt dynamically the robot exploration using the visual information gathered online. This framework is based on a novel decision-time adaptive replanning (DAR) behavior that works together with a sparse Gaussian process (SGP) for environmental modeling and a Convolutional Neural Network (CNN) for semantic image segmentation. The framework is executed in mission time. The SGP uses semantic data obtained from stereo images to probabilistically model the spatial distribution of certain species of seagrass that colonize the sea bottom forming widespread meadows. The uncertainty of the probabilistic model provides a measure of sampling informativeness to the DAR behavior. The DAR behavior has been designed to execute successive informative paths, without stopping, considering the newest information obtained from the SGP. We solve the information path planning (IPP) problem by means of a novel depthfirst (DF) version of the Monte Carlo tree search (MCTS). The DF-MCTS method has been designed to explore the state-space in a depth-first fashion, provide solution paths of a given length in an anytime manner, and reward smooth paths for field realization with non-holonomic robots. The complete framework has been integrated in a ROS environment as a high level layer of the AUV software architecture. A set of simulations and field testing show the effectiveness of the framework to gather data in P. oceanica environments.

show abstract

“…The fact that plankton imagery is usually analyzed after the cruise due to the large quantity of data, precludes it from being used for adaptive sampling, which by definition needs near-immediate data availability. With advancements in ocean technology, thanks to the increased affordability and availability of advanced hard-, and software, the number of studies working on real-time identification and adaptive sampling based on different underwater vehicles has increased though in recent years (Fossum et al, 2019;Ohman et al, 2019;Stankiewicz et al, 2021;Bi et al, 2022). However, having the necessary computing power at sea to classify large quantities of videography remains a bottleneck.…”

Section: Introductionmentioning

confidence: 99%

Edge computing at sea: high-throughput classification of in-situ plankton imagery for adaptive sampling

Schmid,

Daprano,

Damle

et al. 2023

Front. Mar. Sci.

View full text Add to dashboard Cite

The small sizes of most marine plankton necessitate that plankton sampling occur on fine spatial scales, yet our questions often span large spatial areas. Underwater imaging can provide a solution to this sampling conundrum but collects large quantities of data that require an automated approach to image analysis. Machine learning for plankton classification, and high-performance computing (HPC) infrastructure, are critical to rapid image processing; however, these assets, especially HPC infrastructure, are only available post-cruise leading to an ‘after-the-fact’ view of plankton community structure. To be responsive to the often-ephemeral nature of oceanographic features and species assemblages in highly dynamic current systems, real-time data are key for adaptive oceanographic sampling. Here we used the new In-situ Ichthyoplankton Imaging System-3 (ISIIS-3) in the Northern California Current (NCC) in conjunction with an edge server to classify imaged plankton in real-time into 170 classes. This capability together with data visualization in a heavy.ai dashboard makes adaptive real-time decision-making and sampling at sea possible. Dual ISIIS-Deep-focus Particle Imager (DPI) cameras sample 180 L s-1, leading to >10 GB of video per min. Imaged organisms are in the size range of 250 µm to 15 cm and include abundant crustaceans, fragile taxa (e.g., hydromedusae, salps), faster swimmers (e.g., krill), and rarer taxa (e.g., larval fishes). A deep learning pipeline deployed on the edge server used multithreaded CPU-based segmentation and GPU-based classification to process the imagery. AVI videos contain 50 sec of data and can contain between 23,000 - 225,000 particle and plankton segments. Processing one AVI through segmentation and classification takes on average 3.75 mins, depending on biological productivity. A heavyDB database monitors for newly processed data and is linked to a heavy.ai dashboard for interactive data visualization. We describe several examples where imaging, AI, and data visualization enable adaptive sampling that can have a transformative effect on oceanography. We envision AI-enabled adaptive sampling to have a high impact on our ability to resolve biological responses to important oceanographic features in the NCC, such as oxygen minimum zones, or harmful algal bloom thin layers, which affect the health of the ecosystem, fisheries, and local communities.

show abstract

Adaptive sampling with an autonomous underwater vehicle in static marine environments

Cited by 29 publications

References 50 publications

Using Remote Sensing and in situ Measurements for Efficient Mapping and Optimal Sampling of Coral Reefs

Using Remote Sensing and in situ Measurements for Efficient Mapping and Optimal Sampling of Coral Reefs

Adaptive Visual Information Gathering for Autonomous Exploration of Underwater Environments

Edge computing at sea: high-throughput classification of in-situ plankton imagery for adaptive sampling

Contact Info

Product

Resources

About