An official website of the United States government
This paper investigates the problem of informative path planning for a mobile robotic sensor network in spatially temporally distributed mapping. The robots are able to gather noisy measurements from an area of interest during their movements to build a Gaussian process (GP) model of a spatio-temporal field. The model is then utilized to predict the spatio-temporal phenomenon at different points of interest. To spatially and temporally navigate the group of robots so that they can optimally acquire maximal information gains while their connectivity is preserved, we propose a novel multi-step prediction informative path planning optimization strategy employing our newly defined local cost functions. By using the dual decomposition method, it is feasible and practical to effectively solve the optimization problem in a distributed manner. The proposed method was validated through synthetic experiments utilizing real-world data sets.
more »
« less
Adaptive sampling with an autonomous underwater vehicle in static marine environments
Abstract This paper explores the use of autonomous underwater vehicles (AUVs) equipped with sensors to construct water quality models to aid in the assessment of important environmental hazards, for instance related to point‐source pollutants or localized hypoxic regions. Our focus is on problems requiring the autonomous discovery and dense sampling of critical areas of interest in real‐time, for which standard (e.g., grid‐based) strategies are not practical due to AUV power and computing constraints that limit mission duration. To this end, we consider adaptive sampling strategies on Gaussian process (GP) stochastic models of the measured scalar field to focus sampling on the most promising and informative regions. Specifically, this study employs the GP upper confidence bound as the optimization criteria to adaptively plan sampling paths that balance a trade‐off between exploration and exploitation. Two informative path planning algorithms based on (i) branch‐and‐bound techniques and (ii) cross‐entropy optimization are presented for choosing future sampling locations while considering the motion constraints of the sampling platform. The effectiveness of the proposed methods are explored in simulated scalar fields for identifying multiple regions of interest within a three‐dimensional environment. Field experiments with an AUV using both virtual measurements on a known scalar field and in situ dissolved oxygen measurements for studying hypoxic zones validate the approach's capability to quickly explore the given area, and then subsequently increase the sampling density around regions of interest without sacrificing model fidelity of the full sampling area.
more »
« less
- Award ID(s):
- 1931821
- PAR ID:
- 10231541
- Publisher / Repository:
- Wiley Blackwell (John Wiley & Sons)
- Date Published:
- Journal Name:
- Journal of Field Robotics
- Volume:
- 38
- Issue:
- 4
- ISSN:
- 1556-4959
- Page Range / eLocation ID:
- p. 572-597
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This work studies online learning-based trajectory planning for multiple autonomous underwater vehicles (AUVs) to estimate a water parameter field of interest in the under-ice environment. A centralized system is considered, where several fixed access points on the ice layer are introduced as gateways for communications between the AUVs and a remote data fusion center. We model the water parameter field of interest as a Gaussian process with unknown hyper-parameters. The AUV trajectories for sampling are determined on an epoch-by-epoch basis. At the end of each epoch, the access points relay the observed field samples from all the AUVs to the fusion center, which computes the posterior distribution of the field based on the Gaussian process regression and estimates the field hyper-parameters. The optimal trajectories of all the AUVs in the next epoch are determined to maximize a long-term reward that is defined based on the field uncertainty reduction and the AUV mobility cost, subject to the kinematics constraint, the communication constraint and the sensing area constraint. We formulate the adaptive trajectory planning problem as a Markov decision process (MDP). A reinforcement learning-based online learning algorithm is designed to determine the optimal AUV trajectories in a constrained continuous space. Simulation results show that the proposed learning-based trajectory planning algorithm has performance similar to a benchmark method that assumes perfect knowledge of the field hyper-parameters.more » « less
-
Abstract Environmental sensors are crucial for monitoring weather conditions and the impacts of climate change. However, it is challenging to place sensors in a way that maximises the informativeness of their measurements, particularly in remote regions like Antarctica. Probabilistic machine learning models can suggest informative sensor placements by finding sites that maximally reduce prediction uncertainty. Gaussian process (GP) models are widely used for this purpose, but they struggle with capturing complex non-stationary behaviour and scaling to large datasets. This paper proposes using a convolutional Gaussian neural process (ConvGNP) to address these issues. A ConvGNP uses neural networks to parameterise a joint Gaussian distribution at arbitrary target locations, enabling flexibility and scalability. Using simulated surface air temperature anomaly over Antarctica as training data, the ConvGNP learns spatial and seasonal non-stationarities, outperforming a non-stationary GP baseline. In a simulated sensor placement experiment, the ConvGNP better predicts the performance boost obtained from new observations than GP baselines, leading to more informative sensor placements. We contrast our approach with physics-based sensor placement methods and propose future steps towards an operational sensor placement recommendation system. Our work could help to realise environmental digital twins that actively direct measurement sampling to improve the digital representation of reality.more » « less
-
The process of seeking, sampling, and characterizing deep hydrothermal systems is benefited by the use of autonomous underwater vehicles (AUVs) equipped with in situ sensors. Traditional AUV operations require multiple deployments with manual data analysis by ship-board scientists. Development of advanced autonomous methods that analyze in situ data in real-time and allow the vehicle itself to make decisions would improve the efficiency of operations and enable new frontiers in exploration at hydrothermal systems on Ocean Worlds. Adaptive robotic decision making is facilitated by computational models of hydrothermal systems and selected in situ sensors used to refine and validate these predictions. Improving autonomous missions requires better models, and thus an understanding of how different sensors respond to hydrothermally altered seawater. During cruise AT50-15 (Juan De Fuca Ridge, 2023), we performed surveys of the hydrothermal plumes at the Endeavour Segment with AUV Sentry to investigate the utility of in situ sensors measuring tracers such as oxidation-reduction potential, optical backscatter, methane abundance, conductivity, and temperature, for building working models of plume dynamics. We investigated length scales of under 1 km to 5 km with a focus on reoccupying locations over varying time scales. Persistent deep current data were available through the Ocean Networks Canada mooring array. Using these datasets, we investigate two questions: (1) how reliably and at what length scales can real-time current information be used to predict the location and source of a hydrothermal plume? (2) How does the relative age (hence, biogeochemical maturation) of the hydrothermal plume fluid affect the response of different in situ sensors? These results will be used to inform the development of autonomous plume detection algorithms that use real-time, in situ data with the purpose of improving AUV exploration of hydrothermal plumes on Earth and other Ocean Worlds.more » « less
-
In an application involving Autonomous Underwater Vehicles (AUV) it is important to track the trajectory and spatially correlate the collected data. Relying on an Inertial Navigation System (INS) while factoring in the initial AUV position would not suffice given the major accumulated errors. Employing surface nodes is a logistically complicated option, especially for missions involving emerging events. This paper proposes a novel localization approach that offers both agility and accuracy. The idea is to exploit a communication mechanism across the air-water interface. In particular, we employ an airborne unit, e.g., a drone, that scans the area of interest and uses visual light communication (VLC) to reach the AUV. In essence, the airborne unit defines virtual anchors with known GPS coordinates. The AUV uses the light intensity of the received VLC transmissions to estimate the range relative to the anchor points and then determine its own global coordinates at various time instances. The proposed approach is validated through extensive simulation experiments. The simulation results demonstrate the viability of our approach and analyze the effect of the VLC parameters.more » « less
