检索结果-内蒙古大学图书馆

SSRN 2025年

作者： Catipovic, Luka Laney, Samuel R. Woods Hole Oceanographic Institution Woods HoleMA United States The MIT-WHOI Joint Program in Oceanography/Applied Ocean Science and Engineering Cambridge and Woods Hole MA United States City College of New York New YorkNY United States

Highlights• ML algorithms can classify water and sea ice characteristics in the coastal Arctic.• Spring freshet runoff over sea ice is optically distinct from surface melt ponds.• Time-series analyses of satellite ima... 详细信息

关键词： Sea ice

Multi-Robot Distributed Semantic Mapping in Unfamiliar Environments through Online Matching of Learned Representations

学校读者我要写书评

暂无评论

Multi-Robot Distributed Semantic Mapping in Unfamiliar Envir...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Stewart Jamieson Kaveh Fathian Kasra Khosoussi Jonathan P. How Yogesh Girdhar MIT-WHOI Joint Program in Oceanography/Applied Ocean Science and Engineering Massachusetts Institute of Technology (MIT) Woods Hole Oceanographic Institution (WHOI)

We present a solution to multi-robot distributed semantic mapping of novel and unfamiliar environments. Most state-of-the-art semantic mapping systems are based on supervised learning algorithms that cannot classify novel observations online. While unsupervised learning algorithms can invent labels for novel observations, approaches to detect when multiple robots have independently developed their own labels for the same new class are prone to erroneous or inconsistent matches. These issues worsen as the number of robots in the system increases and prevent fusing the local maps produced by each robot into a consistent global map, which is crucial for cooperative planning and joint mission summarization. Our proposed solution overcomes these obstacles by having each robot learn an unsupervised semantic scene model online and use a multiway matching algorithm to identify consistent sets of matches between learned semantic labels belonging to different robots. Compared to the state of the art, the proposed solution produces 20-60% higher quality global maps that do not degrade even as many more local maps are fused.

关键词： Conferences Semantics Supervised learning Buildings Bandwidth Path planning Classification algorithms

The Ceres Human Exploration and Transit Architecture (CHEATA): A Mission Architecture for Small Bodies Exploration 73

学校读者我要写书评

暂无评论

The Ceres Human Exploration and Transit Architecture (CHEATA...

73rd International Astronautical Congress, IAC 2022

作者： Todd, Jessica Gentgen, Chloe Porter, Allison Bellisle, Rachel Martell, Benjamin Hoffman, Jeffrey Department of Aeronautics and Astronautics Massachusetts Institute of Technology 77 Massachusetts Ave CambridgeMA02139 United States MIT-WHOI Joint Program in Oceanography/Applied Ocean Science and Engineering Woods Hole Oceanographic Institution Woods HoleMA United States Harvard-MIT Health Sciences and Technology Massachusetts Institute of Technology 77 Massachusetts Ave CambridgeMA02139 United States

The Ceres Human Exploration and Transit Architecture (CHEATA) is a conceptual mission developed to enable human exploration of Ceres and other small bodies in the asteroid belt. These small bodies present tempting targets for future human exploration, providing insight into the evolution of our solar system, potentially containing environments of interest to astrobiologists, and acting as water- and mineral-rich stepping stones for outer solar system exploration. Minimizing radiation exposure and mission duration while maximizing surface science operations on the surface of Ceres was the critical driving requirement for this design reference mission. Key elements of the design include (1) a low gravity hopping vehicle using vacuum retro-propulsion and LOX/Methane propellant, taking advantage of the low gravity environment for regional exploration and surface operations on Ceres, (2) a bimodal nuclear thermal propulsion (NTP) system that utilizes liquid hydrogen and a reusable CERMET core, and (3) an active high-temperature superconducting magnet system, complemented by a passive high-density polyethylene system, to mitigate crew exposure to galactic cosmic radiation and solar energetic particle events. A transit habitat vehicle is assembled in cislunar space and used to ferry astronauts to Ceres orbit. The study also details breakdowns of the human countermeasures employed to address the effects of microgravity and isolation. The CHEATA mission concept was initially presented at the IEEE Aerospace Conference in 2022. The mission architecture has been updated to now include the design of additional spacecraft and habitation subsystems. These include the design of an Environmental Control and Life Support System, secondary propulsion for corrections, small maneuvers, and attitude control, but also more in-depth power and thermal management systems. The propellant storage was refined with the inclusion of zero boil-off technology for the Liquid Hydrogen tanks. A detail

关键词： Liquefied gases

Distributed Certifiably Correct Range-Aided SLAM

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Thoms, Alexander Papalia, Alan Velasquez, Jared Rosen, David M. Narasimhan, Sriram Sensing and Robotics for Infrastructure Laboratory University of California Los Angeles Los Angeles United States The Massachusetts Institute of Technology The MIT-WHOI Joint Program in Oceanography/Applied Ocean Science & Engineering Woods Hole CambridgeMA United States Robust Autonomy Lab Northeastern University BostonMA United States

Reliable simultaneous localization and mapping (SLAM) algorithms are necessary for safety-critical autonomous navigation. In the communication-constrained multi-agent setting, navigation systems increasingly use point-to-point range sensors as they afford measurements with low bandwidth requirements and known data association. The state estimation problem for these systems takes the form of range-aided (RA) SLAM. However, distributed algorithms for solving the RA-SLAM problem lack formal guarantees on the quality of the returned estimate. To this end, we present the first distributed algorithm for RA-SLAM that can efficiently recover certifiably globally optimal solutions. Our algorithm, distributed certifiably correct RA-SLAM (DCORA), achieves this via the Riemannian Staircase method, where computational procedures developed for distributed certifiably correct pose graph optimization are generalized to the RA-SLAM problem. We demonstrate DCORA’s efficacy on real-world multi-agent datasets by achieving absolute trajectory errors comparable to those of a state-of-the-art centralized certifiably correct RA-SLAM algorithm. Additionally, we perform a parametric study on the structure of the RA-SLAM problem using synthetic data, revealing how common parameters affect DCORA’s performance. Copyright © 2025, The Authors. All rights reserved.

关键词： Navigation systems

Multi-robot distributed semantic mapping in unfamiliar environments through online matching of learned representations

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Jamieson, Stewart Fathian, Kaveh Khosoussi, Kasra How, Jonathan P. Girdhar, Yogesh The MIT-WHOI Joint Program in Oceanography/Applied Ocean Science and Engineering United States United States United States

关键词： Industrial robots

Tracking Sargassum in the Caribbean: The Deployment and Validation of a Low-Cost Surface Drifter

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Pixa, Chase Manganini, Kevin Myers, Alyson Michel, Anna P.M. Department of Applied Ocean Physics and Engineering Woods Hole Oceanographic Institution 266 Woods Hole Road Woods HoleMA02543 United States Department of Mechanical Engineering Massachusetts Institute of Technology 77 Massachusetts Ave CambridgeMA02139 United States MIT-WHOI Joint Program in Oceanography/Applied Ocean Science & Engineering Cambridge and Woods Hole MA United States Fearless Fund 3029 Woodland Drive NW WashingtonDC20008 United States

Sargassum blooms have been causing significant ecological and economic damage to coastal regions in the Northern Equatorial Atlantic since 2011. To better understand the movement and effects of this macroalgae, there is a need to track its transport. In this study, a low-cost drifter was deployed, designed to entangle with Sargassum and aid in its tracking. The design was based on the results of twenty-seven drifter designs and five days of field trials. The tracking data was validated using gridded wind and current products, as well as high resolution satellite imagery. The successful entanglement and tracking with the Sargassum demonstrated in this study can provide in situ movement data to ground-truth models and supplement gaps in satellite imaging. The results can guide future studies and further our understanding of its movement in the great Atlantic Sargassum belt (GASB). © 2023, The Authors. All rights reserved.

关键词： Costs

Enabling Under-Ice Geochemical Observations with a Size, Weight, and Power-Constrained Robot

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Horowitz, Jess Preston, Victoria Michel, Anna P.M. Mechanical Engineering Massachusetts Institute of Technology Cambridge United States MIT-WHOI Joint Program Massachussetts Institute of Technology Cambridge United States Applied Ocean Physics and Engineering Woods Hole Oceanographic Institution Woods Hole United States

Estimates of greenhouse gas emissions from Arctic estuarine environments are dominated by in situ summer-time ice-free dissolved gas measurements due to the logistical ease of performing field observations in these conditions. Recent evidence in coastal Arctic environments, however, has demonstrated that dissolved methane (CH4) and carbon dioxide (CO2) are strongly seasonally variable, and at least one significant gas ventilation event occurs during the spring freshet. Whether the Arctic serves as a source or sink of greenhouse emissions has significant implications on modeling climate change and its feedback mechanisms. To enable higher resolution spatiotemporal measurements of dissolved gases in typically undersampled conditions, remotely operated vehicles (ROVs) can be used to extract near continuous water samples below ice before and during the spring freshet. Here, we present a size, weight, and power-constrained (SWAP) underwater vehicle (UV) and novel geochemical sampling system suitable for taking under-ice geochemical observations and demonstrate the proposed system in a field-analog setting for Arctic estuarine studies. Copyright © 2022, The Authors. All rights reserved.

关键词： Carbon dioxide

Robotic Planning under Uncertainty in Spatiotemporal Environments in Expeditionary science

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Preston, Victoria Flaspohler, Genevieve Michel, Anna P.M. Fisher, John W. Roy, Nicholas MIT-WHOI Joint Program Massachusetts Institute of Technology CambridgeMA02139 United States Applied Ocean Physics and Engineering Woods Hole Oceanographic Institution United States Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology CambridgeMA02139 United States

In the expeditionary sciences, spatiotemporally varying environments - hydrothermal plumes, algal blooms, lava flows, or animal migrations - are ubiquitous. Mobile robots are uniquely well-suited to study these dynamic, mesoscale natural environments. We formalize expeditionary science as a sequential decision-making problem, modeled using the language of partially-observable Markov decision processes (POMDPs). Solving the expeditionary science POMDP under real-world constraints requires efficient probabilistic modeling and decision-making in problems with complex dynamics and observational models. Previous work in informative path planning, adaptive sampling, and experimental design have shown compelling results, largely in static environments, using data-driven models and information-based rewards. However, these methodologies do not trivially extend to expeditionary science in spatiotemporal environments: they generally do not make use of scientific knowledge such as equations of state dynamics, they focus on information gathering as opposed to scientific task execution, and they make use of decision-making approaches that scale poorly to large, continuous problems with long planning horizons and real-time operational constraints. In this work, we discuss these and other challenges related to probabilistic modeling and decision-making in expeditionary science, and present some of our preliminary work that addresses these gaps. We ground our results in a real expeditionary science deployment of an autonomous underwater vehicle (AUV) in the deep ocean for hydrothermal vent discovery and characterization. Our concluding thoughts highlight remaining work to be done, and the challenges that merit consideration by the reinforcement learning and decision-making community. Copyright © 2022, The Authors. All rights reserved.

关键词： Decision making

Active reward learning for co-robotic vision based exploration in bandwidth limited environments

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Jamieson, Stewart How, Jonathan P. Girdhar, Yogesh MIT-WHOI Joint Program in Applied Ocean Science and Engineering United States United States

We present a novel POMDP problem formulation for a robot that must autonomously decide where to go to collect new and scientifically relevant images given a limited ability to communicate with its human operator. From this formulation we derive constraints and design principles for the observation model, reward model, and communication strategy of such a robot, exploring techniques to deal with the very highdimensional observation space and scarcity of relevant training data. We introduce a novel active reward learning strategy based on making queries to help the robot minimize path "regret" online, and evaluate it for suitability in autonomous visual exploration through simulations. We demonstrate that, in some bandwidth-limited environments, this novel regret-based criterion enables the robotic explorer to collect up to 17% more reward per mission than the next-best criterion. Copyright © 2020, The Authors. All rights reserved.

关键词： Machine design

Corrigendum to “Lipid composition, caloric content, and novel oxidation products from microbial communities within seasonal pack ice cores” [Geochimica et Cosmochimica Acta 368 (2024) 12–23]

学校读者我要写书评

暂无评论

Geochimica et Cosmochimica Acta 2024年 382卷 161-161页

作者： Henry C. Holm Helen F. Fredricks Shavonna M. Bent Daniel P. Lowenstein Kharis R. Schrage Benjamin A.S. Van Mooy Marine Chemistry and Geochemistry Department Woods Hole Oceanographic Institution Woods Hole MA 02543 USA MIT-WHOI Joint Program in Oceanography/Applied Ocean Science & Engineering Cambridge MA 02139 USA