A5101739685- Underwater Vehicles and Communication Systems
- Advanced Computational Techniques and Applications
- Soft Robotics and Applications
- Teleoperation and Haptic Systems
- Orbital Angular Momentum in Optics
- Robot Manipulation and Learning
- Target Tracking and Data Fusion in Sensor Networks
- Underwater Acoustics Research
- Geographic Information Systems Studies
- Micro and Nano Robotics
- Remote Sensing and Land Use
- Land Use and Ecosystem Services
- Data Stream Mining Techniques
- Robotic Path Planning Algorithms
- Advanced Materials and Mechanics
- Infrastructure Maintenance and Monitoring
- Virtual Reality Applications and Impacts
- Engineering and Technology Innovations
- Evolutionary Algorithms and Applications
- Entrepreneurship Studies and Influences
- Environmental Changes in China
- Advanced Neural Network Applications
- Distributed Sensor Networks and Detection Algorithms
- Characterization and Applications of Magnetic Nanoparticles
- Gaze Tracking and Assistive Technology
Peng Cheng Laboratory
2020-2024
Zhejiang Ocean University
2024
Zhejiang University
2024
Sanya University
2024
Yangzhou University
2015
Institute of Navigation
2004
Abstract Underwater object detection (UOD) is crucial for marine economic development, environmental protection, and the planet's sustainable development. The main challenges of this task arise from low‐contrast, small objects, mimicry aquatic organisms. key to addressing these focus model on obtaining more discriminative information. authors observe that edges underwater objects are highly unique can be distinguished low‐contrast or environments based their edges. Motivated by observation,...
Large-scale complex underwater concrete structures have structural damage and the traditional detection method mostly uses manual identification, which is inaccurate inefficient. Therefore, robotic systems been proposed to replace identification for in ocean engineering. However, highly corrosive disruptive environment of poses great difficulties application. Here, we develop a manta ray-inspired robot with well controllability establish datasets structures, proposing YOLOX-DG algorithm...
Accurately localization between multi-robots is crucial for many underwater applications, such as tracking, convoying and subsea intervention tasks. 6D pose estimation a fundamental task that enables precise object in 3D space with full six degrees of freedom. However, one critical challenge the lack available large-scale datasets due to unbearable cost labelled data collection. To overcome this difficulty, we propose benchmark dataset, ROV6D, remotely operated vehicles (ROVs). The training...
Streaming data sequences arise from various areas in the era of big data, and it is challenging to explore efficient online models that adapt them. To address potential heterogeneity, we introduce a new estimation procedure analyze constantly incoming streaming datasets. The underlying model structures are assumed be generalized linear with dynamic regression coefficients. Our key idea lies introducing vector unknown parameters measure differences between batch-specific coefficients adjacent...
Underwater navigation that relies solely on dead reckoning suffers from unbounded position error growth. In traditional positioning method, the cost and trouble of deploying, recovering, assembly have become insuperable obstacle. Based combination SLBL with an Argo float, a new method autonomous is proposed in paper. order to improve ranging accuracy, pattern time delay shift coding system, second correlation given for estimation this The superiority cross-correlation could be estimated...
Although methods for estimating the pose of objects in indoor scenes have achieved great success, estimation underwater remains challenging due to difficulties brought by complex environment, such as degraded illumination, blurring, and substantial cost obtaining real annotations. In response, we introduce FAFA, a Frequency-Aware Flow-Aided self-supervised framework 6D unmanned vehicles (UUVs). Essentially, first train frequency-aware flow-based estimator on synthetic data, where an...
It has been demonstrated that sound waves carrying orbital angular momentum undergo frequency modulation after being reflected by a rotating object. In this paper, we, observed the rotational Doppler shift phenomenon of acoustic vortex in an underwater environment using Fresnel-spiral zone plate for construction focused with controllable topological charge. The positive and negative rotation speeds spinning object are precisely determined vortex's effect provides possibility to improve...
Based on education agent application, the paper designed emotional detection model and overall schema of for learners.Then completed personality learning monitoring learners defined attitude, cognitive state preference through extraction analysis information between learners.The conducted personalized resources service by using automatically generated courses tool based results in order to improve human-computer interaction status remote effect.The also studied evaluation method system...
Abstract We discuss the following theoretical questions regarding GIS spatial data in this paper: integration of concepts, quantity data, structure oriented multi-dimensional and dynamic analysis, initialization measurement data. In paper, we problems that occur when using to resolve these questions. Based on analysis necessary for GIS, four types relation were defined: location, adjacency, nearness, influence. These are ordered by increasing quantity. The organization all comprehensively...
Population aging is one of the challenges facing China’s rural industrial upgrading. Rural upgrading basis revitalization strategy, and agricultural technological innovation core Clarifying relationship between population aging, technology can provide a practical for government to formulate effective Revitalization Strategy. Based on time series data from 1997 2018, an autoregressive model constructed test interactive The results show that will promote industries. Although in short term,...
Observation of the rotational Doppler
To explore the complex underwater world, autonomous vehicles (AUVs) are extensively used, whose recovery has been a challenging issue. achieve high-efficiency AUV recovery, we propose novel transformable vehicle (TUV) which can maintain closed state for low-resistance approaching and transform into an opening to increase possibility of success. The configuration thrusters is evaluated optimized. design simulation results will be shown in this paper.
Underwater acoustic positioning has been commonly used in a wide variety of underwater work, including deep construction, oil and gas extraction, ocean sciences robot navigation. To date, various methods have developed to achieve accurate coordinate localization, such as ultrashort baseline (USBL), short (SBL) long (LBL) system. The surveys these classic hydroacoustic localizations are typically executed by employing the time-of-flight method measure distance orientation (vertical horizontal...
The long propagation delay and limited node energy seriously affect the transmission efficiency in underwater acoustic network. Solutions based on network coding have been investigated many literatures. Though improved, when destination fails to receive enough uncorrelated packets a generation, time spent this generation are wasted. As hardware performance improves, we can use edge caching improve decoding probability of coding, taking advantage little extra storage resource exchange for...
The recovery of autonomous underwater vehicles (AUVs) has been a challenging mission due to the limited localization accuracy and movement capability AUVs. To overcome these limitations, we propose novel design deployable robot (DUR) for mission. Utilizing origami structure, DUR can transform between open closed states maximize performance at different stages. At approaching stage, will remain state reduce drag force. While capturing state, deploy form much larger opening improve success...