A5006754128- Underwater Vehicles and Communication Systems
- Robotics and Sensor-Based Localization
- Ammonia Synthesis and Nitrogen Reduction
- Catalytic Processes in Materials Science
- Robotics and Automated Systems
- Multimodal Machine Learning Applications
- Robotic Path Planning Algorithms
- Advanced Data Storage Technologies
- Human-Automation Interaction and Safety
- Service-Oriented Architecture and Web Services
- Maritime Navigation and Safety
- Virtual Reality Applications and Impacts
- Advanced Malware Detection Techniques
- Context-Aware Activity Recognition Systems
- Tactile and Sensory Interactions
- Advanced Image and Video Retrieval Techniques
- Catalysis and Oxidation Reactions
- Teleoperation and Haptic Systems
- Distributed systems and fault tolerance
- Industrial Gas Emission Control
- Digital and Cyber Forensics
- AI and HR Technologies
- Software Engineering Techniques and Practices
University of Florida
2023-2024
Universität Hamburg
2022
Hamburg University of Technology
2022
Enabling autonomous robots to safely and efficiently navigate, explore, map underwater caves is of significant importance water resource management, hydrogeology, archaeology, marine robotics. In this work, we demonstrate the system design algorithmic integration a visual servoing framework for semantically guided cave exploration. We present hardware edge-AI considerations deploy on novel AUV (Autonomous Underwater Vehicle) named CavePI. The navigation driven by computationally light yet...
Vision-language navigation (VLN) has emerged as a promising paradigm, enabling mobile robots to perform zero-shot inference and execute tasks without specific pre-programming. However, current systems often separate map exploration path planning, with relying on inefficient algorithms due limited (partially observed) environmental information. In this paper, we present novel pipeline named ''ClipRover'' for simultaneous target discovery in unknown environments, leveraging the capabilities of...
The growing worldwide attention toward large-scale subsea data centers has garnered substantial interest from commercial entities which have built and deployed underwater prototypes since 2015. These utilize hard disk drives (HDDs) as a cost-effective method of storage. However, researchers demonstrated that acoustic waves can affect the availability integrity HDDs applications rely on them. studies are all conducted in air laptops, hence their applicability implications submerged...
Underwater datacenters (UDCs) hold promise as next-generation data storage due to their energy efficiency and environmental sustainability benefits. While the natural cooling properties of water save power, isolated aquatic environment long-range sound propagation in create unique vulnerabilities which differ from those on-land centers. Our research discovers fault-tolerant devices, resource allocation software, distributed file systems acoustic injection attacks UDCs. With a realistic...
Underwater ROVs (Remotely Operated Vehicles) are unmanned submersible vehicles designed for exploring and operating in the depths of ocean. Despite using high-end cameras, typical teleoperation engines based on first-person (egocentric) views limit a surface operator's ability to maneuver navigate ROV complex deep-water missions. In this paper, we present an interactive interface that (i) offers on-demand "third"-person (exocentric) visuals from past egocentric views, (ii) facilitates...
This paper addresses the challenge of deploying machine learning (ML)-based segmentation models on edge platforms to facilitate real-time scene for Autonomous Underwater Vehicles (AUVs) in underwater cave exploration and mapping scenarios. We focus three ML models-U-Net, CaveSeg, YOLOv8n-deployed four platforms: Raspberry Pi-4, Intel Neural Compute Stick 2 (NCS2), Google Edge TPU, NVIDIA Jetson Nano. Experimental results reveal that mobile with modern architectures, such as YOLOv8n,...
This paper explores the design and development of a language-based interface for dynamic mission programming autonomous underwater vehicles (AUVs). The proposed 'Word2Wave' (W2W) framework enables interactive parameter configuration AUVs remote subsea missions. W2W includes: (i) set novel language rules command structures efficient language-to-mission mapping; (ii) GPT-based prompt engineering module training data generation; (iii) small model (SLM)-based sequence-to-sequence learning...
This review explores the evolution of human-machine interfaces (HMIs) for subsea telerobotics, tracing back transition from traditional first-person "soda-straw" consoles (narrow field-of-view camera feed) to advanced powered by gesture recognition, virtual reality, and natural language models. First, we discuss various forms telerobotics applications, current state-of-the-art (SOTA) interface systems, challenges they face in robust underwater sensing, real-time estimation, low-latency...
This review paper examines the integration of Artificial Intelligence (AI) within data mining, focusing on various algorithms, tools, and applications across different sectors. The details strengths weaknesses key algorithms such as supervised learning, unsupervised reinforcement learning. Furthermore, it discusses popular mining tools presents case studies highlighting impact AI fields like healthcare, finance, retail. concludes by identifying emerging trends, challenges, future research...
The industrial production of nitric acid by the Ostwald process is a major emission source potent green-house gas nitrous oxide that formed during catalytic oxidation ammonia. A systematic knowledge-based optimization ammonia oxidation, e.g. with respect to minimizing formation, hindered limited fundamental understanding resulting from lack experimental insight into reaction at conditions. Here we bridge this gap knowledge resolving concentration and temperature profiles in bench-scale...