A Comparative Study of Range Based and Range Free Algorithm for Node Localization in Underwater

e-Prime - Advances in Electrical Engineering Electronics and Energy, Journal Year: 2024, Volume and Issue: 9, P. 100727 - 100727

Published: Aug. 15, 2024

• Localization of underwater localization wireless sensor networks. Range-based algorithm for node in underwater. Range free Parameters considered The exploration surfaces and their monitoring has become an emerging field interest many researchers. is a crucial task the Underwater Wireless Sensor Network (UWSN). In comparison to terrestrial nodes, localizing nodes more difficult. UWSN, communication signals between challenging due acoustic position tends move strong water current deep sea whereas are static comparatively easier. Strategic surveillance relies on accurate UWSN follow assets activities. Addressing issues improves situational awareness, disaster response, mitigation areas. We reviewed Range-Based Range-Free algorithms from numerous research articles discussed trade-offs improvement opportunities. comparative analysis was made based various parameters like coverage area, density network, energy consumption, error computational complexity. performance helps researchers decide best or improve available UWSN.

Language: Английский

Underwater SLAM Meets Deep Learning: Challenges, Multi-Sensor Integration, and Future Directions

Sensors, Journal Year: 2025, Volume and Issue: 25(11), P. 3258 - 3258

Published: May 22, 2025

The underwater domain presents unique challenges and opportunities for scientific exploration, resource extraction, environmental monitoring. Autonomous vehicles (AUVs) rely on simultaneous localization mapping (SLAM) real-time navigation in these complex environments. However, traditional SLAM techniques face significant obstacles, including poor visibility, dynamic lighting conditions, sensor noise, water-induced distortions, all of which degrade the accuracy robustness systems. Recent advances deep learning (DL) have introduced powerful solutions to overcome challenges. DL enhance by improving feature image denoising, distortion correction, fusion. This survey provides a comprehensive analysis latest developments DL-enhanced applications, categorizing approaches based their methodologies, dependencies, integration with models. We critically evaluate benefits limitations existing techniques, highlighting key innovations unresolved In addition, we introduce novel classification framework its wireless networks (UWSNs). UWSNs offer collaborative that enhances localization, mapping, data sharing among AUVs leveraging acoustic communication distributed sensing. Our proposed taxonomy new insights into how communication-aware methodologies can improve operational efficiency Furthermore, discuss emerging research trends, use transformer-based architectures, multi-modal fusion, lightweight neural deployment, self-supervised techniques. By identifying gaps current outlining potential directions future work, this serves as valuable reference researchers engineers striving develop robust adaptive solutions. findings aim inspire further advancements autonomous supporting critical applications marine science, deep-sea management, conservation.

Language: Английский

Improved Robot Localization and Mapping Using Adaptive Tuna Schooling Optimization With Sensor Fusion Techniques

Journal of Field Robotics, Journal Year: 2025, Volume and Issue: unknown

Published: May 27, 2025

ABSTRACT Localization in mobile robotics is essential for achieving autonomy. Effective localization systems integrate data from multiple sensors to enhance state estimation and achieve accurate positioning. Accurate real‐time crucial robot control trajectory following. Key challenges include initializing the inertial measurement unit (IMU) biases direction of gravity, as well determining metric scale with a monocular camera. Traditional visual–inertial (VI) initialization techniques rely on precise vision‐only motion assessments address these issues. Multi‐sensor fusion faces challenges, such calibration, sensor groups, handling errors varying rates delays. This paper introduces an Adaptive Tuna Schooling Optimization (ATSO) method adjust strategies based environmental conditions dynamically. The factors affecting process are considered optimization algorithm, position optimally selected accordingly. Using Q‐learning Q‐DNN performs decision‐making past experiences. dynamic adaptation weight parameter allows algorithm converge toward optimal solutions, reducing computational complexity. Experimental results demonstrate that proposed approach improves performance, even challenging conditions.

Language: Английский