Scholarlink

<p>Unmanned aerial vehicles (UAVs) are increasingly utilized in complex surveillance operations, necessitating efficient coordination algorithms to ensure optimal performance under dynamic conditions. Current methods often struggle with scalability, dynamic environments, and real-time decision-making. To overcome the above drawbacks and develop a scalable, robust method for coordinating among diverse entities in UAVs, utilize a scalable glowworm swarm-tuned versatile support vector machine (SGS–VSVM) to optimize UAV behavior and task assignment in surveillance operations. Data for UAV missions were collected from simulations, including real-time positional data, environmental conditions, 1000 UAV sensor readings, and task completion metrics. Data cleaning and normalization are performed to reduce noise, standardize inputs, and optimize the model's performance in predicting the behavior of diverse entities during surveillance operations, robotics and autonomous systems play crucial roles. The SGS–VSVM integrates glowworm swarm optimization (GSO) for tuning VSVM parameters, improving the accuracy and efficiency of UAV coordination under complex, dynamic conditions. The model is tested and implemented in Python, and it shows encouraging results in accuracy (98.5%), <i>F</i>1-score (98.42%), total cost, energy consumption, and task execution delay for large-scale UAV systems in surveillance missions. The SGS–VSVM algorithm is effective in coordinating heterogeneous entities and UAVs for complex surveillance missions. It can adapt to changing environments, scale effectively, and offer a promising solution for real-time applications in autonomous systems with enhancement in coverage, task distribution, and mission success rates.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

SGS–VSVM: An Adaptive UAV Coordination and Task Distribution Strategy for Large-Scale Real-Time Surveillance Missions

  • 期刊论文

  • 发表日期：

    2025年12月16日

查看全文
  • Simranjeet Nanda,
  • Abhishek Singla,
  • Rakhi Chakraborty,
  • Aneesh Wunnava,
  • S K Manju Bargavi,
  • Radhika Sreedharan

摘要

Unmanned aerial vehicles (UAVs) are increasingly utilized in complex surveillance operations, necessitating efficient coordination algorithms to ensure optimal performance under dynamic conditions. Current methods often struggle with scalability, dynamic environments, and real-time decision-making. To overcome the above drawbacks and develop a scalable, robust method for coordinating among diverse entities in UAVs, utilize a scalable glowworm swarm-tuned versatile support vector machine (SGS–VSVM) to optimize UAV behavior and task assignment in surveillance operations. Data for UAV missions were collected from simulations, including real-time positional data, environmental conditions, 1000 UAV sensor readings, and task completion metrics. Data cleaning and normalization are performed to reduce noise, standardize inputs, and optimize the model's performance in predicting the behavior of diverse entities during surveillance operations, robotics and autonomous systems play crucial roles. The SGS–VSVM integrates glowworm swarm optimization (GSO) for tuning VSVM parameters, improving the accuracy and efficiency of UAV coordination under complex, dynamic conditions. The model is tested and implemented in Python, and it shows encouraging results in accuracy (98.5%), F1-score (98.42%), total cost, energy consumption, and task execution delay for large-scale UAV systems in surveillance missions. The SGS–VSVM algorithm is effective in coordinating heterogeneous entities and UAVs for complex surveillance missions. It can adapt to changing environments, scale effectively, and offer a promising solution for real-time applications in autonomous systems with enhancement in coverage, task distribution, and mission success rates.