学习增强了对边缘辅助遥感中异质无人机群体的日程安排和资源分配
Jingjing Zhang1, Yunyi Hu2, Mengmeng Shao3
1School of Computer Science and Engineering, Central South University, Changsha, China.
Scientific reports
|January 6, 2026
概括
这项研究引入了一个新的框架,用于协调大规模遥感中的无人机群. 该系统优化了任务分配和路径规划,提高了任务成功率和效率,特别是在关键任务中.
科学领域:
- 机器人技术和自主系统
- 地理空间科学与技术 空间科学与技术
- 计算机科学与工程 计算机科学与工程
背景情况:
- 大规模的3D绘图和高分辨率的遥感对于环境监测,灾害评估和城市规划至关重要.
- 不同质的无人机群为这些任务提供了高效,适应性和资源意识的操作.
- 挑战包括实现完整的空间覆盖,确保传感相关性,以及在动态环境中优化通信和计算资源.
研究的目的:
- 为异质无人机群体提出一个能源和资源意识的合作框架 (DMMP-PR-TSA).
- 共同优化用于传感任务的空间路径规划和用于边缘处理的计算资源配置.
- 嵌入关键任务的优先处理,并提高整体运营效率.
主要方法:
- 遥感数据驱动的区域分区.
- 改进了基于自组织地图 (SOM) 的智能预分配.
- 基于优先级的动态任务重新分配 (PR) 和基于强化学习 (RL) 的任务顺序调整 (TSA).
主要成果:
- 在大规模任务中,DMMP-PR-TSA表现出[公式:参见文本]更高的完成率.
- 在动态车队变化下实现了[公式:参见文本]的改进.
- 与基线算法相比,高优先级任务的成功率始终更高.
结论:
- 拟议的框架有效地解决了无人机群基于遥感和边缘计算的挑战.
- 模拟结果验证了其可扩展性,稳定性和适用于关键任务场景的适用性.
- 突出了无人机系统大规模遥感的智能化和运营效率的进步.
更多相关视频
07:49Automated Deployment of an Internet Protocol Telephony Service on Unmanned Aerial Vehicles Using Network Functions Virtualization
Published on: November 26, 2019
8.5K
06:00Electroantennography-based Bio-hybrid Odor-detecting Drone using Silkmoth Antennae for Odor Source Localization
Published on: August 27, 2021
6.0K
相关概念视频
00:48Optimal Foraging
13.6K
How animals obtain and eat their food is called foraging behavior. Foraging can include searching for plants and hunting for prey and depends on the species and environment.
13.6K
02:12Short-distance Transport of Resources
17.4K
Short-distance transport refers to transport that occurs over a distance of just 2-3 cells, crossing the plasma membrane in the process. Small uncharged molecules, such as oxygen, carbon dioxide, and water, can diffuse across the plasma membrane on their own. In contrast, ions and larger molecules require the assistance of transport proteins due to their charge or size. Transport across membranes also occurs within individual cells, playing a variety of essential roles for the plant as a whole.
17.4K