基于能效轨迹设计的无人机场景多用户移动数据

数据内容：此数据集针对应急救援场景下的无人机任务调度，旨在优化无人机路径，以最大化对地面移动用户的通信覆盖和数据采集量。该数据集中包含多个地面用户随时间的二维位置移动信息，以评估不同基于Q-learning的能效优化算法的效果。具体内容包括：（a）用户二维移动坐标：记录多个用户随时间变化的二维位置;（b）路径规划优化数据：通过Q-learning优化算法生成的路径数据，包含各飞行路径在不同任务完成时间和功率消耗方面的对比。数据集内含1个数据集说明文件，1个支撑数据文件。 数据来源：该数据集通过Python软件进行仿真生成。模拟了用户在不同速度和方向下的移动特性，并根据能效轨迹规划策略迭代更新无人机路径，生成覆盖最大化的数据集。 时间及地点：采集地点为之江实验室，采集时间为2022年5月至2023年1月。 设备情况：实验中使用了个人计算机、远程服务器等设备。Data Content: This dataset targets UAV mission scheduling in emergency rescue scenarios, aiming to optimize UAV paths to maximize communication coverage and data collection volume for ground mobile users. It contains time-varying 2D position movement information of multiple ground users, used to evaluate the performance of different energy-efficiency optimization algorithms based on Q-learning. The specific contents include: (a) User 2D movement coordinates: records the time-varying 2D positions of multiple users; (b) Path planning optimization data: path data generated via Q-learning optimization algorithms, including comparisons of different flight paths in terms of task completion time and power consumption. The dataset includes 1 dataset description file and 1 supporting data file. Data Source: This dataset is generated through Python-based simulations. The movement characteristics of users with different speeds and directions are simulated, and the UAV paths are iteratively updated based on energy-efficient trajectory planning strategies to generate a dataset with maximized coverage. Time and Location: The data collection was conducted at ZhiJiang Lab, from May 2022 to January 2023. Equipment: Personal computers, remote servers and other equipment were used in the experiments.

搜集汇总

背景与挑战

背景概述

该数据集针对应急救援场景，提供无人机场景下多用户移动数据，旨在通过优化无人机路径来最大化地面用户的通信覆盖和数据采集。它包含地面用户的二维移动坐标和基于Q-learning算法的路径规划数据，通过Python仿真生成，采集于2022年5月至2023年1月的浙江实验室。