Dynamic path planning of unmanned aerial vehicle based on crowd density prediction
Received date: 2020-12-29
Revised date: 2021-03-30
Online published: 2021-11-28
Supported by
National Key Research and Development Program of China(2017YFB0503005)
The Key Research Program of Chinese Academy of Sciences(ZDRW-KT-2020-2-1)
Tianjin Intelligent Manufacturing Project(Tianjin-IMP-2018-2)
Copyright
With the rapid growth of the number of unmanned aerial vehicles (UAVs), in order to assess the risk of people on the ground especially in cities, improve the operational efficiency of UAV, and reduce the threat of UAV to the crowd, it is necessary to make a specific path planning for UAVs based on the crowd density. However, static demographic data are still used as the ground risk analysis basis for the path planning of UAV, and real-time path planning of UAV according to the spatial-temporal characteristics of crowd density are often not performed. This study first analyzed the characteristics of urban road network crowd density based on the spatiotemporal data. Second, the convolutional neural network-long short-term memory (CNN-LSTM) combined model (C-Snet model) was established to predict the population density in different urban areas. Finally, the improved A* algorithm was used for real-time path planning and risk assessment of UAV according to the predicted crowd density data. The results show that the risk of UAV operation is reduced by 76%, which can provide a theoretical reference for the development of real-time path planning function of UAV traffic management system.
Key words: UAV traffic management; risk assessment; CNN; crowd density; path planning
JIAO Qingyu , CHEN Xinfeng , ZHENG Zhigang , BAI Yiqin , LIU Yansi , ZHANG Zhengjuan , SUN Longni . Dynamic path planning of unmanned aerial vehicle based on crowd density prediction[J]. PROGRESS IN GEOGRAPHY, 2021 , 40(9) : 1516 -1527 . DOI: 10.18306/dlkxjz.2021.09.007
表1 SORA评估初始地面风险系数Tab.1 SORA initial ground risk scores |
指标 | 无人机尺寸/m | |||
---|---|---|---|---|
1 | 3 | 8 | >8 | |
动能 | <700 J | <34 kJ | <1084 kJ | >1084 kJ |
运行场景 | ||||
视距内运行(VLOS),受控区域且人口稀少 | 1 | 2 | 3 | 4 |
视距外运行(BVLOS),受控区域且人口稀少 | 2 | 3 | 4 | 5 |
VLOS,人口居住区 | 3 | 4 | 5 | 6 |
BVLOS,受控区域且在人口居住区 | 4 | 5 | 6 | 8 |
BVLOS,人口居住区 | 5 | 6 | 8 | 10 |
VLOS,密集人群 | 7 | |||
BVLOS,密集人群 | 8 |
表3 人口密度指数Tab.3 Population density index |
编号 | 观测 时间 | 中心点 经度/(°E) | 中心点 纬度/(°N) | 范围 面积/m2 | 区域人群密度指数 |
---|---|---|---|---|---|
1 | 2020-01-17T01:00 | 116.201 | 39.906 | 90062 | 2.9 |
2 | 2020-01-17T03:00 | 116.311 | 39.933 | 100235 | 1.0 |
3 | 2020-01-17T09:00 | 116.251 | 39.920 | 73640 | 6.5 |
表4 模型参数调整Tab.4 Model parameter adjustments |
epoch | 学习速率(lr) | |||
---|---|---|---|---|
MSE (标准化) | ||||
0.1 | 0.01 | 0.001 | ||
100 | 0.98 | 0.22 | 0.22 | |
500 | 1.00 | 0.19 | 0.15 | |
1000 | 0.63 | 0.14 | 0.08 |
表5 基于不同卷积核数量的卷积层性能Tab.5 Performance of convolution layers based on different numbers of convolution cores |
Conv1 | Conv2 | Maxpooling | MSE |
---|---|---|---|
3×3 | 3×3 | 3×3 | 14.7 |
5×5 | 3×3 | 3×3 | 10.5 |
7×7 | 3×3 | 3×3 | 12.3 |
表6 基于不同神经元数量的全连接层性能Tab.6 Performance of the full join layer based on different numbers of neurons |
神经元数量 | MSE | 拟合速率/s |
---|---|---|
64-64-64 | 15.48(欠拟合) | 1048.06 |
256-256-256 | 7.03 | 1326.51 |
256-128-64 | 7.07 | 1023.37 |
表7 模型对比Tab.7 Model comparison |
模型 | R2 | MSE | MAE |
---|---|---|---|
SVM | 0.73 | 4.02 | 18.30 |
RF | 0.82 | 3.77 | 10.25 |
Multi regression | 0.70 | 14.23 | 22.30 |
C-Snet | 0.86 | 3.78 | 5.32 |
[1] |
中国民航局. 中国民用航空局低空联网无人机安全飞行测试报告 [EB/OL]. 2018-02-06 [2020-11-01]. http://www.caac.gov.cn/XXGK/XXGK/GFXWJ/201811/t20181127_193186.html.
[Civil Aviation Administration of China. CAAC low altitude networking UAV flight safety test report. 2018-02-06 [2020-11-01]. http://www.caac.gov.cn/XXGK/XXGK/GFXWJ/201811/t20181127_193186.html.]
|
[2] |
徐瑞华, 罗帆. 机场净空区无人机扰航监管演化博弈研究[J]. 中国安全科学学报, 2019, 29(5):25-30.
[
|
[3] |
[
|
[4] |
中国民用航空局航空器适航审定司. 基于运行风险的无人机适航审定指导意见 [EB/OL]. 2019-01-25 [2020-11-01]. http://www.caac.gov.cn/XXGK/XXGK/ZFGW/201901/P020190125609946283900.pdf.
[CAAC Aircraft Airworthiness Certification Department. Guidance on airworthiness certification of UAV based on operational risk. 2019-01-25 [2020-11-01]. http://www.caac.gov.cn/XXGK/XXGK/ZFGW/201901/P020190125609946283900.pdf.]
|
[5] |
|
[6] |
|
[7] |
|
[8] |
张启钱, 许卫卫, 张洪海, 等. 复杂低空物流无人机路径规划[J]. 北京航空航天大学学报, 2020, 46(7):1275-1286.
[
|
[9] |
|
[10] |
|
[11] |
|
[12] |
|
[13] |
Joint Authorities for Rulemaking of Unmanned Systems. JARUS guidelines on Specific Operations Risk Assessment (SORA)[EB/OL]. 2019-01-30 [2020-11-01]. https://rpas-regulations.com/wp-content/uploads/2017/07/170626_JARUS_Specific-Operations-Risk-Assessment_SORA_v1.0.pdf.
|
[14] |
胡莘婷, 戴福青. 基于城区行人安全的无人机运行风险评估[J]. 中国安全科学学报, 2020, 30(8):137-142.
[
|
[15] |
中国民用航空局航空器适航审定司. 无人机云系统数据规范: MH-T2011-2019 [EB/OL]. 2019-10-22 [2020-11-01]. http://www.caac.gov.cn/XXGK/XXGK/BZGF/HYBZ/202008/P020200824383769494708.pdf.
[CAAC Aircraft Airworthiness Certification Department. UAV cloud system data specification: MH-T2011-2019. 2019-10-22 [2020-11-01]. http://www.caac.gov.cn/XXGK/XXGK/BZGF/HYBZ/202008/P020200824383769494708.pdf. ]
|
[16] |
中国民用航空局航空器适航审定司. 无人机云系统接口数据规范: MH-T2009-2017 [EB/OL]. 2017-10-20[2020-11-01]. http://www.caac.gov.cn/HDJL/YJZJ/201707/P020170711601854912740.pdf.
[CAAC Aircraft Airworthiness Certification Department. Specification for interface data of unmanned aircraft system: MH-T2009-2017. 2017-10-20[2020-11-01]. http://www.caac.gov.cn/HDJL/YJZJ/201707/P020170711601854912740.pdf.]
|
[17] |
廖小罕. 地理科学发展与新技术应用[J]. 地理科学进展, 2020, 39(5):709-715.
[
|
[18] |
付婧婷, 陈慈发. 风力下的无人机偏离公共航路仿真研究[J]. 信息通信, 2020, 33(11):49-53.
[
|
[19] |
魏宗康, 高荣荣, 周姣, 等. 基于椭圆概率误差的落点精度评定方法[J]. 导弹与航天运载技术, 2020(2):58-63.
[
|
[20] |
|
[21] |
|
/
〈 |
|
〉 |