第15卷第2期 智能系统学报 Vol.15 No.2 2020年3月 CAAI Transactions on Intelligent Systems Mar.2020 D0:10.11992/tis.201811018 网络出版地址：http:/kns.cnki.net/kcms/detail/23.1538.tp.20190409.0932.010.html 多约束下多无人机的任务规划研究综述 齐小刚，李博，范英盛，刘立芳2 (1.西安电子科技大学数学与统计学院，陕西西安710071；2.西安电子科技大学计算机学院，陕西西安 710071,3.西安电子科技大学宁波信息技术研究院，浙江宁波315200) 摘要：高度信息化的发展使得无人机作战优势凸显。准确的无人机任务规划技术是完成给定任务的重要保 障。任务分配、路径规划是构成无人机任务规划技术的两个核心部分。基于该技术，首先讨论了无人机任务规 划的发展状况、分类标准、体系结构。其次，分别详细介绍了影响任务分配、路径规划的重要指标，如分类标 准、约束指标、相应模型、代表算法、评价指标等，然后，分别分析对比求解任务分配的启发式算法、数学规划 方法、随机智能优化算法的优缺点和求解路径规划的数学规划方法、人工势场法、基于图形学法、智能优化算 法的优缺点：最后，总结了无人机任务规划存在的开放性问题、未来发展方向和研究重点。 关键词：无人机；任务规划：任务分配：路径规划；启发式算法；智能优化算法；平滑处理；可飞性 中图分类号：TP393文献标志码：A文章编号：1673-4785(2020)02-0204-14 中文引用格式：齐小刚，李博，范英盛，等.多约束下多无人机的任务规划研究综述.智能系统学报，2020,15(2)：204-217. 英文引用格式：QI Xiaogang,LIBo,FAN Yingsheng,etal.A survey of mission planning on UAVs systems based on multiple con straintsJCAAI transactions on intelligent systems,2020,15(2):204-217. A survey of mission planning on UAVs systems based on multiple constraints QI Xiaogang,LI Bo',FAN Yingsheng',LIU Lifang23 (1.School of Mathematics and Statistics,Xidian University,Xi'an 710071,China;2.School of Computer Science and Technology, Xidian University,Xi'an 710071,China;3.Xidian-Ningbo Information Technology Institute,Ningbo 315200,China) Abstract:Depending on the highly developed information technology,unmanned aerial vehicles(UAVs)have shown unprecedented advantages in combat.Accurate mission planning technique for UAVs provides an important guarantee for completing a given mission.Task assignment and path planning are the two core components of the mission plan- ning technology for UAVs.Based on this technology,first,the development status,classification standards,and archi- tecture of the mission planning for UAVs are discussed.Second,the important indicators,which affect task assignment and path planning are described in detail;they include classification criteria,constraint indicator,corresponding model, representative algorithm,and evaluation indicator.Then,the strength and weakness of the algorithms for solving tasks are compared,such as heuristic algorithm,mathematical programming method,and stochastic intelligent optimization algorithm.Similarly,for the path planning problem,the advantages and disadvantages of its algorithms,which include mathematical programming method,artificial potential field method,graphic-based method,and intelligent optimization algorithm,are also analyzed.Finally,open problems,the future work,and the research focus in UAVs mission planning are summarized. Keywords:unmanned aerial vehicle;mission planning;task assignment;path planning;heuristic algorithm;intelligence optimization algorithm;smoothing;flyable 近年来，随着科学技术的不断发展，信息技术 收稿日期：2018-11-24.网络出版日期：2019-04-11 的日新月异，战争的智能化、信息化和一体化，使 基金项目：国家自然科学基金项目(61877067,61572435)：教 育部-中国移动联合基金项目(MCM20170I03):西安 得任务规划成为高技术战争的重要支撑。自1917 市科技创新项目(201805029YD7CG13-6):宁波市自 然科学基金项目(2016A610035,2017A610119) 年美国研制出第一架无人机以来，无人机先后经 通信作者：李博.E-mail:libo202017@163.com. 历了靶机、侦察机和诱饵机几个发展阶段。无人DOI: 10.11992/tis.201811018 网络出版地址: http://kns.cnki.net/kcms/detail/23.1538.tp.20190409.0932.010.html 多约束下多无人机的任务规划研究综述 齐小刚1,3，李博1 ，范英盛1 ，刘立芳2,3 （1. 西安电子科技大学 数学与统计学院，陕西 西安 710071; 2. 西安电子科技大学 计算机学院，陕西 西安 710071; 3. 西安电子科技大学 宁波信息技术研究院，浙江 宁波 315200） 摘 要：高度信息化的发展使得无人机作战优势凸显。准确的无人机任务规划技术是完成给定任务的重要保 障。任务分配、路径规划是构成无人机任务规划技术的两个核心部分。基于该技术，首先讨论了无人机任务规 划的发展状况、分类标准、体系结构。其次，分别详细介绍了影响任务分配、路径规划的重要指标，如分类标 准、约束指标、相应模型、代表算法、评价指标等，然后，分别分析对比求解任务分配的启发式算法、数学规划 方法、随机智能优化算法的优缺点和求解路径规划的数学规划方法、人工势场法、基于图形学法、智能优化算 法的优缺点；最后，总结了无人机任务规划存在的开放性问题、未来发展方向和研究重点。 关键词：无人机；任务规划；任务分配；路径规划；启发式算法；智能优化算法；平滑处理；可飞性 中图分类号：TP393 文献标志码：A 文章编号：1673−4785(2020)02−0204−14 中文引用格式：齐小刚, 李博, 范英盛, 等. 多约束下多无人机的任务规划研究综述 [J]. 智能系统学报, 2020, 15(2): 204–217. 英文引用格式：QI Xiaogang, LI Bo, FAN Yingsheng, et al. A survey of mission planning on UAVs systems based on multiple con￾straints[J]. CAAI transactions on intelligent systems, 2020, 15(2): 204–217. A survey of mission planning on UAVs systems based on multiple constraints QI Xiaogang1,3 ，LI Bo1 ，FAN Yingsheng1 ，LIU Lifang2,3 (1. School of Mathematics and Statistics, Xidian University, Xi’an 710071, China; 2. School of Computer Science and Technology, Xidian University, Xi’an 710071, China; 3. Xidian-Ningbo Information Technology Institute, Ningbo 315200, China) Abstract: Depending on the highly developed information technology, unmanned aerial vehicles (UAVs) have shown unprecedented advantages in combat. Accurate mission planning technique for UAVs provides an important guarantee for completing a given mission. Task assignment and path planning are the two core components of the mission plan￾ning technology for UAVs. Based on this technology, first, the development status, classification standards, and archi￾tecture of the mission planning for UAVs are discussed. Second, the important indicators, which affect task assignment and path planning are described in detail; they include classification criteria, constraint indicator, corresponding model, representative algorithm, and evaluation indicator. Then, the strength and weakness of the algorithms for solving tasks are compared, such as heuristic algorithm, mathematical programming method, and stochastic intelligent optimization algorithm. Similarly, for the path planning problem, the advantages and disadvantages of its algorithms, which include mathematical programming method, artificial potential field method, graphic-based method, and intelligent optimization algorithm, are also analyzed. Finally, open problems, the future work, and the research focus in UAVs mission planning are summarized. Keywords: unmanned aerial vehicle; mission planning; task assignment; path planning; heuristic algorithm; intelligence optimization algorithm; smoothing; flyable 近年来，随着科学技术的不断发展，信息技术 的日新月异，战争的智能化、信息化和一体化，使 得任务规划成为高技术战争的重要支撑。自 1917 年美国研制出第一架无人机以来，无人机先后经 历了靶机、侦察机和诱饵机几个发展阶段。无人 收稿日期：2018−11−24. 网络出版日期：2019−04−11. 基金项目：国家自然科学基金项目 (61877067，61572435)；教 育部−中国移动联合基金项目 (MCM20170103)；西安 市科技创新项目 (201805029YD7CG13-6)；宁波市自 然科学基金项目 (2016A610035，2017A610119). 通信作者：李博. E-mail：libo202017@163.com. 第 15 卷第 2 期 智 能 系 统 学 报 Vol.15 No.2 2020 年 3 月 CAAI Transactions on Intelligent Systems Mar. 2020