收稿日期: 2017-03-27
修回日期: 2017-07-23
网络出版日期: 2017-07-21
基金资助
国家自然科学基金（61202490）；航空科学基金（20150896010）
UAV path planning based on GA-OCPA learning system
Received date: 2017-03-27
Revised date: 2017-07-23
Online published: 2017-07-21
Supported by
National Natural Science Foundation of China (61202490); Aeronautical Science Foundation of China (20150896010)
为解决未知空域中无人机路径规划方法实时性和适用性不足的问题，以生物应激条件反射理论为基础，将无人机实时路径规划类比为在外界条件刺激下的一种自学习行为。首先，将概率自动机与遗传算法相结合，设计了基于Skinner操作条件反射理论框架（GA-OCPA）的学习系统；然后，将无人机规避机动的飞行速度、滚转加速度和拉升加速度作为系统学习的行为，并计算每次学习尝试之后的选择概率和个体适应度，通过遗传算法搜索最优行为进而得到最优路径；最后，运用增量多层判别回归树（IHDR）对学习得到的最优行为建立知识库，形成威胁状态与路径规划的匹配映射。实验结果表明GA-OCPA学习系统对于无人机路径规划具备有效性和适用性。
刘鑫 , 杨霄鹏 , 刘雨帆 , 姚昆 . 基于GA-OCPA学习系统的无人机路径规划方法[J]. 航空学报, 2017 , 38(11) : 321275 -321275 . DOI: 10.7527/S1000-6893.2017.321275
To solve the problem of deficiency in real-timeliness and applicability of path planning for the Unmanned Aerial Vehicle (UAV) in the unknown airspace, the real-time path planning of the UAV is simulated as a self-learning behavior under the condition of external stimuli, based on the biological operant conditioning theory. The probabilistic automaton is combined with the genetic algorithm to construct a learning system of Genetic Algorithm-Operant Conditioning Probabilistic Automaton (GA-OCPA) according to the Skinner operant conditioning. The UAVs' evasion maneuvering flight speed, rolling acceleration and climbing acceleration are taken as the learning behaviors of the system, and the probability of selection and individual fitness are calculated after each learning attempt. The optimal path can then be obtained by searching for the best behavior using the genetic algorithm. The knowledge base of the best learned behaviors is established using Incremental Hierarchical Discriminant Regression (IHDR), and the matching mapping between the threat state and path planning is then formed. The result shows the viability and applicability of the GA-OCPA learning system for UAV path planning.
[1] KAVRAKI L E, SVESTKA P, LATOMBE J C, er al. Randomized preprocessing of configuration space for fast path planning[C]//IEEE International Conference on Robotics and Automation. Piscataway, NJ:IEEE Press, 1994:3020-3026.
[2] XIAO Q K, GAO X G, FU X W, et al. New local path replanning algorithm for unmanned combat air vehicle[C]//Proceedings of the 6th World Congress on Intelligent Control and Automation. Piscataway, NJ:IEEE Press, 2006:4033-4037.
[3] 丁家如, 杜昌平, 赵耀, 等. 基于改进人工势场法的无人机路径规划算法[J]. 计算机应用, 2016, 36(1):287-290. DING J R, DU C P, ZHAO Y, et al. Path planning algorithm for unmanned aerial vehicles based on improved artificial potential field[J]. Journal of Computer Applications, 2016, 36(1):287-290(in Chinese).
[4] CHEN T B, ZHANG Q S. Robot motion planning based on improved artificial potential field[C]//3rd 2013 International Conference on Computer Science and Network Technology. Piscataway, NJ:IEEE Press, 2013:1208-1211.
[5] JU H S, TSAI C C. Design of intelligent flight control law following the optical payload[C]//Proceedings of the 2004 IEEE International Conference on Networking, Science & Network. Piscataway, NJ:IEEE Press, 2004:761-766.
[6] LUGO G I, FLORES G, SALAZAR S, et al. Dubins path generation for a fixed wing UAV[C]//International Conference on Unmanned Aircraft Systems. Piscataway, NJ:IEEE Press, 2014:339-346.
[7] LEE D, SHIM D H. Spline-RRT* based optimal path planning of terrain following flight for fixed-wing UAVs[C]//The 11th International Conference on Ubiquitous Robots and Intelligence. Piscataway, NJ:IEEE Press, 2014:257-261.
[8] GUAN X M, ZHANG X J, WEI J, et al. A strategic conflict avoidance approach based on cooperative coevolutionary with the dynamic grouping strategy[J]. International Journal of Systems Science, 2016, 47(9):1995-2008.
[9] 魏瑞轩, 何仁珂, 张启瑞, 等. 基于Skinner理论的无人机应急威胁规避方法[J]. 北京理工大学学报, 2016, 36(6):620-624. WEI R X, HE R K, ZHANG Q R, et al. Skinner-based emergency collision avoidance mechanism for UAV[J]. Transactions of Beijing Institute of Technology, 2016, 36(6):620-624(in Chinese).
[10] LIN Z J, LIU H T. Consensus based on learning game theory with a UAV rendezvous application[J]. Chinese Journal of Aeronautics, 2015, 28(1):191-199.
[11] ZHANG B, LIU W, MAO Z, et al. Cooperative and Ge-ometric Learning Algorithm(CGLA) for path planning of UAVs with limited information[J]. Automatica, 2014, 50(3):809-820.
[12] ZHANG B, MAO Z, LIU W, et al. Geometric reinforcement learning for path planning of UAVs[J]. Journal of Intelligent & Robotic Systems, 2015, 77(2):391-409.
[13] 郝钏钏, 方舟, 李平. 基于Q学习的无人机三维航迹规划算法[J]. 上海交通大学学报, 2012, 46(12):1931-1935. HAO C C, FANG Z, LI P. A 3-D route planning algorithm for unmanned aerial vehicle based on Q-learning[J]. Journal of Shanghai Jiaotong University, 2012, 46(12):1931-1935(in Chinese).
[14] ZHAO Y, LI W, SHI P. A real-time collision avoidance learning system for unmanned surface vessels[J]. Neurocomputing, 2016, 182:255-266.
[15] WOLF R, HEISENBERG M. Basic organization of operant-behavior as revealed in drosophila flight orientation[J]. Journal of Comparative Physiology A, 1991:169(6):699-705.
[16] HWANG W S, WENG J. Hierarchical discriminant regression[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(11):1277-1293.
[17] WENG J, HWANG W S. Incremental hierarchical discriminant regression[J]. IEEE Transactions on Neural Networks, 2013, 56(11):2745-2761.
[18] KNEPPER R A, MASON M T. Realtime informed path sampling for motion planning search[J]. International Journal of Robotics Research, 2017, 31(11):1231-1250.
[19] 张军. 空域监视技术的新进展及应用[J]. 航空学报, 2011, 32(1):1-14. ZHANG J. New development and application of airspace surveillance technology[J]. Acta Aeronautica et Astronautica Sinica, 2011, 32(1):1-14(in Chinese).
[20] MELEGA M, LAZARUS S, SAVVARIS A, et al. Multiple threats sense and avoid algorithm for static and dynamic obstacles[J]. Journal of Intelligent & Robotic Systems, 2015, 77(1):630-635.
[21] CHEN Y, YU J, MEI Y, et al. Modified central force optimization (MCFO) algorithm for 3D UAV path planning[J]. Neurocomputing, 2016, 171:878-888.
/
| 〈 |
|
〉 |
CJA