正在加载图片...
·939· 张鹏鹏，等：旋翼无人机在移动平台降落的控制参数自学习调节方法 第5期 based autonomous multirotor landing on a moving plat- mobile robots[J].Expert systems with applications,2017, form[C]//2018 IEEE/RSJ International Conference on In- 80:183-199 telligent Robots and Systems (IROS).Madrid,IEEE, [21]CHOI J,CHEON D,LEE J.Robust landing control of a 2018:1010-1017 quadcopter on a slanted surface[J].International journal [10]SHAKER M,SMITH M N R,YUE Shigang,et al.Vis- of precision engineering and manufacturing,2021,22(6): ion-based landing of a simulated unmanned aerial vehicle 1147-1156. with fast reinforcement learning[C]//2010 International [22]KIM J,JUNG Y,LEE D,et al.Landing control on a mo- Conference on Emerging Security Technologies.Canter- bile platform for multi-copters using an omnidirectional bury,EEE,2010:183-188. image sensor[J].Journal of intelligent robotic systems, [11]RODRIGUEZ-RAMOS A.SAMPEDRO C.BAVLE H. 2016.841/2/3/4):529-541 et al.A deep reinforcement learning strategy for UAV [23]CELEMIN C,RUIZ-DEL-SOLAR J.An interactive autonomous landing on a moving platform[J].Journal of framework for learning continuous actions policies based intelligent&robotic systems,2019,93(1/2):351-366. on corrective feedback[J].Journal of intelligent robotic [12]LEE S,SHIM T,KIM S,et al.Vision-based autonomous systems..2019.95(1):77-97. landing of a multi-copter unmanned aerial vehicle using [24]SILVER D.HUANG A.MADDISON C J.et al.Master- reinforcement learning[C]//2018 International Confer- ing the game of Go with deep neural networks and tree ence on Unmanned Aircraft Systems(ICUAS).Dallas, search[J.Nature,2016,529(7587):484-489 IEEE.2018:108-114. [25]GRIGORESCU S.TRASNEA B.COCIAS T.et al.A [13]ARULKUMARAN K.DEISENROTH M.BRUNDAGE survey of deep learning techniques for autonomous driv- M,et al.Deep reinforcement learning:a brief survey[J]. ing[J].Journal of field robotics,2020,37(3):362-386. IEEE signal processing magazine,2017,34:26-38. [26]HESSEL M.MODAYIL J.VAN HASSELT H.et al. [14]HESSEL M,SOYER H.ESPEHOLT L,et al.Multi-task Rainbow:combining improvements in deep reinforce- deep reinforcement learning with PopArt[J].Proceedings ment learning[EB/OLl.(2017-01-01)[2021-01-011.ht- of the AAAl conference on artificial intelligence,2019, tps://arxiv.org/abs/1710.02298. 33:3796-3803 [27]SUTTON R S,BARTO A G.Reinforcement learning:an [15]SEDIGHIZADEH M,REZAZADEH A.Adaptive PID introduction[M].Cambridge,Mass:MIT Press,1998. controller based on reinforcement learning for wind tur- [28]WATKINS C J C H,DAYAN P.Q-learning[J].Machine bine control[J].World academy of science,engineering learning,1992,8(3/4):279-292. and technology,international journal of computer,elec- [29]MNIH V.KAVUKCUOGLU K.SILVER D,et al.Hu- trical,automation,control and information engineering, man-level control through deep reinforcement learning[J]. 2008.2:124129. Nature,2015,518(7540):529-533. [16]WANG Shuti,YIN Xunhe,LI Peng,et al.Trajectory [30]VAN HASSELT H,GUEZ A,SILVER D.Deep rein- tracking control for mobile robots using reinforcement forcement learning with double Q-learning[EB/OL]. learning and PID[J].Iranian journal of science and tech- (2015-05-01)[2020-12-20].https:/arxiv.org/abs/ nology,transactions of electrical engineering,2020, 1509.06461v3. 44(3):1059-1068 [31]WANG Z.SCHAUL T.HESSEL M,et al.Dueling net- [17]ASADI K.KALKUNTE SURESH A.ENDER A.et al. work architectures for deep reinforcement learning[C]// An integrated UGV-UAV system for construction site International conference on machine learning.PMLR. data collection[J].Automation in construction,2020,112: 2016:1995-2003 103068. [32]KOUBAA A.Robot operating system (ROS):The com- [18]ERGINER B,ALTUG E.Modeling and PD control of a plete reference[M].volume 1.Cham:Springer,2016. quadrotor VTOL vehicle[C]//2007 IEEE Intelligent Vehicles Symposium.Istanbul,IEEE,2007:894-899. 作者简介： [19]LILLICRAP T P.HUNT J J,PRITZEL A,et al.Continu- 张鹏鹏，硕士研究生，主要研究方 ous control with deep reinforcement learning[EB/OL]. 向为空地协同系统、智能无人系统。 (2015-01-01)[2021-01-01].htps:/axiv.org/abs/1509 02971. [20]CARLUCHO I,DE PAULA M,VILLAR S A,et al.In- cremental Q-learning strategy for adaptive PID control ofbased autonomous multirotor landing on a moving platform[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Madrid, IEEE, 2018: 1010−1017. SHAKER M, SMITH M N R, YUE Shigang, et al. Vision-based landing of a simulated unmanned aerial vehicle with fast reinforcement learning[C]//2010 International Conference on Emerging Security Technologies. Canterbury, IEEE, 2010: 183−188. [10] RODRIGUEZ-RAMOS A, SAMPEDRO C, BAVLE H, et al. A deep reinforcement learning strategy for UAV autonomous landing on a moving platform[J]. Journal of intelligent & robotic systems, 2019, 93(1/2): 351–366. [11] LEE S, SHIM T, KIM S, et al. Vision-based autonomous landing of a multi-copter unmanned aerial vehicle using reinforcement learning[C]//2018 International Conference on Unmanned Aircraft Systems (ICUAS). Dallas, IEEE, 2018: 108−114. [12] ARULKUMARAN K, DEISENROTH M, BRUNDAGE M, et al. Deep reinforcement learning: a brief survey[J]. IEEE signal processing magazine, 2017, 34: 26–38. [13] HESSEL M, SOYER H, ESPEHOLT L, et al. Multi-task deep reinforcement learning with PopArt[J]. Proceedings of the AAAI conference on artificial intelligence, 2019, 33: 3796–3803. [14] SEDIGHIZADEH M, REZAZADEH A. Adaptive PID controller based on reinforcement learning for wind turbine control[J]. World academy of science, engineering and technology, international journal of computer, electrical, automation, control and information engineering, 2008, 2: 124–129. [15] WANG Shuti, YIN Xunhe, LI Peng, et al. Trajectory tracking control for mobile robots using reinforcement learning and PID[J]. Iranian journal of science and technology, transactions of electrical engineering, 2020, 44(3): 1059–1068. [16] ASADI K, KALKUNTE SURESH A, ENDER A, et al. An integrated UGV-UAV system for construction site data collection[J]. Automation in construction, 2020, 112: 103068. [17] ERGINER B, ALTUG E. Modeling and PD control of a quadrotor VTOL vehicle[C]//2007 IEEE Intelligent Vehicles Symposium. Istanbul, IEEE, 2007: 894−899. [18] LILLICRAP T P, HUNT J J, PRITZEL A, et al. Continuous control with deep reinforcement learning[EB/OL]. (2015−01−01)[2021−01−01]. https: //arxiv. org/abs/1509. 02971. [19] CARLUCHO I, DE PAULA M, VILLAR S A, et al. Incremental Q-learning strategy for adaptive PID control of [20] mobile robots[J]. Expert systems with applications, 2017, 80: 183–199. CHOI J, CHEON D, LEE J. Robust landing control of a quadcopter on a slanted surface[J]. International journal of precision engineering and manufacturing, 2021, 22(6): 1147–1156. [21] KIM J, JUNG Y, LEE D, et al. Landing control on a mobile platform for multi-copters using an omnidirectional image sensor[J]. Journal of intelligent & robotic systems, 2016, 84(1/2/3/4): 529–541. [22] CELEMIN C, RUIZ-DEL-SOLAR J. An interactive framework for learning continuous actions policies based on corrective feedback[J]. Journal of intelligent & robotic systems, 2019, 95(1): 77–97. [23] SILVER D, HUANG A, MADDISON C J, et al. Mastering the game of Go with deep neural networks and tree search[J]. Nature, 2016, 529(7587): 484−489. [24] GRIGORESCU S, TRASNEA B, COCIAS T, et al. A survey of deep learning techniques for autonomous driving[J]. Journal of field robotics, 2020, 37(3): 362−386. [25] HESSEL M, MODAYIL J, VAN HASSELT H, et al. Rainbow: combining improvements in deep reinforcement learning[EB/OL].(2017−01−01)[2021−01−01]. https: //arxiv. org/abs/1710.02298. [26] SUTTON R S, BARTO A G. Reinforcement learning: an introduction[M]. Cambridge, Mass: MIT Press, 1998. [27] WATKINS C J C H, DAYAN P. Q-learning[J]. Machine learning, 1992, 8(3/4): 279–292. [28] MNIH V, KAVUKCUOGLU K, SILVER D, et al. Human-level control through deep reinforcement learning[J]. Nature, 2015, 518(7540): 529−533. [29] VAN HASSELT H, GUEZ A, SILVER D. Deep reinforcement learning with double Q-learning[EB/OL]. (2015−05−01)[2020−12−20].https://arxiv. org/abs/ 1509.06461v3. [30] WANG Z, SCHAUL T, HESSEL M, et al. Dueling network architectures for deep reinforcement learning[C]// International conference on machine learning. PMLR, 2016: 1995−2003. [31] KOUBAA A. Robot operating system (ROS): The complete reference[M]. volume 1. Cham: Springer, 2016. [32] 作者简介： 张鹏鹏，硕士研究生，主要研究方 向为空地协同系统、智能无人系统。 ·939· 张鹏鹏，等：旋翼无人机在移动平台降落的控制参数自学习调节方法 第 5 期