对深度确定性策略梯度算法训练智能体学习小型无人飞行器的飞行控制策略进行了探索研究。以多数据帧的速度、位置和姿态角等信息作为智能体的观察状态，舵摆角和发动机推力指令作为智能体的输出动作，飞行器的非线性模型和飞行环境作为智能体的学习环境。智能体在与环境交互过程中除了获得包含误差信息的密集惩罚外，也有达成一定目标的稀疏奖励，该设计有效提高了飞行数据的样本多样性，增强了智能体的学习效率。最后智能体实现了从位置、速度和姿态角等信息到控制量的端到端飞行控制，并进行了变航迹点、模型参数拉偏、注入扰动和故障条件下的飞行控制仿真，结果表明智能体除了能有效完成训练任务外，还能应对多种训练时未学习的飞行任务，具有优秀的泛化能力和鲁棒性，该方法具有一定的研究价值和工程参考价值。
The deep deterministic policy gradient algorithm is used to train the agent to learn the flight control strategy of a small UAV. The velocity, position and attitude angle of multi data frames are taken as the observation state of the agent, the rudder deflection angle and engine thrust command the output actions of the agent, and the nonlinear model and flight environment of the UAV the learning environment of the agent. In the interaction process between the agent and the environment, sparse rewards are provided to achieve certain goals, in addition to the dense punishment including error information, thereby effectively improving the diversity of flight data samples and enhancing the learning efficiency of the agent. The agent finally realizes the end-to-end flight control from the position, velocity and attitude angle to the control variables. In addition, the flight control simulations under the conditions of variable track point, model parameter deviation, disturbance and fault are carried out. Simulation results show that the agent can not only effectively complete the training task, but also deal with a variety of flight tasks not learned during training, showing excellent generalization ability and exhibiting certain research value and engineering reference value of the method.
[1] 符文星, 郭行, 闫杰. 智能无人飞行器技术发展趋势综述[J]. 无人系统技术, 2019, 2(4):31-37. FU W X, GUO H, YAN J, et al. Overview on the technology development trend of intelligent unmanned aerial vehicle[J]. Unmanned Systems Technology, 2019, 2(4):31-37(in Chinese).
[2] FLANAGAN J, STRUTZENBERG R, MYERS R, et al. Development and flight testing of a morphing aircraft, the NextGen MFX-1[C]//48th AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference. Reston:AIAA, 2007:23-26.
[3] 雷旭升, 陶冶. 小型无人飞行器风场扰动自适应控制方法[J]. 航空学报, 2010, 31(6):1171-1176. LEI X S, TAO Y. Adaptive control for small unmanned aerial vehicle under wind disturbance[J]. Acta Aeronautica et Astronautica Sinica, 2010, 31(6):1171-1176(in Chinese).
[4] XU R, OZGUNER U. Sliding mode control of a quadrotor helicopter[C]//Proceedings of the 45th IEEE Conference on Decision and Control. Piscataway:IEEE, 2006:4957-4962.
[5] 刘德元, 刘昊, LEWIS F L. 尾座式无人飞行器鲁棒容错编队控制[J]. 航空学报, 2021, 42(2):324296. LIU D Y, LIU H, LEWIS F L. Robust fault-tolerant formation control for tail-sitters[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(2):324296(in Chinese).
[6] 党小为, 唐鹏, 孙洪强, 等. 基于角加速度估计的非线性增量动态逆控制及试飞[J]. 航空学报, 2020, 41(4):323534. DANG X W, TANG P, SUN H Q, et al. Incremental nonlinear dynamic inversion control and flight test based on angular acceleration estimation[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41(4):323534(in Chinese).
[7] 陈书钊, 楚龙飞, 杨秀梅, 等. 状态预测神经网络控制应用于小型可回收火箭[J]. 航空学报, 2019, 40(3):322286. CHEN S Z, CHU L F, YANG X M, et al. Application of state prediction neural network control algorithm in small reusable rocket[J]. Acta Aeronautica et Astronautica Sinica, 2019, 40(3):322286(in Chinese).
[8] 刘金琨. 智能控制[M]. 4版. 北京:电子工业出版社, 2017:178-179. LIU J K. Intelligent control[M]. 4th ed. Beijing:Publishing House of Electronics Industry, 2017:178-179(in Chinese).
[9] NG A Y, COATES A, DIEL M, et al. Autonomous inverted helicopter flight via reinforcement learning[M]//Experimental Robotics IX. Berlin, Heidelberg:Springer, 2006:363-372.
[10] ABBEEL P, COATES A, QUIGLEY M, et al. An application of reinforcement learning to aerobatic helicopter flight[C]//Advances in Neural Information Processing Systems 19:Proceedings of the 2006 Conference. Cambridge:MIT Press, 2007:1-8.
[11] SILVER D, LEVER G, HEESS N, et al. Deterministic policy gradient algorithms[C]//31st International Conference on Machine Learning, 2014:387-395.
[12] LILLICRAP T P, HUNT J J, PRITZEL A, et al. Continuous control with deep reinforcement learning[DB/OL]. arXiv preprint:1509.02971, 2015.
[13] SCHULMAN J, LEVINE S, MORITZ P, et al. Trust region policy optimization[DB/OL]. arXiv preprint:1502.05477, 2015.
[14] SCHULMAN J, WOLSKI F, DHARIWAL P, et al. Proximal policy optimization algorithms[DB/OL]. arXiv preprint:1707.06347, 2017.
[15] HWANGBO J, SA I, SIEGWART R, et al. Control of a quadrotor with reinforcement learning[J]. IEEE Robotics and Automation Letters, 2017, 2(4):2096-2103.
[16] KOCH W, MANCUSO R, WEST R, et al. Reinforcement learning for UAV attitude control[DB/OL]. arXiv preprint:1804.04154, 2018.
[17] LIN X B, YU Y, SUN C Y. Supplementary reinforcement learning controller designed for quadrotor UAVs[J]. IEEE Access, 2019, 7:26422-26431.
[18] WANG Y D, SUN J, HE H B, et al. Deterministic policy gradient with integral compensator for robust quadrotor control[J]. IEEE Transactions on Systems, Man, and Cybernetics:Systems, 2020, 50(10):3713-3725.
[19] 冯超. 强化学习精要:核心算法与TensorFlow实现[M]. 北京:电子工业出版社, 2018. FENG C. Essentials of reinforcement learning:Core algorithm and TensorFlow implementation[M]. Beijing:Publishing House of Electronics Industry, 2018(in Chinese).
[20] KONDA V R, TSITSIKLIS J N. Actor-critic algorithms[C]//Advances in Neural Information Processing Systems, 2000:1008-1014.
[21] WATKINS C J C H. Learning from delayed rewards[D]. Cambridge:University of Cambridge, 1989.
[22] SUTTON R S. Learning to predict by the methods of temporal differences[J]. Machine Learning, 1988, 3(1):9-44.
[23] MNIH V, KAVUKCUOGLU K, SILVER D, et al. Playing Atari with deep reinforcement learning[C]//26th Neural Information Processing Systems, 2013:201-220.
[24] MNIH V, KAVUKCUOGLU K, SILVER D, et al. Human-level control through deep reinforcement learning[J]. Nature, 2015, 518(7540):529-533.
CJA