To address the shortcomings of single-step decision making in the existing deep reinforcement learning based unmanned aerial vehicle(UAV)real-time path planning problem,a real-time UAV path planning algorithm based on...To address the shortcomings of single-step decision making in the existing deep reinforcement learning based unmanned aerial vehicle(UAV)real-time path planning problem,a real-time UAV path planning algorithm based on long shortterm memory(RPP-LSTM)network is proposed,which combines the memory characteristics of recurrent neural network(RNN)and the deep reinforcement learning algorithm.LSTM networks are used in this algorithm as Q-value networks for the deep Q network(DQN)algorithm,which makes the decision of the Q-value network has some memory.Thanks to LSTM network,the Q-value network can use the previous environmental information and action information which effectively avoids the problem of single-step decision considering only the current environment.Besides,the algorithm proposes a hierarchical reward and punishment function for the specific problem of UAV real-time path planning,so that the UAV can more reasonably perform path planning.Simulation verification shows that compared with the traditional feed-forward neural network(FNN)based UAV autonomous path planning algorithm,the RPP-LSTM proposed in this paper can adapt to more complex environments and has significantly improved robustness and accuracy when performing UAV real-time path planning.展开更多
Aiming at the shortcoming that the traditional industrial manipulator using off-line programming cannot change along with the change of external environment,the key technologies such as machine vision and manipulator ...Aiming at the shortcoming that the traditional industrial manipulator using off-line programming cannot change along with the change of external environment,the key technologies such as machine vision and manipulator control are studied,and a complete manipulator vision tracking system is designed.Firstly,Denavit-Hartenberg(D-H)parameters method is used to construct the model of the manipulator and analyze the forward and inverse kinematics equations of the manipulator.At the same time,a binocular camera is used to obtain the threedimensional position of the target.Secondly,in order to make the manipulator track the target more accurately,the fuzzy adaptive square root unscented Kalman filter(FSRUKF)is proposed to estimate the target state.Finally,the manipulator tracking system is built by using the position-based visual servo.The simulation experiments show that FSRUKF converges faster and with less error than the square root unscented Kalman filter(SRUKF),which meets the application requirements of the manipulator tracking system,and basically meets the application requirements of the manipulator tracking system in the practical experiments.展开更多
基金supported by the Natural Science Basic Research Prog ram of Shaanxi(2022JQ-593)。
文摘To address the shortcomings of single-step decision making in the existing deep reinforcement learning based unmanned aerial vehicle(UAV)real-time path planning problem,a real-time UAV path planning algorithm based on long shortterm memory(RPP-LSTM)network is proposed,which combines the memory characteristics of recurrent neural network(RNN)and the deep reinforcement learning algorithm.LSTM networks are used in this algorithm as Q-value networks for the deep Q network(DQN)algorithm,which makes the decision of the Q-value network has some memory.Thanks to LSTM network,the Q-value network can use the previous environmental information and action information which effectively avoids the problem of single-step decision considering only the current environment.Besides,the algorithm proposes a hierarchical reward and punishment function for the specific problem of UAV real-time path planning,so that the UAV can more reasonably perform path planning.Simulation verification shows that compared with the traditional feed-forward neural network(FNN)based UAV autonomous path planning algorithm,the RPP-LSTM proposed in this paper can adapt to more complex environments and has significantly improved robustness and accuracy when performing UAV real-time path planning.
基金supported by Natural Science Basic Research Program of Shaanxi(2022JQ-593)Key Research and Development Program of Shaanxi(2022GY-089)。
文摘Aiming at the shortcoming that the traditional industrial manipulator using off-line programming cannot change along with the change of external environment,the key technologies such as machine vision and manipulator control are studied,and a complete manipulator vision tracking system is designed.Firstly,Denavit-Hartenberg(D-H)parameters method is used to construct the model of the manipulator and analyze the forward and inverse kinematics equations of the manipulator.At the same time,a binocular camera is used to obtain the threedimensional position of the target.Secondly,in order to make the manipulator track the target more accurately,the fuzzy adaptive square root unscented Kalman filter(FSRUKF)is proposed to estimate the target state.Finally,the manipulator tracking system is built by using the position-based visual servo.The simulation experiments show that FSRUKF converges faster and with less error than the square root unscented Kalman filter(SRUKF),which meets the application requirements of the manipulator tracking system,and basically meets the application requirements of the manipulator tracking system in the practical experiments.
