TY - GEN
T1 - Reinforcement-learning-based miniature UAV identification
AU - Xiaoyu, She
AU - Zhenyu, Guan
AU - Ruizhi, Mao
AU - Jie, Li
AU - Chengwei, Yang
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/7/2
Y1 - 2017/7/2
N2 - The present paper proposes a novel identification method (RL-BP) for miniature unmanned aircrafts, utilizing Reinforcement-Learning Algorithm to explore the unknown environment, thus optimizing to the appropriate hidden layer node number of the neural network. RL-BP then constructs the corresponding network, trains through samples and updates the network weights, wherein the reward function values are fed back to Reinforcement-Learning Algorithm for optimization. This paper represents and analyzes the RL-BP method, and verifies the method with recorded flight data. The test results show that RL-BP greatly improves upon traditional neural network identification method in both resource consumption and computation accuracy, as RL-BP reduces Average Relative Error by 37.89% and Maximum Relative Error by 31.44% on an average.
AB - The present paper proposes a novel identification method (RL-BP) for miniature unmanned aircrafts, utilizing Reinforcement-Learning Algorithm to explore the unknown environment, thus optimizing to the appropriate hidden layer node number of the neural network. RL-BP then constructs the corresponding network, trains through samples and updates the network weights, wherein the reward function values are fed back to Reinforcement-Learning Algorithm for optimization. This paper represents and analyzes the RL-BP method, and verifies the method with recorded flight data. The test results show that RL-BP greatly improves upon traditional neural network identification method in both resource consumption and computation accuracy, as RL-BP reduces Average Relative Error by 37.89% and Maximum Relative Error by 31.44% on an average.
KW - Reinforcement Learning
KW - UAV
KW - identification method
KW - miniature aircraft
KW - neural network
UR - https://www.scopus.com/pages/publications/85050861820
U2 - 10.1109/ICUS.2017.8278347
DO - 10.1109/ICUS.2017.8278347
M3 - Conference contribution
AN - SCOPUS:85050861820
T3 - Proceedings of 2017 IEEE International Conference on Unmanned Systems, ICUS 2017
SP - 237
EP - 242
BT - Proceedings of 2017 IEEE International Conference on Unmanned Systems, ICUS 2017
A2 - Xu, Xin
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 IEEE International Conference on Unmanned Systems, ICUS 2017
Y2 - 27 October 2017 through 29 October 2017
ER -