与陈绍冯 康宇 曹洋 等合作的题为 “Spectrally Normalized Adaptive Neural Identiﬁer for Dynamic Modeling and Trajectory Tracking Control of Unmanned Aerial Vehicle” 的论文获得《7th IEEE Conference on Advanced Robotics & Mechatronics (ICARM)》最佳会议论文奖（冯如奖）。该论文摘要如下：
Accurate dynamic modeling is diﬃcult for aerobatic unmanned aerial vehicle ﬂying at its physical limit, due to the model uncertainty caused by unobservable hidden states like airﬂow and vibrations. Although some progresses have been made, these hidden states are still not properly characterized, rendering system identiﬁcation problem for aerobatic unmanned aerial vehicle extremely challenging. To address this issue, this paper proposes a novel spectrally normalized adaptive neural identiﬁer for dynamic modeling of aerobatic unmanned aerial vehicle. Speciﬁcally, to characterize the model uncertainty, we propose a spectrally normalized adaptive neural network (SNANet) to extract deep features representing the hidden states of the system. Particularly, the proposed SNANet adopts a multi-model adaptive structure, making the model update online quickly and dynamically. Furthermore, the spectral normalization constraint is introduced into the training process to ensure the Lipschitz stability of the SNANet. Consequently, a trajectory tracking control scheme including a SNANet and a sliding mode controller is presented. The modeling eﬀectiveness of the proposed method is veriﬁed on a real ﬂight dataset. The results demonstrates that the proposed method has the characteristics of high modeling accuracy, short training time and fast model response speed.