Yaokun Lu

Ph.D. Student, Beihang University

A portrait of Yaokun Lu

Education

Beihang University (BUAA)
Ph.D. in Electronic Information, School of Automation Science and Electrical Engineering. Advisors: Prof. Lei Guo and Prof. Jianzhong Qiao. Thesis: multi-stage pointing control of airborne electro-optical tracking systems under disturbances and constraints.
2023 – 2027 (expected)
University of Electronic Science and Technology of China (UESTC)
M.S. in Signal and Information Processing, School of Information and Communication Engineering. Advisor: Prof. Zhenming Peng. Thesis: moving-target tracking in complex scenes.
2016 – 2019
University of Electronic Science and Technology of China (UESTC)
B.S. in Optical Information Science and Technology, School of Optoelectronic Science and Engineering.
2012 – 2016

Experience

Huzhou Institute of Zhejiang University
Research assistant in Prof. Fei Gao's group. Motion planning and control for agile fixed-wing UAVs at high angles of attack; observability-optimal excitation trajectories for online parameter self-calibration; fixed-wing test platform and flight software. One patent application (CN117891275A).
2022 – 2023
DiDi Chuxing
Senior algorithm engineer, international business. ETA prediction under a 5 ms online inference budget; passenger diversion model (DeepFM + ESMM; A/B tests: GMV +0.85%, CR +0.26 pp); order dispatch, hotspot and subsidy scheduling models. Outstanding Newcomer Award; promoted during tenure.
2019 – 2022
Tencent AI Lab
Research assistant, vision group. A lightweight QR-based nonlinear least-squares back-end for VINS, with half-precision support and ARM FPU acceleration on mobile devices.
2018 – 2019
Chengdu Yuanliu Automation Technology Co., Ltd.
Founder and technical lead (founded Oct 2018). Flight software for a tilt-rotor VTOL and an aerial-survey system that counts tobacco seedlings and measures field area from SfM reconstruction and YOLO detection, delivered to a provincial tobacco company.
2018
DJI
Flight-control intern. BSP/HAL embedded software for the A3 flight controller; a standard test procedure for barometer selection; ADS-B demo integration.
2015 – 2016

Main Awards and Honors

National Champion (First Prize), ROBOCON 2015
China's national university robot contest. Badminton robot; I was responsible for its vision system: high-speed stereo calibration, shuttlecock detection and Kalman-filter landing-point prediction.
2015
National Second Prize, National Undergraduate Electronic Design Contest
Autonomous line-following UAV; I was responsible for its flight control (Hough-transform line detection, MAVLink communication with Pixhawk).
2015
National Second Prize, National Undergraduate Optoelectronic Design Contest
Non-contact measurement of objects with complex surfaces.
2014
Outstanding Newcomer Award, DiDi Chuxing
2019
People's Scholarship (Second Class), UESTC; Graduate Academic Scholarship (First Class), UESTC
2012 – 2019

Publications

Disturbance-distribution learned Tube MPC for current-command gimbal pointing control
Yaokun Lu, et al.
The disturbance distribution is learned and used to tighten Tube-MPC constraints online. On a two-axis current-command gimbal (Intel N100 + CAN, 100 Hz), the 2-D pointing RMSE is 3.94 mrad, about 47% lower than nominal MPC, with zero current-limit activations and a worst-case solve time of 4.5 ms.
IEEE Transactions on Circuits and Systems II (under review), 2026
Model predictive control of airborne inertially stabilized platforms: A physics-informed and data-driven disturbance separation approach
Yaokun Lu, et al.
Periodic and non-periodic disturbances on an airborne inertially stabilized platform are separated with a physics-informed model and data-driven observers, then predicted and compensated inside MPC.
IEEE Transactions on Aerospace and Electronic Systems (under review), 2026
Active excitation through motion: Raptor-inspired attack separation control of airborne inertial stabilized platforms In staring mode, disturbances from different sources look like the same slow drift. Small aircraft maneuvers inside the field-of-view safety limits excite them, so they can be separated online and compensated separately.
2026 IEEE 20th International Conference on Control and Automation (ICCA), pp. 105–110
Disturbance refined separation-based composite control for airborne electro-optical gimbals subject to pointing constraints Composite control for airborne electro-optical gimbals that separates disturbances in finer detail while respecting pointing constraints.
Actuators, 15(4), 197, 2026
Refined disturbance utilization-based green control for spacecraft with composite actuator disturbances Spacecraft attitude control that separates composite actuator disturbances and exploits the usable part instead of cancelling all of it.
IEEE/ASME Transactions on Mechatronics, 30(6), 5652–5662, 2025
Composite disturbance separation and utilization-based maneuver control for spacecrafts with reaction wheel errors Maneuver control for spacecraft with reaction-wheel errors, based on separating composite disturbances and exploiting the usable part.
Proceedings of ICGNC 2024, Lecture Notes in Electrical Engineering, Springer, pp. 454–463, 2025