Jiaze Cai

Cambridge, Massachusetts

United States

jiaze12@mit.edu; jiaze12@berkeley.edu

Hi! I am a PhD student in the Department of Electrical Engineering and Computer Science (EECS) at MIT, working in the Soft and Micro Robotics Laboratory advised by Prof. Kevin Chen. My research interest is in the design and low-level control of bio-inspired aerial robots, particularly bird-scale and micro flapping-wing platforms.

I received my B.S. in Aerospace Engineering with a minor in Electrical Engineering from Texas A&M University and my M.Eng. in Mechanical Engineering (with a concentration in Control of Robotic and Autonomous Systems) from the University of California, Berkeley. During my master’s, I was a Research Assistant at UC Berkeley Hybrid Robotics Group advised by Prof. Koushil Sreenath, working on the design and learning-based control for a bird-inspired flapping-wing UAV.

Since high school, I have designed and built FIRST Robotics Competition (FRC) robots and made DIY drones with Arduino. In college, I was a TAMU SAE AERO Aerodynamic, Stability & Control (ASC) Sub-team member working on the aerodynamic design of a 16-lb wooden Aircraft that can store 26 soccer balls inside its wing. I was also an undergraduate researcher at TAMU Advanced Vertical Flight Lab supervised by Prof. Moble Benedict, where I worked on Vertical Take-off and Landing (VTOL) Unmanned Aerial Vehicles (UAVs) and flight dynamics.

You can find more details about my work in the publications page and view my full portfolio for more projects and research work.

Selected Publications

UAV Design
Development of a tube-launched tail-sitter unmanned aerial vehicle

Jiaze Cai, Hunter Denton, Moble Benedict, and 1 more author

International Journal of Micro Air Vehicles, 2024

Abs DOI Bib

This paper describes the development and flight testing of a tail-sitter unmanned aerial vehicle (UAV) platform that has the potential to be tube-launched. Integrated with vertical take-off and landing (VTOL) capability, the platform can perform high-endurance loiter tasks along with low-speed and hovering flights, and land vertically in limited spaces. The current design utilizes a thrust-vectored counter-rotating coaxial propeller combined with a foldable conventional fixed-wing to accomplish both vertical and horizontal flights. A feedback control strategy capable of stabilizing and controlling the vehicle in both vertical and horizontal flight was designed and implemented on a custom-designed 1.7-gram autopilot. Several tests were conducted in hover and edgewise flight with aggressive pilot inputs to demonstrate the controllability of the aircraft even in the presence of moderate wind gusts. Additionally, transition flight tests were also performed, which demonstrated the vehicle’s capability of transitioning from vertical to fixed-wing horizontal flight using thrust-vectoring-based pitch control.
@article{cai2024ALUAS, author = {Cai, Jiaze and Denton, Hunter and Benedict, Moble and Kang, Hao}, title = {Development of a tube-launched tail-sitter unmanned aerial vehicle}, journal = {International Journal of Micro Air Vehicles}, publisher = {sagepub}, volume = {16}, number = {}, pages = {17568293241254045}, year = {2024}, doi = {10.1177/17568293241254045}, }
Control, RL
Learning-based Trajectory Tracking for Bird-inspired Flapping-Wing Robots

Jiaze Cai, Vishnu Sangli, Mintae Kim, and 1 more author

2024

Abs Bib HTML Video

Bird-sized flapping-wing robots offer significant potential for agile flight in complex environments, but achieving agile and robust trajectory tracking remains a challenge due to the complex aerodynamics and highly nonlinear dynamics inherent in flapping-wing flight. In this work, a learning-based control approach is introduced to unlock the versatility and adaptiveness of flapping-wing flight. We propose a model-free reinforcement learning (RL)-based framework for a high degree-of-freedom (DoF) bird-inspired flapping-wing robot that allows for multimodal flight and agile trajectory tracking. Stability analysis was performed on the closed-loop system comprising of the flapping-wing system and the RL policy. Additionally, simulation results demonstrate that the RL-based controller can successfully learn complex wing trajectory patterns, achieve stable flight, switch between flight modes spontaneously, and track different trajectories under various aerodynamic conditions.
@article{cai2024learning, title = {Learning-based Trajectory Tracking for Bird-inspired Flapping-Wing Robots}, author = {Cai, Jiaze and Sangli, Vishnu and Kim, Mintae and Sreenath, Koushil}, year = {2024}, eprint = {2411.15130}, archiveprefix = {arXiv}, primaryclass = {cs.RO}, }

Jiaze Cai

Selected Publications

Selected Projects

Tube-launched VTOL UAV (2022-2023)

High-DoF Flapping-Wing Robot (2024-present)