header-img header-img

Boyu Zhou's Homepage

Hello! I am Boyu Zhou, currently working toward the Ph.D. degree in the Aerial Robotics Group, Robotics Institute, Hong Kong University of Science and Technology. I am expected to graduate in 2022. I got my B.Eng. degree from Shanghai Jiao Tong University.

My research focuses on mobile robot motion planning and dense mapping that enable safe and agile autonomous navigation in unknown complex environments. I am also interested in informative path planning with their application in inspection, exploration, etc.

News

Autonomous exploration is a fundamental problem for various applications of unmanned aerial vehicles(UAVs). Recently I propose FUEL, a hierarchical framework that can support Fast UAV ExpLoration in complex unknown environments. Our method is demonstrated to complete challenging exploration tasks 3-8 times faster than state-of-the-art approaches. Our work was showed on IEEE Spectrum Video Friday. It has been accepted by RA-L.
[Paper] [Video] [Code] (code to be released)

gif image: FUEL1 gif image: FUEL2

Videos of papers Robust and Efficient Quadrotor Trajectory Generation for Fast Autonomous Flight and Robust Real-time UAV Replanning Using Guided Gradient-based Optimization and Topological Paths were featured on IEEE Spectrum Video Friday! Thanks for Contributor Fan Shi, and Editor Evan and Erico! [Link2] [Link2] [Link3] (Search for HKUST in the pages).

I present RAPTOR, a Robust And Perception-aware TrajectOry Replanning framework to enable fast and safe flight in complex unknown environments. Its main features are: (a) finding feasible and high-quality trajectories in very limited computation time, and (b) introducing a perception-aware strategy to actively observe and avoid unknown obstacles. The associated paper is accepted by T-RO. [Paper] [Video]

gif image: raptor1 gif image: raptor2

Paper Robust Real-time UAV Replanning Using Guided Gradient-based Optimization and Topological Paths has been accepted by ICRA 2020. It presents a UAV replanning method that can support aggressive autonomous flight in unknown cluttered environments. It features searching for multiple trajectories in distinctive topological classes, exploring the solution space more thoroughly and yielding better solutions. [Paper] [Video] [Code] [IEEE Spectrum]

gif image: icra20

Paper Robust and Efficient Quadrotor Trajectory Generation for Fast Autonomous Flight has been accepted by RA-L. It presents kinodynamic path searching and B-spline-based optimization to generate high-quality trajectories within a few milliseconds. Fully autonomous flights and aggressive human chasing are demonstrated in our video. [Paper] [Video] [Code] [IEEE Spectrum]

gif image: ral19

I work with Fei Gao to develop a complete and robust system called Teach-Repeat-Replan that is competent for autonomous drone race, infrastructure inspection, aerial transportation, and search-and-rescue tasks. The associated paper has been accepted by T-RO. [Paper] [Video] [Code]

gif image: trofei20