Projects and Experiences

Developed GNSS-denied UAV navigation systems with a focus on visual SLAM algorithms.

Designed and implemented embedded systems for UAVs using Pixhawk flight controllers.

Engineered UAV hardware, including mechanical structure and power systems.

Designed and optimized control systems for UAV tracking gimbals.

Website

Won 3rd place out of 20 teams in the competition

Developed resilient communication system using the combination of customized Wi-Fi device TVL and Xbee; achieved stable communication between WAM-V and shoreside base station for situation awareness purpose.

Integrated lidar and camera to get the precise depth of the desired object in the bounding box with Python and ROS, and is used in docking, find and fling, entrance and exit, scan the code mission.

In charge of WAM-V-related missions; responsible for heartbeat and design of find and fling system

Head of Control & Communication system, responsible to all propulsion and communication system on board, including cracking Torqeedo motor RS485 protocol.

Paper Website News

Implemented HRVO algorithm to multiple USV, prevent multiple USV from colliding to each other during doing search and rescue mission in same area.

Applied resilient communication system to USV, let USV can switch to decentralized mode when facing signal interference.

Design and assemble light weight solar USV- Solar Duckieboat , which can survive by itself for about 3 month by the lake, and has remote control and monitor availability at the same time.

Ongoing project – sending second version Solar Duckieboat to Suao port and control it by VR device from Hsinchu.

Video

Tied for fifth place among more than a hundred teams.

Using Autodesk Inventor to design whole robot mechanism, manufacturing robot parts by laser cutting or light-cured 3D printing and assemble the robot.

Using Eagle Autodesk to design circuit and PCB layout, we used stm32 chip to be our main microcontroller.

Implemented closed loop control to do precise robot localization within 2m*1m competition space.

Report News

Won 24th place among more than a hundred teams.

Using Autodesk Inventor to design whole robot mechanism, manufacturing robot parts by laser cutting or light-cured 3D printing and assemble the robot.

Using Eagle Autodesk to design circuit and PCB layout, we used stm32 chip to be our main microcontroller.

Implemented closed loop control to do precise robot localization within 2m*1m competition space.

News

Duckiepond 2.0 extends the education and research environment Duckiepond, including an accessible “Duckieboat” platform and simulation environments (Gazebo and Unity).

Website

I audit Marine Autonomy, Sensing and Communications(MOOS-IvP) course given by MIT, the course focus mainly on software and algorithms for autonomous decision making by vehicles operating in the ocean environments. We accomplish the final project of the course at Bamboo Lake, Taiwan. Executing multi-vehicles waypoints navigation by MOOS using Duckieboats which are developed by our laboratory.

I am responsible for the communication between multi-vehicles and base station.

Course Website