• Jeonghwan Park / M.S. Candidate
  • 관리자 |
  • 2022-04-18 15:31:51|
  • 107
Jeonghwan Park

M.S. Candidate

I am currently a M.S. Candidate at Aerospace Engineering department at KAIST, under my advisor, prof. Jae-Hung Han. I’ve received a B.S. degree for mechanical engineering and set my career course towards classic mechanical engineering fields. However, attending some of the graduate courses triggered my interests in the robotics field, constituting of branches such as cognition and control. After deciding to change my direction in the career path, I’ve studied some core concepts in elementary robotics and conducted a research about stereo vision-based collision avoidance systems for UAVs, which was awarded prizes at the 2021 Aerospace Journal Award, held by Korea Aerospace Industries(KAI), and 2021 Student Conference, Held by American Institute of Aeronautics and Astronautics(AIAA). Recently, the field of numerical optimization, which enables description and solving of various robotics tasks, held my interests and I am currently working my way towards being a general robotics engineer.

About my research

Development of high-performance, low-cost Unmanned Aerial Vehicles paired with rapid progress in vision-based perception systems herald a new era of autonomous flight systems with mission-ready capabilities. However, modern autonomous systems are not yet fully capable of coping with dynamically changing environments, and one of the key features of a robust autonomous flight systems is a mid-air collision avoidance strategy. This work focuses on the design, implementation and examination of vision-based moving object detection and tracking system with decision-making capabilities for performing evasive maneuvers. In detail, the geometrical transformation of a 2-D image structure due to the movement of the camera is approximated as a 2-D Homography transform, and this approximation is utilized to detect independent moving objects in the scene, which are then tracked using a Kalman Filter-based tracking system. Risk assessment and decision-making for performing evasive maneuvers is performed with data from stereo camera-based depth estimation. Examination was performed with a quadrotor UAV equipped with this system, and the performance was comparable to state-of-the-art systems without any additional sensors.