Computer Vision and Interactive Technology (CVIT)
Research Field
Prof. Chih-Yang Lin is a professor in the Department of Mechanical Engineering at National Central University in Taoyuan, Taiwan. He is recognized as an IET Fellow and IEEE Senior Member. With a wealth of experience, he has authored or co-authored over 200 papers in highly-cited international conferences and journals, and has received numerous Best Paper Awards from renowned international conferences. In addition to his research pursuits, Dr. Lin has also played an active role in the academic community as a session chair, publication chair, and organizer for various international conferences. His research interests include computer vision, machine learning, deep learning, image processing, big data analysis, and robotics.
Our lab is at the cutting edge of computer vision technology, harnessing the power of machine learning and deep learning to unlock mysteries and create systems that see beyond human capabilities. We're not just following the trends—we're setting them, with research that spans the spectrum from theoretical underpinnings to tangible, industry-altering applications.
https://cvitlab.me/
Real-world applications in machine learning, AI robots, robot arms, deep learning, computer vision, generative AI, and signal processing
https://cvitlab.me/
Who We're Looking For
Python Proficiency: You should have a solid foundation in Python programming, the lingua franca of modern computing.
Machine Learning & Deep Learning Savvy: A strong background in machine learning and deep learning is essential, as these are the core of our research efforts.
Language Skills: Excellent command of English is required for collaborative research and contributing to the global scientific dialogue.
Educational Background: Master or PhD students, especially those with a track record of academic excellence in related fields.
Job Description
Robotics:
a. Our goal is to develop a small vision-language-action (VLA) model to help a robotic arm break down complex instructions into smaller, logical steps. Our goal is to add better task planning without making the model too heavy for edge devices.
b. Developing simple world models so the system can predict what will happen in its environment. This lets the model plan ahead internally while still running smoothly on low-power hardware
Agriculture:
The current general approach in self-learning, where we minimise the human manual effort needed (manual labelling, etc.)
What we aim to do is to find a new self-learning method outside of the general student-teacher method.
UAV:
The current focus for the drone is implementing obstacle avoidance and Vision-Language-Action (VLA) integration on an autonomous drone system.
What we want to aim for is to simulate and implement obstacle avoidance that is sustainable for the drone in the unknown environment.
Project Outcomes: Completion of research reports will be submitted to international conferences or academic journals.
Preferred Intern Educational Level
Preferred Intern Educational Level: i) Master's graduate students are preferred and first considered, next are doctoral graduates, and then the senior undergraduates. Be noted that junior undergraduates and younger individuals won’t be considered. ii) Major in CS, EE, or Mechanical Engineering.
Skill sets or Qualities
Deep Learning, Machine Learning, Computer Vision, Robotics
Job Description
Robotics:
a. Our goal is to develop a small vision-language-action (VLA) model to help a robotic arm break down complex instructions into smaller, logical steps. Our goal is to add better task planning without making the model too heavy for edge devices.
b. Developing simple world models so the system can predict what will happen in its environment. This lets the model plan ahead internally while still running smoothly on low-power hardware
Agriculture:
The current general approach in self-learning, where we minimise the human manual effort needed (manual labelling, etc.)
What we aim to do is to find a new self-learning method outside of the general student-teacher method.
UAV:
The current focus for the drone is implementing obstacle avoidance and Vision-Language-Action (VLA) integration on an autonomous drone system.
What we want to aim for is to simulate and implement obstacle avoidance that is sustainable for the drone in the unknown environment.
Project Outcomes: Completion of research reports will be submitted to international conferences or academic journals.
Preferred Intern Educational Level
Preferred Intern Educational Level: i) Master's graduate students are preferred and first considered, next are doctoral graduates, and then the senior undergraduates. Be noted that junior undergraduates and younger individuals won’t be considered. ii) Major in CS, EE, or Mechanical Engineering.
Skill sets or Qualities
Deep Learning, Machine Learning, Computer Vision, Robotics