I am a computer vision engineer with 5 years of experience in vision-based deep learning for real-world robotic manipulation and autonomous machine operation. I specialize in developing novel techniques for complex robotic manipulation and real-time object detection in dynamic environments.

I completed my MSc in Computer Science from the University of Toronto (2018-2020), where I researched machine learning with applications in computational genomics. From 2020 to 2022, I worked at DeepX, Inc., developing vision-based deep learning for scene comprehension in complex environments. Currently, at Sony Research since 2022, I focus on vision-based deep learning for deformable object manipulation.

My general interests include:

  • 2D/3D Object Recognition: Enabling machines to accurately identify and localize objects in their environment.
  • 6-DoF Pose Estimation: Determining an object's precise position and orientation in 3D space.
  • Vision-Based Deep Learning for Robotics: Developing intelligent vision systems that allow robots to perceive and interact with the real world.
  • Vision-Language Models: Exploring the powerful synergy between visual perception and natural language understanding.

Contact

github; google scholar

academic:

rachelchan [at] cs [dot] toronto [dot] edu

personal:

rcwzychan [at] gmail [dot] com