Loomo Project

Robot Vision Exploration Project

In this project, we achieved 3D real-time reconstruction in real situations, as well as multi-dimensional scene understanding using a scene graph and 3D semantic segmentation. A distributed, decentralized, and scalable module communication framework between the robot (i.e., Loomo) and functional modules (e.g., 3D Reconstruction, Scene Graph, etc.) has been built. We also implemented the function of dynamic display and analysis of each module’s results with the front end of the web page.

In the Robot Vision Exploration Project, I designed and maintained the customized communication framework that transfers data between the robot (e.g., LoCoBot or Loomo) and functional modules (e.g., 3D Reconstruction, Scene Graph, etc.) based on ROS. In this project, I learned practical robotic tools like PyRobot to control the robots, front-end/back-end web technology to build a demonstration website, and the ability to self-study and quickly assume responsibility in teamwork.

Fengyuan Yang
Fengyuan Yang
Final-year Ph.D. candidate in Computer Science

My research focuses on controllable video generation and human-centric 3D/4D vision, with broader interests in world modeling and its potential applications to embodied intelligence.

Related