Junting Chen 陈俊廷

Junting Chen 陈俊廷

Master’s student in Robotics and AI

ETH Zurich

Biography

This is Junting Chen, currently a student researcher at Shanghai Artificial Intelligence Lab in Embodied AI and robotic systems. I did my master’s degree in Robotics and Artificial Intelligence at ETH Zurich, with Prof. Luc Van Gool as master’s program tutor. At ETH Zurich, I worked with Dr. Suryansh Kumar and Dr. Guohao Li at CVL. Before that, I earned my BSc in Computer Science at the University of Chinese Academy of Sciences. I did my bachelor’s thesis and first research internship with Prof. Ruiping Wang, at VIPL, Institute of Computing Technology, Chinese Academy of Sciences.

My current research interest is the gap between the perception and action in indoor-scene Embodied AI: 1) How to construct a unified scene representation during active exploration that supports multiple high-level embodied tasks. 2) How to make long-term decisions and predict instant actions conditioned on different intentions by leveraging the information in the scene representation and common sense knowledge.

My long-term goal is to develop a general intelligent robotic system, which interacts with the scene and humans based on hierarchical information processing capability:

  1. Common-sense knowledge from the structured knowledge base or unstructured text corpus. (Lifespan +++; information density +++; reliability +.)
  2. Global scene representation that maintains the geometric and semantic information of the current environment. (Lifespan ++; information density ++; reliability ++.)
  3. Instant sensor input (RGBD camera, Lidar, etc.) that provides instant information in the dynamic environment. (Lifespan +; information density +; reliability +++.)

Download my resumé .

Interests
  • Embodied AI & LLM
  • Robot Perception
  • Scene Understanding
  • RL for Robot Control
Education
  • MSc in Robotics, 2020-2023

    ETH Zurich

  • BSc in Computer Science, 2015-2019

    University of Chinese Academy of Sciences

Experience

 
 
 
 
 
Institute of Computing Technology, Chinese Academy of Sciences
Research Assistant
September 2019 – May 2020 Beijing, China

Projects include:

  • Implemented visual navigation system on Segway Loomo robot
  • Worked on Robothor 2020 challenge held on CVPR
 
 
 
 
 
ANYbotics
Perception Engineer
January 2023 – June 2023 Zurich, Switzerland
  • 50 % Algorithm: Improved perception for stair climbing and dynamicity detection on CPU.
  • 50 % DevOps: Sensor/Robot testing; Issue tracking; Push for perception models on Jetson.
 
 
 
 
 
Shanghai AI Laboratory
Intern Researcher
July 2023 – Present Shanghai, China
  • Worked on the research projects about LLM Code generation for robot manipulation
  • Worked on LLM multi-agent system for embodied agents

Selected Publications

RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis
RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis
RoboScript: Code Generation for Free-Form Manipulation Tasks across Real and Simulation
RoboScript: Code Generation for Free-Form Manipulation Tasks across Real and Simulation

Projects

*
Visual Object Navigation on Loomo robot
Framework to train visual navigation models in virtual environment and deploy model onto Loomo robot
Visual Object Navigation on Loomo robot