
Robotics & Embodied AI
I build and study learning-based robotic systems — from demonstrations and simulation to real-world deployment.
VLA · Robot Learning · Sim-to-Real · Robotic Manipulation
Research Assistant, City Science Lab @ Taipei Tech
Learning-based robotic systems, from data collection and simulation to real-world deployment.
Assisting in developing the VLA project for robotic arms, visual navigation systems on quadrupeds.
Assisted in developing an autonomous image recognition system, using data augmentation and model training to deploy custom image recognition models on edge devices.
More work from earlier in the robotics research trajectory above.
Research interests include Vision-Language-Action (VLA) models and mechanistic interpretability — studying the internal representations associated with successful and failed robot behaviors, and how they might be used to better understand or steer learned policies (Overall GPA: 4.0).
Study interests included image processing, data augmentation in computer vision, and robot navigation (Overall GPA: 3.72).
Feel free to reach out via email or connect on social media — I'm always open to discussing new projects, collaborations, or opportunities in robotics and AI.
闕楷宸|機器人學習、視覺語言動作模型與具身人工智慧研究