About This Blog

This blog will serve as a platform for me to share:

1. Technical insights from my work on robot learning and VLA models
2. Tutorials on setting up and using various robotics tools
3. Project updates and progress reports
4. Research notes and findings

My Background

I am a third-year undergraduate student at Huazhong University of Science and Technology, where I lead the Dian Team’s robotics group. My research focuses on:

• Robot Learning: Imitation learning and reinforcement learning for robotic manipulation
• Vision-Language-Action Models: Fine-tuning and deploying VLA models for robot control
• Computer Vision: 3D perception and visual servoing

Current Projects

SO-101 Robot Arm System

I’ve been developing a comprehensive system for SO-101 dual-arm robot control. This includes:

• Teleoperation with real-time feedback
• Automated calibration procedures
• Data collection pipelines
• Policy training and deployment

LeRobot Framework

I contribute to HuggingFace’s LeRobot framework, which provides standardized tools for robot learning. My contributions include:

• Dataset management utilities
• Training pipeline improvements
• Deployment tools

VLA Model Fine-tuning

I’m working on tools for fine-tuning Vision-Language-Action models like SmolVLA for specific robotic tasks. This involves:

• Data preparation scripts
• Training infrastructure
• Evaluation frameworks

What to Expect

I plan to publish posts regularly, covering:

• Beginner tutorials for those new to robotics
• Advanced techniques for experienced practitioners
• Project walkthroughs with code examples
• Research discussions on emerging trends

Stay Connected

Feel free to:

• Subscribe to the RSS feed for updates
• Contact me with questions or suggestions
• Follow my GitHub repositories for code updates

Thank you for visiting, and I hope you find the content useful!

“The best way to predict the future is to create it.” - Peter Drucker