Computer Vision Engineer & Robotics Expert passionate about building intelligent autonomous systems that bridge the gap between cutting-edge AI research and real-world applications. Currently developing production-grade perception systems for autonomous applications at AIRUCA INC. in Tokyo.
- 🏢 Current Role: CV/AI Engineer at AIRUCA INC., specializing in real-time perception systems and edge AI deployment
- 🌍 Location: Tokyo, Japan
- 🎓 Education:
- MSc. Advanced Robotics (JEMARO Program) - Keio University & Warsaw University of Technology
- MSc. Navigation, Guidance & Control - Nanjing University of Aeronautics and Astronautics
- 🏆 Recognition: Erasmus Mundus & Chinese Government Scholarship recipient, Top 2% graduate
- 🤖 Autonomous Systems: Multi-modal object detection, tracking, and semantic segmentation for robotics applications
- 🔍 Computer Vision: Real-time perception systems, 3D reconstruction, pose estimation, and thermal imaging
- ⚡ Edge AI: Model optimization with CUDA/TensorRT for deployment on resource-constrained hardware
- 🚁 Robotics Integration: ROS 2, sensor fusion, SLAM, and hardware-software integration for autonomous platforms
- 🏗️ Production Systems: Built and deployed real-time perception systems for surveillance and security applications
- 🚗 Autonomous Vehicles: Developed multi-camera tracking and 3D reconstruction systems for infrastructure analysis
- 🌡️ Research Innovation: Advanced thermal imaging-based human activity recognition and fall detection systems
- 🔧 Hardware Integration: End-to-end system development from embedded sensors to cloud deployment
- 🎮 Edge Optimization: Successfully optimized deep learning models for Raspberry Pi and edge device deployment
Note: Many of my recent projects involve proprietary work and cannot be shared publicly. The repositories here represent my academic and personal exploration work.
- 🤖 Multi-Robot Coordination: SLAM and autonomous navigation systems using ROS
- 🦾 Manipulator Control: 6-DOF robotic arm with advanced kinematics and trajectory planning
- 🚐 Mobile Robotics: Complete autonomous mobile robot development with ROS 2 and micro-ROS integration
- 🔥 Computer Vision: Object detection, tracking, and real-time video processing applications
- Multi-Modal Perception: LiDAR + Vision + Radar sensor fusion for autonomous systems
- Edge AI Optimization: Advanced model compression and deployment techniques
- 3D Scene Understanding: Semantic segmentation and spatial reasoning for robotics
- Production MLOps: Robust deployment pipelines for computer vision systems
I'm always interested in discussing:
- 🤖 Autonomous robotics and perception systems
- 👁️ Computer vision applications and optimization
- 🚀 Startup opportunities in AI/Robotics
- 🌍 Real-world AI deployment challenges
"The best way to predict the future is to invent it." – Alan Kay