I am a Computer Science and Mathematics student at Arizona State University (ASU), passionate about Robotics, Autonomous Systems, and Artificial Intelligence. Originally from Vietnam, I am now based in Arizona, working on interdisciplinary research and hands-on projects at the intersection of machine learning, control systems, and computer vision.
🎸 Fun fact: I also play a mean guitar!
- Developed face detection and recognition pipelines using PyTorch and TensorFlow.
- At LAB V2, fine-tuned Vision Transformer models for multi-label classification.
- Integrated explainable rules to correct model predictions, improving accuracy by ~5%.
- During an internship in Germany, built a binary classifier for traffic accident detection in videos.
- Achieved 0.7 F1 score and developed a protocol for collecting data in critical scenarios.
- Contributing to the Duckiebot project using:
- Object detection, PID control
- Implemented both simulation and real-world testing to follow traffic rules autonomously.
- Experimented with:
- Imitation Learning (BC, BC-RNN)
- Offline RL (TD3-BC, IQL)
- Applied these techniques to real-world robot lane-following tasks in the Duckiebot system.
Programming Languages: Python, C++, MATLAB, R, Java, Shell Script
Systems & Tools: Linux, ROS, Docker
ML/DL Frameworks: PyTorch, TensorFlow, Scikit-learn, Ray, OpenCV, Pandas
Deep Learning Models: ResNet, DenseNet, EfficientNet, ViTs
Object Detection: YOLOv3/v4/v5
Special Topics: Logic Tensor Networks (Neuro-symbolic AI)
-
[C.1] Kricheli J. S., Vo K., et al.
"Error Detection and Constraint Recovery in Hierarchical Multi-Label Classification."
In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (CIKM), Oct. 2024. -
[C.2] Zhang Y., Vo K., et al.
"Poster Abstract: Reproducible and Low-cost Sim-to-real Environment for Traffic Signal Control."
In Proceedings of the 14th ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS), Apr. 2025. -
[C.3] Turnau J., Da L., Vo K., et al.
"Joint-Local Grounded Action Transformation for Sim-to-Real Transfer in Multi-Agent Traffic Control."
In RLC 2025.
- Traffic Accident Projects: GitHub Repo
- LAB V2 Research: Meta-Cognitive Error Detection
- Duckiebot Autonomous Driving: Duckiebot Project
- Connecting with researchers and builders in AI, robotics, and autonomy.
- Collaborating on applied machine learning and robotics challenges.
- Learning continuously to push the boundary between theory and practice.
- Email: ngocbach@asu.edu
- LinkedIn: Ngoc Bach Khoa Vo
Credit to Joykishan Sharma for original README template inspiration.