Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
CV
CV of Ching-Hsiang (Andrew) Huang: robot learning, computer vision and geospatial ML research at the University of Michigan, ITRI and Purdue.
Posts
Welcome
Published:
Welcome to my first post. Just set up the website yesterdary, still figuring things out.
portfolio
Senior Design - Lane Wizard
Lane Wizard is an autonomous vehicle prototype
Forest Biomass Mapping
Mapping above-ground forest biomass across Michigan at 10 m from GEDI lidar, Sentinel-2 and AlphaEarth embeddings
CPU Design
Multicore RISC-V CPU: from a 5-stage pipeline to cached, cache-coherent dual-core designs on an FPGA
GeoVision - Traffic Violation Detection
Detecting red-light runs, rolling stops and near-collisions from a single traffic camera with YOLO12, ByteTrack and ground-plane homography
ITRI Internship - Quadruped Vision Locomotion
A depth-based reinforcement-learning locomotion policy for the Unitree Go2 that climbs stairs, jumps onto boxes, leaps gaps and crosses narrow beams, taken from Isaac Gym to Gazebo to the real robot
RaceGAN
A Racing Dataset and Baseline Model for Track Detection in Autonomous Racing
Weighted Branch Aggregation CNN
Weighted branch aggregation based deep learning model for track detection in autonomous racing
publications
Weighted Branch Aggregation Based Deep Learning Model for Track Detection in Autonomous Racing
Published in The Second Tiny Papers Track at ICLR 2024, 2024
WeBACNN, a lightweight CNN that detects the race track in real time without relying on lane markings, running 47× faster than YOLOv8 with 65% fewer parameters.
Recommended citation: Ghosh, S., Chen, Y. H., Huang, C. H., Jameel, A. S. M. M., El Gamal, A., & Labi, S. (2024). "Weighted branch aggregation based deep learning model for track detection in autonomous racing." The Second Tiny Papers Track at ICLR 2024.
Download Paper
A Racing Dataset and Baseline Model for Track Detection in Autonomous Racing
Published in arXiv preprint arXiv:2502.14068, 2025
RoRaTrack, a multi-camera road-racing dataset with pixel-level track annotations, and RaceGAN, a GAN baseline that outperforms eight state-of-the-art models on it.
Recommended citation: Ghosh, S., Chen, Y. H., Huang, C. H., Jameel, A. S. M. M., Ho, C. C., El Gamal, A., & Labi, S. (2025). "A Racing Dataset and Baseline Model for Track Detection in Autonomous Racing." arXiv preprint arXiv:2502.14068.
Download Paper
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.