Home

Google Scholar link

Hank graduated with B.A. in Computer Science from University of California, San Diego (UCSD),and completed his M.S. in Computer Science from National Taiwan University (NTU).His research experience includes computer vision, robotics, and machine learning. During his year abroad in Japan he is fascinated by how charismatic robots social with humans, and thus he sought out researches in bio-inspired robotics.

His undergraduate experiences can be described as from Ocean to Outer Space. He has worked with biologists at Scripps Institute of Oceanography to build a automatic segmentation tools on coral reef, and also NTU with marine biologists to build an automatic plankton recognition system.

Later at NASA Jet Propulsion Laboratory he worked on building an Automated Target Recognition system for autonomous vehicles.

In his graduate study at NTU, he focused on Intelligent Transportation System for robotic autonomous driving.

The idea is to do Simultaneously Localization and Mapping together with Moving Object Tracking (SLAMMOT),

allowing the robot to navigate in real-world dynamic environment.

His research mainly is on detecting moving objects, such as pedestrians and cars, with only monocular/stereo camera.

His master thesis (ICRA 2014) was one of the pioneer work fusing deep learning and traditional robotics for learning spatial-temporal features.

Hank has been working on applied research in the industry., in various places like

Volkswagen Group of America, Electronics Research Lab, Uber Advances Technologies Group, and Lyft Level 5,

focusing on deep learning and robotics for real-world self-driving car.

NEWS

2020 - Paper accepted

H. Cui, T. Nguyen, F.-C. Chou, T.-H. Lin, J Schneider, D Bradley, N. Djuric,

“Deep Kinematic Models for Kinematically Feasible Vehicle Trajectory Predictions,”

in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA 2020).

2019 - Present.

Working at Lyft Level 5, self-driving car division.

2019 - Paper accepted

H. Cui, V. Radosavljevic, F.-C. Chou, T.-H. Lin, T. Nguyen, T.-K.Huang, J. Schneider, N. Djuric,

“Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks,”

in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA 2019).

2019 - Paper accepted

F.-C. Chou, T.-H. Lin, H. Cui, V. Radosavljevic, T. Nguyen, T.-K.Huang, M. Niedoba, J. Schneider, N. Djuric,

“Predicting Motion of Vulnerable Road Users using High-Definition Maps and Efficient ConvNets,”

Neurips workshop, 2018. (pdf)

2015 - 2019.

Working at Uber Advanced Technologies Group.

Had worked on end-to-end driving (sensor to control), and pioneered 'deep prediction', bringing deep network to motion predictions for pedestrian, vehicle.

2013 - 2015.

Working at Volkswagen ERL, bringing deep learning to autonomous self-driving car.

2014 - Master thesis Paper accepted

“Deep Learning of Spatio-Temporal Features with Geometric-based Moving Point Detection for Motion Segmentation,”

accepted for publication in IEEE International Conference on Robotics and Automation (ICRA), 2014

2013 - Graduated from National Taiwan University, M.S. Computer Science

- Projects Page updated with research result

2011 - On NASA USRP Student Stories Initiative

2010 - Paper accepted for publication,

Lin,T.H., Lu,T., Braun H., Edens W., Zhang, Y, Chao, T., Assad, C, and Huntsberger, T

" Optimization of a multi-stage ATR system for small target identification,"

Proceedings of SPIE Vol. 7696C, (2010)

2009 - FEATURE ARTICLE from my school!

UCSD Undergrad Tsung-Han 'Hank' Lin: From Oceans to Outer Space

By UC San Diego - California Institute for Telecommunications and Information Technology

[in pdf]

2009 - NASA Press Release Undergraduate Student Research Program

2009 - Appear on UCSD Computer Science Department Weekly News! (Click on the picture)