Lei Tai (邰磊)

PhD candidate
Robotics Institute,
Department of Electronic and Computer Engineering,
The Hong Kong University of Science and Technology

Email: ltai AT ust DOT hk

About Me

I am a fifth-year PhD candidate in RAM Lab, The Hong Kong University of Science and Technology(HKUST), supervised by Ming Liu. I received the B.S.(2012) and the M.S.(2014) in Engineering from Harbin Institute of Technology(HIT). In the last year of the undergraduate, I joined the ABU Robocon as a team member of HIT Competitive Robot Team. Since then, I started my robotics work. In 2017, I was a visiting researcher in AIS, University of Freiburg, working with Wolfram Burgard and Joschka Boedecker. I was also with City University of Hong Kong from Sep 2015 to Aug 2017 which is another long story...

Google Scholar  /  Github  /  CV  /  LinkedIn

Research

My research interests mainly include deep reinforcement learning and learning from demonstrations on mobile robots. I have also worked in exploration of reinforcement learning, 3D perception for autonomous driving and human gaze in imitation learning. Representative works are highlighted.

End-to-end Driving Deploying through Uncertainty-Aware Imitation Learning and Stochastic Visual Domain Adaptation.
IROS, 2019

Lei Tai, Peng Yun, Yuying Chen, Congcong Liu, Haoyang Ye, Ming Liu
arXiv / bibtex / video / code
Gaze Training by Modulated Dropout Improves Imitation Learning.
IROS, 2019
Utilizing Eye Gaze to Enhance the Generalization of Imitation Network to Unseen Environments.
ICML workshop, 2019

Yuying Chen*, Congcong Liu*, Lei Tai, Ming Liu, Bertram Shi
arXiv / bibtex
A Gaze Model Improves Autonomous Driving.
ETRA, 2019 (acceptance rate 37.9%)

Congcong Liu*, Yuying Chen*, Lei Tai, Haoyang Ye, Ming Liu, Bertram Shi
page / bibtex / video
Focal Loss in 3D Object Detection.
IEEE Robotics and Automation Letters (RA-L), 2019
ICRA, 2019

Peng Yun, Lei Tai, Yuan Wang, Chengju Liu, Ming Liu
pdf / bibtex / page / code
VR-Goggles for Robots: Real-to-sim Domain Adaptation for Visual Control.
IEEE Robotics and Automation Letters (RA-L), 2019

Jingwei Zhang*, Lei Tai*, Peng Yun, Yufeng Xiong, Ming Liu, Joschka Boedecker, Wolfram Burgard
(*indicates equal contribution)
pdf / bibtex / supplement / page / video
Curiosity-driven Exploration for Mapless Navigation with Deep Reinforcement Learning.
ICRA workshop, 2018

Oleksii Zhelo, Jingwei Zhang, Lei Tai, Ming Liu, Wolfram Burgard
pdf / bibtex / page / video
A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation.
arXiv 1612.07139

Lei Tai*, Jingwei Zhang*, Ming Liu, Joschka Boedecker, Wolfram Burgard
(*indicates equal contribution)
arXiv / bibtex
Socially Compliant Navigation through Raw Depth Inputs with Generative Adversarial Imitation Learning.
ICRA, 2018

Lei Tai, Jingwei Zhang, Ming Liu, Wolfram Burgard
pdf / bibtex / dataset / video
Neural SLAM: Learning to Explore with External Memory.
arXiv 1706.09520

Jingwei Zhang, Lei Tai, Joschka Boedecker, Wolfram Burgard, Ming Liu
arXiv / bibtex / video
Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigation.
IROS, 2017

Lei Tai, Giuseppe Paolo, Ming Liu,
pdf / bibtex / video
Towards Cognitive Exploration through Deep Reinforcement Learning for Mobile Robots.
arXiv 1610.01733

Lei Tai, Ming Liu
arXiv / bibtex
PCA-aided Fully Convolutional Networks for Semantic Segmentation of Multi-channel fMRI.
International Conference on Advanced Robotics, 2017 (best student paper award)

Lei Tai, Ming Liu
pdf / bibtex
A Robot Exploration Strategy Based on Q-learning Network.
IEEE International Conference on Real-time Computing and Robotics(RCAR), 2016
Mobile robots exploration through cnn-based reinforcement learning.
Robotics and Biomimetics, 2016

Lei Tai, Ming Liu
pdf / bibtex
A Deep-network Solution Towards Model-less Obstacle Avoidance.
IROS, 2016
Autonomous exploration of mobile robots through deep neural networks.
International Journal of Advanced Robotic Systems(IJARS), 2017

Lei Tai, Shaohua Li, Ming Liu
pdf / bibtex / dataset
Service
Journal Reviewer for AURO, IEEE Trans-NNLS, IJARS and IEEE RA-L.

Conference Reviewer for ICRA 2017-19, IROS 2016-19 and NeurIPS 2019 Workshop.
Misc

Complete Oxfam Trailwalker 100km in 34 hours 30 mins.

Master thesis which is nothing to do with robotics.

ABU Robocon 2012 and 2013.

page template