Zuxin Liu

Ph.D. Student, College of Engineering, Carnegie Mellon University.

M.S. Student, Machine Learning Department, Carnegie Mellon University.

Contact: zuxinl AT andrew DOT cmu DOT edu

Github / Google Scholar / LinkedIn

I am a third-year Ph.D. candidate at the Safe AI Lab, advised by Prof. Ding Zhao. I am also fortunate to be co-advised by Prof. Bo Li at UIUC and Prof. Steven Wu at CMU. Before that, I finished my bachelor's degree from Beihang University in June, 2019. I also spent a great time in visiting Technische Universität Darmstadt during 2018 winter, where I got my first exposure to robot learning from Prof. Jan Peters.

My research interests include reinforcement learning, imitation learning, robotics, and autonomous vehicle. Particularly, I am interested in how to safely and robustly deploy learning-based decision-making algorithms to real-world safety-critical applications.

Amazon Lab126. Applied Scientist Intern. 2022 Summer.

Nuro, Inc. Machine Learning Research Intern. Host: Dr. Wei Liu, 2021 Summer.

Dajiang Innovations (DJI) Technology Co., Ltd. Algorithm Engineer Intern, 2017 Summer.

On the Robustness of Safe Reinforcement Learning under Observational Perturbations

Zuxin Liu, Zijian Guo, Zhepeng Cen, Huan Zhang, Jie Tan, Bo Li and Ding Zhao.
Under review.

[arXiv] [website]

Constrained Variational Policy Optimization for Safe Reinforcement Learning

Zuxin Liu, Zhepeng Cen, Vladislav Isenbaev, Wei Liu, Steven Wu, Bo Li and Ding Zhao.
2022 ICML.

[arXiv] [code]

Investigating the Impact of Multi-LiDAR Placement on Object Detection for Autonomous Driving

Hanjiang Hu*, Zuxin Liu*, Sharad Chitlangia, Akhil Agnihotri and Ding Zhao.
2022 CVPR.

[arXiv] [code]

Constrained Model-based Reinforcement Learning with Robust Cross-Entropy Method

Zuxin Liu, Hongyi Zhou, Baiming Chen, Sicheng Zhong, Martial Hebert and Ding Zhao.
2021 ICLR Workshop on Security and Safety in Machine Learning Systems.

[arXiv] [code]

Context-Aware Safe Reinforcement Learning in Non-Stationary Environments

Baiming Chen, Zuxin Liu, Jiacheng Zhu, Mengdi Xu, Wenhao Ding and Ding Zhao.
IEEE International Conference on Robotics and Automation (ICRA) 2021, Xi'an.

[arXiv] [code]

MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments

Zuxin Liu, Baiming Chen, Hongyi Zhou, Guru Koushik, Martial Hebert and Ding Zhao.
IEEE International Conference on Intelligent Robots and Systems (IROS) 2020, Las Vegas.


Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes

Mengdi Xu, Wenhao Ding, Jiacheng Zhu, Zuxin Liu, Baiming Chen and Ding Zhao
2020 NeurIPS.

[arXiv] [code]

Delay-Aware Multi-Agent Reinforcement Learning

Baiming Chen, Mengdi Xu, Zuxin Liu, and Ding Zhao.
Under review.

[arXiv] [code]

SAnE: Smart Annotation and Evaluation tools for point cloud data

Hasan Arief, Mansur Arief, Guilin Zhang, Zuxin Liu, Manoj Bhat, and Ding Zhao
IEEE Access.

[arXiv] [code]

Where Should We Place LiDARs on the Autonomous Vehicle? - An Optimal Design Approach

Zuxin Liu, Mansur Arief and Ding Zhao
IEEE International Conference on Robotics and Automation (ICRA) 2019, Montreal.

[arXiv] [code]

DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments

Chao Yu, Zuxin Liu and Fei Qiao
IEEE International Conference on Intelligent Robots and Systems (IROS) 2018, Madrid

[arXiv] [code]

Robot’s Eyes and Brain: Visual Semantic SLAM System, 2018

We developed a visual semantic SLAM system based on orb-slam2 and Mask-RCNN. The robot can build a semantic map for the environment and remember each object's position. With a speech recognition module, we can use voice command to let the robot find a particular object if he has seen before. This project won the first prize in the 2018 International Conference on Optics and Photonics(ICOPEN) 3-D Sensor Application Design Competition (1 out of 20 teams around the world)


VR Multicopter System, 2017

Do you want to fly? Our VR-Multicopter system can help you to experience the feeling of fly. We use a VR device to control orientation of a gimbal that mounted on our multicopter. The stereo camera on the gimbal will send videos back to our VR equipment in real-time. Just move your head and enjoy the view from sky! This project won the first prize in the 2017 International Design and Innovation Competition (1 out of 14 teams around the world)


Autonomous Navigation Robot, 2017

I led a team to build a mobile robot platform which could achieve autonomous navigation and obstacle avoidance based on RTAB-Map SLAM and ROS Navigation Stack. Just with one-click, the robot can autonomously navigate to wherever you want.


Automatic AI Robot System, 2017

This project is designed for ICRA DJI Robotmaster AI challenge. The robots are required to autonomously find enemy robots and hit them (shoot rubber ball). More exciting information and videos about this robot platform and the relevant robot competition can be found here.

Arduino-based Interactive Facial Expression Robot, 2016

This cute robot could make different expressions according to user’s voice command. The movements of its eyes, eyebrow, and mouth etc are fully controlled by servo motors. Most of the materials are 3D printed.

[2016&2017&2018] National Scholarship (top 1%), Ministry of Education of the People's Republic of China

[2016&2017&2018] University-level Outstanding Student, Beihang University

[2018] ShenYuan Medal Award (10/4000), Beihang University

[2018] Beijing Outstanding Student, Ministry of Education of Beijing

[2018] 28th First prize of the Feng Ru Cup Competition of Academic and Technological Works (top1%), Beihang University

[2017] Dean's Award, Beihang University

Updated on April 08st, 2020

      Zuxin Liu© 2019-2020