Ziang Liu

Ziang Liu

Graduate Student

Stanford University

Biography

I am a first year MS student in Computer Science at Stanford University. My previous research work focuses on motion planning for robot arm and multi-agent systems, and robot perception with LiDAR. Currently I am actively exploring new fields including robot learning and vision. I am actively applying for a PhD position. I’m crazy about skiing, birding, and travelling.

Interests

  • Robotics
  • Artificial Intelligence
  • Motion Planning
  • Reinforcement Learning
  • Human-Robot Interaction
  • Legged Locomotion

Education

  • MS in Computer Science, 2023 (Expected)

    Stanford University

  • BS in Computer Science, 2021

    University of Southern California

  • BS in Applied and Computational Mathematics, 2021

    University of Southern California

Research Experience

 
 
 
 
 

Research Assistant

Dynamic Robotics and Control Laboratory

Oct 2020 – Mar 2021 University of Southern California
Advised by Dr. Guillaume Bellegarda and Professor Quan Nguyen
 
 
 
 
 

Research Assistant

Interactive and Collaborative Autonomous Robotics Lab (ICAROS)

Jun 2020 – Jul 2021 University of Southern California
Advised by Heramb Nemlekar and Professor Stefanos Nikolaidis
 
 
 
 
 

Research Assistant

IDM Artificial Intelligence Laboratory

Jun 2020 – May 2021 University of Southern California
Advised by Han Zhang and Professor Sven Koenig
 
 
 
 
 

Research Assistant

Robotic Embedded Systems Laboratory (RESL)

Jan 2019 – Present University of Southern California
Advised by Eric Heiden and Professor Gaurav Sukhatme

Selected Publications

Robotic Lime Picking by Considering Leaves as Permeable Obstacles

The problem of robotic lime picking is challeng- ing; lime plants have dense foliage which makes it difficult for a robotic arm to …
Robotic Lime Picking by Considering Leaves as Permeable Obstacles

A Hierarchical Approach to Multi-Agent Path Finding

We propose a hierarchical framework for solving the Multi-Agent Path Finding (MAPF) problem. We spatially divide a large map instance …
A Hierarchical Approach to Multi-Agent Path Finding

Physics-based Simulation of Continuous-Wave LIDAR for Localization, Calibration and Tracking

Light Detection and Ranging (LIDAR) sensors play an important role in the perception stack of autonomous robots, supplying mapping and …
PDF Video
Physics-based Simulation of Continuous-Wave LIDAR for Localization, Calibration and Tracking

Research Projects

.js-id-Project
All Motion Planning LiDAR Control and Optimization

Autonomous Car Drifting

Optimize car trajectory in constrained time frame using dynamic/kinematic limits and collision as constraints for non-linear optimization problem. Localize with LiDAR scan matching and feed estimated pose to MPC.

Inverse Rendering

Create realistic sensor model that enables optimization of sensor model parameters and reasoning about scene geometry.

Hiking

Because the moutain is there. I hiked Mt. San Gorgonio, Mt. San Jacinto, and Mt. San Antonio. I don’t have the best physical endurance to stay happy during the hike but I very much enjoy the summit.

Cost-Based APF-RRTs

Speed up RRT with artifical potential field while being able to escape local minima.

Photography

To discover, to capture, to share. I record the unseen world to keep the most beautiful memories.

Skiing

I miss the mountains, and hope that I’ll be back on the snow soon.

Hierarchical Multi-Agent Path Finding

Spatially divide large maps into sub-regions and find high-level paths to provide guidance to low-level ECBS solvers in each sub-region.

Birding

I am a twitcher who is crazy about birds. I love walking in the wilderness with a pair of binoculars looking for birds and wild animals. I have observed 937 species of birds in Asia, and have just started birding in the US (currently 94 species observed).

Piano

I started playing the piano when I was 10. Currently I’m practicing Liebestraum No. 3 by Liszt and Etude Op. 10 No. 3 by Chopin.

Task and Contact Optimization for Robot Manipulation

Formulate high-level symbolic planning as a smooth optimization problem and combine with low-level CIO framework to optimize over complex contact planning problems.

Physics-based LiDAR Simulation

Accurately model LiDAR sensor in a differentiable framework supporting gradient-based optimizations
PDF Video

Motion Planning Benchmark

Benchmark state-of-the-art motion planners and techniques for wheeled mobile robots to highlight their strengths and weaknesses.
PDF Website

External Project

An example of linking directly to an external project website using external_link.

Internal Project

An example of using the in-built project page.
Follow

Teaching

Undergraduate TA

 
 
 
 
 

Head TA

CS 161 - Design and Analysis of Algorithms

Jan 2022 – Present Stanford University
With Professors Moses Charikar and Nima Anari (Winter 2022)
 
 
 
 
 

Graduate TA

CS 161 - Design and Analysis of Algorithms

Sep 2021 – Dec 2021 Stanford University
With Professor Aviad Rubinstein (Fall 2021)
 
 
 
 
 

Undergraduate TA

CSCI 360 - Introductioin to Artificial Intelligence

Apr 2019 – Dec 2020 University of Southern California
With Professor Chao Wang (Spring 2020)
With Professor Mohammad Reza Rajati (Fall 2020)
 
 
 
 
 

Undergraduate TA

CSCI 270 - Introduction to Algorithms and Theory of Computing

Mar 2019 – Jul 2020 University of Southern California
With Professor Aaron Cote (Summer 2020)
 
 
 
 
 

Undergraduate TA

CSCI 170 - Discrete Methods in Computer Science

Feb 2019 – Dec 2020 University of Southern California
With Professor Michael Shindler (Spring 2019, Summer 2019)
With Professor Aaron Cote (Spring 2020, Fall 2020)
 
 
 
 
 

Undergraduate TA

CSCI 104 - Data Structures and Object Oriented Design

Jan 2019 – Dec 2019 University of Southern California
With Professor Aaron Cote (Fall 2019)

Hobbies

.js-id-Hobby

Autonomous Car Drifting

Optimize car trajectory in constrained time frame using dynamic/kinematic limits and collision as constraints for non-linear optimization problem. Localize with LiDAR scan matching and feed estimated pose to MPC.

Inverse Rendering

Create realistic sensor model that enables optimization of sensor model parameters and reasoning about scene geometry.

Hiking

Because the moutain is there. I hiked Mt. San Gorgonio, Mt. San Jacinto, and Mt. San Antonio. I don’t have the best physical endurance to stay happy during the hike but I very much enjoy the summit.

Cost-Based APF-RRTs

Speed up RRT with artifical potential field while being able to escape local minima.

Photography

To discover, to capture, to share. I record the unseen world to keep the most beautiful memories.

Skiing

I miss the mountains, and hope that I’ll be back on the snow soon.

Hierarchical Multi-Agent Path Finding

Spatially divide large maps into sub-regions and find high-level paths to provide guidance to low-level ECBS solvers in each sub-region.

Birding

I am a twitcher who is crazy about birds. I love walking in the wilderness with a pair of binoculars looking for birds and wild animals. I have observed 937 species of birds in Asia, and have just started birding in the US (currently 94 species observed).

Piano

I started playing the piano when I was 10. Currently I’m practicing Liebestraum No. 3 by Liszt and Etude Op. 10 No. 3 by Chopin.

Task and Contact Optimization for Robot Manipulation

Formulate high-level symbolic planning as a smooth optimization problem and combine with low-level CIO framework to optimize over complex contact planning problems.

Physics-based LiDAR Simulation

Accurately model LiDAR sensor in a differentiable framework supporting gradient-based optimizations

Motion Planning Benchmark

Benchmark state-of-the-art motion planners and techniques for wheeled mobile robots to highlight their strengths and weaknesses.

External Project

An example of linking directly to an external project website using external_link.

Internal Project

An example of using the in-built project page.