Ziang Liu

Ziang Liu

Graduate Student

Stanford University

Biography

I am a MS student in Computer Science at Stanford University advised by Professor Jiajun Wu. During my undergraduate study, I was fortunate to have worked with Professors Gaurav Sukhatme, Stefanos Nikolaidis, and Sven Koenig. My previous research work focuses on motion planning for robot arm and multi-agent systems, and robot perception with LiDAR.

My goal is to build robots that perceive, understand, reason, and interact in the physical world to better assist people with day-to-day tasks, leveraing inspiration from human cognition. Currently I am actively exploring research directions in robot learning and computer vision.

I am honored to be nominated by Stanford CS and appointed as a Siebel Scholar for 2023!

I am actively applying for a PhD position for Fall 2023.

Interests

  • Robot Learning
  • Robot Manipulation
  • Deep Reinforcement Learning
  • Human-Robot Interaction
  • Computer Vision
  • Cognitive Science
  • Motion Planning
  • 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

Recent News

Selected Publications

Inferring Articulated Rigid Body Dynamics from RGBD Video

Being able to reproduce physical phenomena ranging from light interaction to contact mechanics, simulators are becoming increasingly …
PDF Website
Inferring Articulated Rigid Body Dynamics from RGBD Video

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 …
PDF Video
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 …
PDF
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 Experience

 
 
 
 
 

Research Assistant

Assistive Robotics and Manipulation Lab (ARM)

May 2022 – Sep 2022 Stanford University

Advised by

Projects

  • Human-Robot Collaborative Carrying

More Details

 
 
 
 
 

Research Assistant

Stanford Vision and Learning Lab (SVL)

Aug 2021 – Present Stanford University

Advised by

Projects

  • Adaptive Scene Representations for Manipulation
  • Learning to Design and Use Tools for Goal-Conditioned Manipulation
  • Simulator-Agnostic Task Description

More Details

 
 
 
 
 

Research Assistant

Dynamic Robotics and Control Laboratory

Oct 2020 – Mar 2021 University of Southern California

Advised by

Projects

  • Autonomous Car Drifting

More Details

 
 
 
 
 

Research Assistant

Interactive and Collaborative Autonomous Robotics Lab (ICAROS)

Jun 2020 – Jul 2021 University of Southern California

Advised by

Projects

  • Cost-Based RRT for Robot Lime Picking

More Details

 
 
 
 
 

Research Assistant

IDM Artificial Intelligence Laboratory

Jun 2020 – May 2021 University of Southern California

Advised by

Projects

  • Hierarchical Multi-Agent Path Finding

More Details

 
 
 
 
 

Research Assistant

Robotic Embedded Systems Laboratory (RESL)

Jan 2019 – Dec 2021 University of Southern California

Advised by

Projects

  • Rigid Body Dynamics Inference from RGBD Video
  • Task and Contact Optimization
  • Physics-Based LIDAR Simulation
  • Motion Planner Benchmark

More Details

Teaching

 
 
 
 
 

Graduate TA

CS 231A - Computer Vision, From 3D Reconstruction to Recognition

Jan 2023 – Present Stanford University
With Professors Silvio Savarese and Jeannette Bohg (Winter 2023)
 
 
 
 
 

Graduate TA

CS 229 - Machine Learning

Mar 2022 – Jun 2022 Stanford University
With Professors Tengyu Ma and Chris Re (Spring 2022)
 
 
 
 
 

Head TA

CS 161 - Design and Analysis of Algorithms

Jan 2022 – Mar 2022 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, Fall 2022)
With Ian Tullis (Summer 2022)
 
 
 
 
 

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)

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

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.