Yulun Zhang

Yulun Zhang

Ph.D. Student

Carnegie Mellon University

Biography

My name is Yulun Zhang (张宇伦). I am a second year Ph.D. student in Robotics Institute at the Carnegie Mellon University, advised by Professor Jiaoyang Li. Currently I am focusing on environment optimization for Multi-Agent Path Finding (MAPF) algorithms using Quality-Diversity (QD) optimization, evolutionary computation, and generative modeling methods.

Previously, I was a master/undergrad student majoring in Computer Science at the University of Southern California. I was working in ICAROS lab at USC with Professor Stefanos Nikolaidis and Matt Fontaine on surrogate assisted QD optimization and scenario generation for human-robot coordination. I was also working in RESL at USC with Dr. Ryan Julian and K.R. Zentner on transfer learning for robotics.

In addition, I was working in the USC Interaction Lab with Dr. Matt Rueben on socially assistive robotics as well as Professor William Halfond’s group on record and replay tools for Android.

Here is my most recent CV (updated Dec 2023).

I am also enthusiastic about photography, especially scenery photography. Check out my photography portfolio and instagram for some of my works.

Contact me: yulunzhang [at] cmu [dot] edu

Interests
  • Quality Diversity Optimization
  • Evolutionary Computation
  • Multi-Robot Coordination
  • Human-Robot Interaction
Education
  • Ph.D. in Robotics, 2022 - Present

    Carnegie Mellon University

  • MSc in Computer Science, 2020 - 2022

    University of Southern California

  • BSc in Computer Science, 2017 - 2021

    University of Southern California

Recent News

Publications

Quickly discover relevant content by filtering publications.
Guidance Graph Optimization for Lifelong Multi-Agent Path Finding. Preprint, 2024.
Scalable Mechanism Design for Multi-Agent Path Finding. Preprint, 2024.
Arbitrarily Scalable Environment Generators via Neural Cellular Automata. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), December 10–16, 2023, New Orleans, LA, USA, 2023.
Multi-Robot Coordination and Layout Design for Automated Warehousing. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), August 19–25, 2023, Macao, China, 2023.
pyribs: A Bare-Bones Python Library for Quality Diversity Optimization. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), July 15–19, 2023, Lisbon, Portugal, 2023.
Efficient Multi-Task Learning via Iterated Single-Task Transfer. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 23-27, 2022, Kyoto, Japan, 2022.
Deep Surrogate Assisted MAP-Elites for Automated Hearthstone Deckbuilding. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), July 9–13, 2022, Boston, MA, USA, 2022.
A Simple Approach to Continual Learning by Transferring Skill Parameters. Preprint, 2021.
Long-Term, in-the-Wild Study of Feedback about Speech Intelligibility for K-12 Students Attending Class via a Telepresence Robot. In Proceedings of the 2021 International Conference on Multimodal Interaction (ICMI), October 18–22, 2021, Montréal, QC, Canada, 2021.
On the Importance of Environments in Human-Robot Coordination. In Proceedings of Robotics: Science and Systems (RSS), July 12–16 2021, 2021.
Towards Exploiting Geometry and Time for Fast Off-Distribution Adaptation in Multi-Task Robot Learning. In NeurIPS 2020 Workshop: Challenges of Real World Reinforcement Learning, December 12, 2020, 2020.
Increasing Telepresence Robot Operator Awareness of Speaking Volume Appropriateness: Initial Model Development. In Companion of the 2020 ACM/IEEE International Conference on Human-Robot Interaction (HRI), March 24-26, 2020, Cambridge, United Kingdom, 2020.