Zhe Chen

Amazon Robotics

North Reading, MA

I am a Postdoctoral Scientist at Amazon Robotics working on efficient motion planning and coordination of mobile robots in warehouse environments. My research focuses on Multi-Agent Path Finding (MAPF), Heuristic Search, and Planning algorithms that enable large teams of robots to coordinate seamlessly.

I received my PhD in Computer Science from Monash University in 2024, advised by Prof Daniel Harabor and Prof Peter Stuckey.

Research Interests

Multi-Agent Path Finding: Developing scalable algorithms for coordinating large teams of robots
Heuristic Search: Creating efficient search algorithms for path planning problems
Planning and Scheduling: Designing algorithms that handle dynamic environments and uncertainties
Traffic Flow Optimization: Optimizing robot movement in dense environments
Real-time Planning: Developing algorithms that can adapt to changing conditions

My research has practical applications in warehouse robotics, autonomous vehicle coordination, and any scenario requiring efficient coordination of multiple autonomous agents. I am passionate about bridging the gap between theoretical advances and real-world deployment.

I actively contribute to the research community through organizing workshops (AAAI Workshop on Multi-Agent Path Finding), competitions (Grid-Based Path Planning Competition, League of Robot Runners), and serving on program committees for top-tier venues including AAAI, ICAPS, and SoCS.

System Demonstrations

My research translates into practical systems and tools. Here are demonstrations of some key projects:

League of Robot Runners Competition
A competitive platform for multi-agent path finding algorithms with real-time constraints and dynamic environments.

Tracking Progress in Multi-Agent Path Finding
Visualization system showing real-time progress tracking and performance metrics for MAPF algorithms.

Flatland Challenge: Rail Planning System
Our winning solution for the 2020 Flatland Challenge, demonstrating scalable train coordination in complex rail networks.

News

May 29, 2026	“Flow-Based Task Assignment for Large-Scale Online Multi-Agent Pickup and Delivery” was named an AAMAS 2026 Best Student Paper nominee.
Apr 20, 2026	Our paper “A Lightweight Traffic Map for Efficient Anytime LaCAM” has been accepted at IJCAI 2026.
Apr 08, 2026	Invited by Prof. Jiaoyang Li, I gave a guest lecture at CMU for the Multi-Robot Planning and Coordination unit.
Jan 20, 2026	Two papers accepted at AAMAS 2026: “Flow-Based Task Assignment for Large-Scale Online Multi-Agent Pickup and Delivery” and “Flexibility-Based Traffic Flow Optimisation in Lifelong Multi-Agent Path Finding”.
Aug 25, 2025	Our paper “Symbolic Planning and Multi-Agent Path Finding in Extremely Dense Environments with Unassigned Agents” has been accepted at AAAI 2026.
Feb 01, 2025	Two Papers Accepted at AAAI 2025

Selected publications

A Lightweight Traffic Map for Efficient Anytime LaCAM

Bojie Shen, Yue Zhang, Zhe Chen, and 1 more author

In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI 2026, 2026

arXiv Bib PDF Code

@inproceedings{shen2026lightweighttrafficmap,
  author = {Shen, Bojie and Zhang, Yue and Chen, Zhe and Harabor, Daniel},
  title = {A Lightweight Traffic Map for Efficient Anytime LaCAM},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
                    Artificial Intelligence, {IJCAI} 2026},
  year = {2026},
  doi = {10.48550/ARXIV.2603.07891},
  eprinttype = {arXiv},
  eprint = {2603.07891},
  timestamp = {Fri, 10 Apr 2026 01:00:00 +0200},
  biburl = {https://dblp.org/rec/journals/corr/abs-2603-07891.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
}

Flow-Based Task Assignment for Large-Scale Online Multi-Agent Pickup and Delivery

Yue Zhang, Zhe Chen, Daniel Harabor, and 2 more authors

In Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2026, 2026

Best Student Paper Nominee arXiv Bib PDF

AAMAS 2026 Best Student Paper Nominee

@inproceedings{zhang2026flowbasedtaskassignment,
  author = {Zhang, Yue and Chen, Zhe and Harabor, Daniel and Bodic, Pierre Le and Stuckey, Peter J.},
  title = {Flow-Based Task Assignment for Large-Scale Online Multi-Agent Pickup
                    and Delivery},
  booktitle = {Proceedings of the 25th International Conference on Autonomous Agents
                    and Multiagent Systems, {AAMAS} 2026},
  year = {2026},
  doi = {10.48550/ARXIV.2508.05890},
  eprinttype = {arXiv},
  eprint = {2508.05890},
  timestamp = {Sun, 14 Sep 2025 01:00:00 +0200},
  biburl = {https://dblp.org/rec/journals/corr/abs-2508-05890.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
}

The League of Robot Runners Competition: Goals, Designs, and Implementation

Shao-Hung Chan, Zhe Chen, Teng Guo, and 6 more authors

In ICAPS 2024 System’s Demonstration track, 2024

Bib PDF 🎬 Video Website

@inproceedings{chan2024the,
  title = {The League of Robot Runners Competition: Goals, Designs, and Implementation},
  author = {Chan, Shao-Hung and Chen, Zhe and Guo, Teng and Zhang, Han and Zhang, Yue and Harabor, Daniel and Koenig, Sven and Wu, Cathy and Yu, Jingjin},
  booktitle = {ICAPS 2024 System's Demonstration track},
  year = {2024},
  url = {https://openreview.net/forum?id=mPmCnEHTvJ},
}

Traffic Flow Optimisation for Lifelong Multi-Agent Path Finding

Zhe Chen, Daniel Harabor, Jiaoyang Li, and 1 more author

In Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, Fourteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2014, February 20-27, 2024, Vancouver, Canada, 2024

arXiv Bib PDF Code

@inproceedings{DBLP:conf/aaai/0016H0S24,
  author = {Chen, Zhe and Harabor, Daniel and Li, Jiaoyang and Stuckey, Peter J.},
  editor = {Wooldridge, Michael J. and Dy, Jennifer G. and Natarajan, Sriraam},
  title = {Traffic Flow Optimisation for Lifelong Multi-Agent Path Finding},
  booktitle = {Thirty-Eighth {AAAI} Conference on Artificial Intelligence, {AAAI}
                    2024, Thirty-Sixth Conference on Innovative Applications of Artificial
                    Intelligence, {IAAI} 2024, Fourteenth Symposium on Educational Advances
                    in Artificial Intelligence, {EAAI} 2014, February 20-27, 2024, Vancouver,
                    Canada},
  pages = {20674--20682},
  publisher = {{AAAI} Press},
  year = {2024},
  doi = {10.1609/AAAI.V38I18.30054},
  timestamp = {Tue, 02 Apr 2024 01:00:00 +0200},
  biburl = {https://dblp.org/rec/conf/aaai/0016H0S24.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
}

Planning and Execution in Multi-Agent Path Finding: Models and Algorithms

Yue Zhang, Zhe Chen, Daniel Harabor, and 2 more authors

In Proceedings of the Thirty-Fourth International Conference on Automated Planning and Scheduling, ICAPS 2024, Banff, Alberta, Canada, June 1-6, 2024, 2024

Bib PDF Code

@inproceedings{DBLP:conf/icaps/ZhangCHBS24,
  author = {Zhang, Yue and Chen, Zhe and Harabor, Daniel and Bodic, Pierre Le and Stuckey, Peter J.},
  editor = {Bernardini, Sara and Muise, Christian},
  title = {Planning and Execution in Multi-Agent Path Finding: Models and Algorithms},
  booktitle = {Proceedings of the Thirty-Fourth International Conference on Automated
                    Planning and Scheduling, {ICAPS} 2024, Banff, Alberta, Canada, June
                    1-6, 2024},
  pages = {707--715},
  publisher = {{AAAI} Press},
  year = {2024},
  doi = {10.1609/ICAPS.V34I1.31534},
  timestamp = {Tue, 30 Jul 2024 01:00:00 +0200},
  biburl = {https://dblp.org/rec/conf/icaps/ZhangCHBS24.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
}

Tracking Progress in Multi-Agent Path Finding

Bojie Shen, Zhe Chen, Muhammad Aamir Cheema, and 2 more authors

CoRR, 2023

arXiv Bib 🎬 Video Website

@article{DBLP:journals/corr/abs-2305-08446,
  author = {Shen, Bojie and Chen, Zhe and Cheema, Muhammad Aamir and Harabor, Daniel Damir and Stuckey, Peter J.},
  title = {Tracking Progress in Multi-Agent Path Finding},
  journal = {CoRR},
  volume = {abs/2305.08446},
  year = {2023},
  url = {https://doi.org/10.48550/arXiv.2305.08446},
  doi = {10.48550/ARXIV.2305.08446},
  eprinttype = {arXiv},
  eprint = {2305.08446},
  timestamp = {Wed, 16 Aug 2023 01:00:00 +0200},
  biburl = {https://dblp.org/rec/journals/corr/abs-2305-08446.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
}

Integrated Task Assignment and Path Planning for Capacitated Multi-Agent Pickup and Delivery

Zhe Chen, Javier Alonso-Mora, Xiaoshan Bai, and 2 more authors

IEEE Robotics Autom. Lett., 2021

arXiv Bib

@article{DBLP:journals/ral/ChenABHS21,
  author = {Chen, Zhe and Alonso{-}Mora, Javier and Bai, Xiaoshan and Harabor, Daniel Damir and Stuckey, Peter J.},
  title = {Integrated Task Assignment and Path Planning for Capacitated Multi-Agent
                    Pickup and Delivery},
  journal = {{IEEE} Robotics Autom. Lett.},
  volume = {6},
  number = {3},
  pages = {5816--5823},
  year = {2021},
  url = {https://doi.org/10.1109/LRA.2021.3074883},
  doi = {10.1109/LRA.2021.3074883},
  timestamp = {Wed, 16 Aug 2023 01:00:00 +0200},
  biburl = {https://dblp.org/rec/journals/ral/ChenABHS21.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
}

Scalable Rail Planning and Replanning: Winning the 2020 Flatland Challenge

Jiaoyang Li, Zhe Chen, Yi Zheng, and 5 more authors

In Proceedings of the Thirty-First International Conference on Automated Planning and Scheduling, ICAPS 2021, Guangzhou, China (virtual), August 2-13, 2021, 2021

Bib PDF 🎬 Video Code

@inproceedings{DBLP:conf/aips/0001CZCHS0K21,
  author = {Li, Jiaoyang and Chen, Zhe and Zheng, Yi and Chan, Shao{-}Hung and Harabor, Daniel and Stuckey, Peter J. and Ma, Hang and Koenig, Sven},
  editor = {Biundo, Susanne and Do, Minh and Goldman, Robert and Katz, Michael and Yang, Qiang and Zhuo, Hankz Hankui},
  title = {Scalable Rail Planning and Replanning: Winning the 2020 Flatland Challenge},
  booktitle = {Proceedings of the Thirty-First International Conference on Automated
                    Planning and Scheduling, {ICAPS} 2021, Guangzhou, China (virtual),
                    August 2-13, 2021},
  pages = {477--485},
  publisher = {{AAAI} Press},
  year = {2021},
  timestamp = {Wed, 30 Aug 2023 08:38:08 +0200},
  biburl = {https://dblp.org/rec/conf/aips/0001CZCHS0K21.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
}

Anytime Multi-Agent Path Finding via Large Neighborhood Search

Jiaoyang Li, Zhe Chen, Daniel Harabor, and 2 more authors

In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI 2021, Virtual Event / Montreal, Canada, 19-27 August 2021, 2021

Bib PDF Code

@inproceedings{DBLP:conf/ijcai/0001CHSK21,
  author = {Li, Jiaoyang and Chen, Zhe and Harabor, Daniel and Stuckey, Peter J. and Koenig, Sven},
  editor = {Zhou, Zhi{-}Hua},
  title = {Anytime Multi-Agent Path Finding via Large Neighborhood Search},
  booktitle = {Proceedings of the Thirtieth International Joint Conference on Artificial
                    Intelligence, {IJCAI} 2021, Virtual Event / Montreal, Canada, 19-27
                    August 2021},
  pages = {4127--4135},
  publisher = {ijcai.org},
  year = {2021},
  doi = {10.24963/IJCAI.2021/568},
  timestamp = {Wed, 16 Aug 2023 01:00:00 +0200},
  biburl = {https://dblp.org/rec/conf/ijcai/0001CHSK21.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
}