Xintong Zhang

Hi, I’m Xintong. I am an junior student majoring in Applied Mathematics and Computer Science at Dukekunshan University. I am recently collaborating with Dr. Junfeng Chen, Prof. Meng Guo and his team from Peking University.

My works focus on adaptive coordination and communication in multi-robot systems, particularly under challenging conditions such as intermittent connectivity, limited communication, and unknown environments. I specialize in developing frameworks that optimize task planning, dynamic allocation, and communication strategies for heterogeneous robotic fleets (e.g., UAVs/UGVs) using LLM, optimization, and tree-search algorithms. Through high-fidelity simulations and innovative algorithmic designs, I aim to address practical challenges in dynamic scenarios while ensuring reliable system performance. Currently, I am keenly interested in exploring how learning-based methods and explicit modeling of robot-world interactions can enhance the robustness, adaptability, and practical deployability of autonomous systems.

Publication

LLMs Meet Formal Methods for Robot Swarms: Reliable, Explainable and Efficient Human-in-the-loop Planning in Unknown Environments
Junfeng Chen, Yuxiao Zhu, An Zhuo, Xintong Zhang, Shuo Zhang, Meng Guo#, and Zhongkui Li#
Submitted to Science Robotics
video
Overview: We propose a formal method and LLM framework for coordinating large fleets of heterogeneous robots in open and dynamic environments. Our approach integrates model-checking-based task planning with LLM-powered reasoning and interaction, ensuring adaptability, explainability, and optimal mission execution. Validated through simulations and real-world deployments, it proves effective for disaster response, infrastructure inspection, and dynamic surveillance.

CoCoPlan: Adaptive Coordination and Communication for Multi-robot Systems under Continual Temporal Tasks
Jan 2025-August 2025
Xintong Zhang*, Junfeng Chen*, Yuxiao Zhu, Bing Luo, Meng Guo
Submitted to Robotics and Automation Letter (RAL) (Accepted)
website
Overview: We propose CoCoPlan, a collaborative framework addressing communication-aware task planning for multi-robot systems under intermittent connectivity constraints. The framework focuses on joint optimization of communication events and task allocation, ensuring robustness in unknown environments.

DEXTER-LLM: Dynamic and Explainable Coordination of Multi-Robot Systems in Unknown Environments via Large Language Models
Dec 2024-March 2025
Yuxiao Zhu*, Junfeng Chen*, Xintong Zhang, Meng Guo, Zhongkui Li
International Conference on Intelligent Robots (IROS) (Accepted)
website pdf
Overview: We propose DEXTER-LLM, a novel framework for dynamic task planning in unknown environments. Our approach integrates LLM-based multi-stage reasoning, optimization-based task assignment, and adaptive human-in-the-loop verification to tackle the challenges of online adaptability and explainability.

SLEI3D: Simultaneous Large-scale 3D Exploration Inspection and Interaction via Heterogeneous Fleets under Limited Communication
June-Dec 2024
Junfeng Chen, Yuxiao Zhu, Xintong Zhang, Bing Luo, Meng Guo
Transactions on Automation Science and Engineering (TASE) (Accepted)
website
Overview: We propose SLEI3D, a planning and coordination framework for heterogeneous multi-robot systems to perform simultaneous 3D exploration, inspection, and real-time reporting in unknown environments. Our approach integrates adaptive inspection and intermittent communication protocols with a multi-layer, multi-rate planning mechanism for robust coordination.

CV

Download here