I am a second-year master student at the School of Control Science and Engineering, Shandong University, specializing in control engineering, with a primary research interest in service robotics, and I graduated from China University of Petroleum (East China) with a B.S. degree in 2023.

My research interests include service robotics, task planning, and embodied intelligence. Currently, I am working on general-purpose robotics approaches that can understand human commands and interact with the physical world to execute them.

Email / Github / CSDN

News

  • Jun, 2025       Our Paper has been accepted by TIE 2025

  • Jun, 2024       Our Paper has been accepted by IROS 2024

  • Jun, 2024       Our Paper has been accepted by RAL 2024

Publications

Flow Diagram

Task Guided Multimodal Object Search for Service Robots via Reinforcement Learning

Xiaodong Li, Guohui Tian, Yongcheng Cui

IEEE Transactions on Industrial Electronics, 2025

We present a task-guided multimodal object search method for service robots, combining visual, semantic, and object relationship data to improve search efficiency.

Flow Diagram

Transformer-Based Relationship Inference Model for Household Object Organization by Integrating Graph Topology and Ontology

Xiaodong Li, Guohui Tian, Yongcheng Cui, Yu Gu

The 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024)

Paper / Code

We introduce a dataset of household object properties and a graph-based model combining GAT and BERT to predict relationships, improving robots' object organization using a Transformer framework.

Flow Diagram

Fine-Grained Task Planning for Service Robots Based on Object Ontology Knowledge via Large Language Models

Xiaodong Li, Guohui Tian, Yongcheng Cui

IEEE Robotics and Automation Letters, 2024

Paper / Code

We introduce the Fine-Grained Task Planning (FGTP) framework, which uses object ontology and LLMs to generate action plans and identify alternatives when tasks fail.

Honors

  • National Scholarship, 2024

  • National Scholarship, 2020