Jiajie Zhang

About Me

I am a graduate student at ShanghaiTech University pursuing a Master’s degree in Computer Science and Technology. Since 2023, I have been conducting research at the MARS Lab (Mobile Autonomous Robotics Systems Laboratory) at ShanghaiTech University, advised by Professor Sören Schwertfeger, focusing on cutting-edge areas including Mobile Robotics and Embodied AI.

My research interests lie at the intersection of robotics and artificial intelligence, with particular emphasis on:

Intelligent Navigation Systems: Developing robust navigation algorithms that integrate semantic understanding with traditional path planning
SLAM and Mapping: Creating long-term, lifelong mapping solutions for dynamic indoor environments
Embodied AI: Bridging the gap between large language models and robotic systems for enhanced human-robot interaction

Recent Work

I am currently working on several exciting projects that push the boundaries of mobile robotics:

LLM-Enhanced Navigation: My recent work on integrating Large Language Models with traditional ROS navigation stack has been accepted at IROS 2025. This research demonstrates how contextual understanding can significantly improve robot navigation in complex environments.

Neural Scene Reconstruction: I have contributed to advancing 3D scene mapping through neural surfel-based methods, addressing critical challenges in loop closure and large-scale reconstruction. This work was published in MDPI Sensors in 2024.

AGLoc++ System: I am extending previous work on robust indoor localization by incorporating WiFi-aided recovery and Monte Carlo tracking, making the system more practical for real-world deployment.

Background

Before joining ShanghaiTech University, I completed my Bachelor’s degree in Automation at Zhengzhou University (2019-2023), where I developed a strong foundation in control systems, signal processing, and robotics fundamentals.

Feel free to explore my publications and projects to learn more about my research contributions, or check out my CV for detailed academic information.

news

Jul 01, 2025	New preprint on CAD to OpenStreetMap Generation for robot navigation is now available on arXiv!
Jan 15, 2025	Our paper on LLM-enhanced robot navigation has been accepted by IROS 2025! 🎉
Oct 28, 2024	Neural Surfel Reconstruction Paper Published in MDPI Sensors
Sep 13, 2024	New preprint released: Intelligent LiDAR Navigation with LLM as Copilot on arXiv!
Sep 01, 2024	Serving as Teaching Assistant for the Mobile Manipulation (MoMa) course at ShanghaiTech University.

publications

Intelligent LiDAR Navigation: Leveraging External Information and Semantic Maps with LLM as Copilot

Fujing Xie, Jiajie Zhang, and Sören Schwertfeger

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025

Abs Bib HTML PDF

This study enhances robot navigation by integrating Large Language Models (LLMs) with ROS move_base, using osmAG for semantic mapping. The approach combines human-like contextual understanding with traditional navigation, improving adaptability and robustness in complex environments.
@article{zhang2025llm, title = {Intelligent LiDAR Navigation: Leveraging External Information and Semantic Maps with LLM as Copilot}, author = {Xie, Fujing and Zhang, Jiajie and Schwertfeger, Sören}, journal = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, year = {2025}, publisher = {IEEE}, url = {https://arxiv.org/abs/2409.08493}, dimensions = {true}, }
Neural Surfel Reconstruction: Addressing Loop Closure Challenges in Large-Scale 3D Neural Scene Mapping

Jiadi Cui, Jiajie Zhang, and Sören Schwertfeger

MDPI Sensors, Oct 2024

Abs DOI Bib HTML PDF

This paper introduces a novel neural surfel-based method for large-scale 3D scene reconstruction, addressing challenges in loop closure and bundle adjustment. By integrating neural descriptors with surfels and optimizing surfel associations, the approach achieves improved reconstruction accuracy and significantly reduces file sizes compared to traditional methods.
@article{zhang2024neural, title = {Neural Surfel Reconstruction: Addressing Loop Closure Challenges in Large-Scale 3D Neural Scene Mapping}, author = {Cui, Jiadi and Zhang, Jiajie and Schwertfeger, Sören}, journal = {MDPI Sensors}, volume = {24}, number = {21}, pages = {6919}, year = {2024}, month = oct, publisher = {MDPI}, doi = {10.3390/s24216919}, url = {https://www.mdpi.com/1424-8220/24/21/6919}, dimensions = {true}, }
Generation of Indoor Open Street Maps for Robot Navigation from CAD Files

Jiajie Zhang, Shenrui Wu, Xu Ma, and 1 more author

arXiv preprint arXiv:2507.00552, Jul 2025

Abs arXiv Bib HTML PDF

This paper presents a complete and automated system to convert architectural Computer-Aided Design (CAD) files into a hierarchical topometric OpenStreetMap (OSM) representation for robust, life-long robot navigation. The method overcomes the limitations of traditional SLAM by leveraging permanent structural information, employing a multi-stage pipeline that includes topological segmentation, semantic text association, and multi-floor fusion to generate semantically rich and topologically correct maps.
@article{zhang2025cad2osm, title = {Generation of Indoor Open Street Maps for Robot Navigation from CAD Files}, author = {Zhang, Jiajie and Wu, Shenrui and Ma, Xu and Schwertfeger, Sören}, journal = {arXiv preprint arXiv:2507.00552}, year = {2025}, month = jul, url = {https://arxiv.org/abs/2507.00552}, dimensions = {true}, }