Peijin Jia

Peijin Jia

Tsinghua University

I am currently an algorithm engineer at Li Auto. I was a graduate student at Tsinghua University, under the supervision of Professor Diange Yang. During my graduate studies, I interned at Shanghai AI Lab, NVIDIA, and Didi Inc.

My research interest lies in Autonomous Driving and Embodied AI, which includes vision-language-navigation, simulator and online mapping.

Outside of academia, I have a passion for music, traveling, and swimming. In terms of my life goals, I aspire to have a fulfilling career in a field that I am passionate about and I also strive to make a positive impact by helping others realize their full potential.

  • If you are interested in my research, please feel free to contact me via email

📝 Publications

LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving

ICLR2024 Accepted

Tianyu Li$^\ast$, Peijin Jia$^\ast$, Bangjun Wang$^\ast$, Li Chen, Kun Jiang, Junchi Yan, Hongyang Li

DiffMap: Enhancing Map Segmentation with Map Prior Using Diffusion Model

RAL/ICRA2025 Accepted

Peijin Jia, Tuopu Wen, Ziang Luo, Mengmeng Yang, Kun Jiang, Zhiquan Lei, Xuewei Tang, Ziyuan Liu, Le Cui, Kehua Sheng, Bo Zhang, Diange Yang

Enhancing Lane Segment Perception and Topology Reasoning with Crowdsourcing Trajectory Priors

RAL/IROS2025 Accepted

Peijin Jia, Ziang Luo, Tuopu Wen, Mengmeng Yang, Kun Jiang, Le Cui, Diange Yang

LaneDag: Automatic HD Map Topology Generator Based on Geometry and Attention Fusion Mechanism

IV2024 Accepted

Peijin Jia, Tuopu Wen, Ziang Luo, Zheng Fu, Jiaqi Liao, Kun Jiang, Mengmeng Yang, Diange Yang

OpenLane-V2: A Topology Reasoning Benchmark for Scene Understanding in Autonomous Driving

NIPS2023 Accepted

Huijie Wang, Tianyu Li, Yang Li, Li Chen, Chonghao Sima, Zhenbo Liu, Bangjun Wang, Peijin Jia, Yuting Wang, Shengyin Jiang, Feng Wen, Hang Xu, Ping Luo, Junchi Yan, Wei Zhang, Hongyang Li

High-Definition Maps Construction Based on Visual Sensor: A Comprehensive Survey

TIV Accepted

Xuewei Tang, Kun Jiang, Mengmeng Yang, Zhaoyang Liu, Peijin Jia et.al and Diange Yang

Roadside HD Map Object Reconstruction Using Monocular Camera

RAL Accepted

Tuopu Wen, Kun Jiang, Jinyu Miao, Benny Wijaya, Peijin Jia, Mengmeng Yang, Diange Yang

A Survey on Monocular Re-Localization: From the Perspective of Scene Map Representation

TIV Accepted

Jinyu Miao, Kun Jiang, Tuopu Wen, Yunlong Wang, Peijin Jia, Benny Wijaya, Xuhe Zhao, Qian Cheng, Zhongyang Xiao, Jin Huang, Zhihua Zhong, Diange Yang

📖 Summary

  • Programming Language: Python, C, C++, Matlab
  • English: CET4:598 CET6:541
  • Based on my project experience, I have gained knowledge and expertise in various aspects of AD maps, including algorithm review, dataset processing (AV2, NuScenes, Openlanev2), topological correlation research, and algorithm optimization. I am proficient in using the PyTorch deep learning framework and familiar with a range of open-source tools such as mmdet, Detectron2, and diffusers. These skills enable me to quickly adapt to internship requirements.