Junyi (Kevin) Ma

About Me

I received the B.S degree in vehicle engineering from the Beijing Institute of Technology, Beijing, China, in 2020. I’m currently a Master student in Intelligent Vehicle Research Center at Beijing Institute of Technology. I am trying to apply machine learning methods to robotics and use multiple sensor data for enhanced perception capability of robots and intelligent vehicles.

Research Interests

• Localization and Mapping
• Robotics
• Intelligent Vehicles

News

• [May. 2023] Our paper PCPNet: An Efficient and Semantic-Enhanced Transformer Network for Point Cloud Prediction is accepted to RAL.
• [Mar. 2023] Our paper A Non-Uniform Quadtree Map Building Method Including Dead-End Semantics Extraction is accepted to Green Energy and Intelligent Transportation.
• [Dec. 2022] Our paper SeqOT: A Spatial-Temporal Transformer Network for Place Recognition Using Sequential LiDAR Data is accepted by IEEE Transactions on Industrial Electronics.
• [Aug. 2022] Our paper Semantic Segmentation Based Rain and Fog Filtering Only by LiDAR Point Clouds is accepted to ICUS 2022.
• [May. 2022] Our paper OverlapTransformer: An Efficient and Yaw-Angle-Invariant Transformer Network for LiDAR-Based Place Recognition is accepted to RAL/IROS 2022.
• [Apr. 2022] Our paper Multi-Uncertainty Captured Multi-Robot Lidar Odometry and Mapping Framework for Large-Scale Environments is accepted by Unmanned Systems.
• [Apr. 2022] Our paper A Comparative Study of Deep Reinforcement Learning-based Transferable Energy Management Strategies for Hybrid Electric Vehicles is accepted to IV 2022.

Publications

• CVTNet: A Cross-View Transformer Network for Place Recognition Using LiDAR Data
  Junyi Ma, Guangming Xiong, Jingyi Xu, Xieyuanli Chen*
  arXiv preprint arXiv:2302.01665, 2023.
  [PDF] [Code]
  

• PCPNet: An Efficient and Semantic-Enhanced Transformer Network for Point Cloud Prediction Mentorship
  Zhen Luo, Junyi Ma, Zijie Zhou, Guangming Xiong
  IEEE Robotics and Automation Letters (RA-L), 2023.
  [PDF] [Code]
  

• A Non-Uniform Quadtree Map Building Method Including Dead-End Semantics Extraction
  Xiuzhong Hu, Guangming Xiong*, Junyi Ma, Gege Cui, Quanfu Yu, Shihao Li, Zijie Zhou
  Green Energy and Intelligent Transportation (GEIT), 2023.
  [PDF] [Code]
  

• SeqOT: A Spatial-Temporal Transformer Network for Place Recognition Using Sequential LiDAR Data
  Junyi Ma, Xieyuanli Chen, Jingyi Xu, Guangming Xiong*
  IEEE Transactions on Industrial Electronics (TIE), 2022.
  [PDF] [Code]
  

• OverlapTransformer: An Efficient and Yaw-Angle-Invariant Transformer Network for LiDAR-Based Place Recognition
  Junyi Ma, Jun Zhang, Jintao Xu, Rui Ai, Weihao Gu, and Xieyuanli Chen*
  IEEE Robotics and Automation Letters (RA-L), 2022, and IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022.
  [PDF] [Code]
  

• A Comparative Study of Deep Reinforcement Learning-based Transferable Energy Management Strategies for Hybrid Electric Vehicles
  Jingyi Xu, Zirui Li, Li Gao, Junyi Ma, Qi Liu, and Yanan Zhao*
  IEEE Intelligent Vehicles Symposium (IV), 2022.
  [PDF] [Code]
  

• Semantic Segmentation Based Rain and Fog Filtering Only by LiDAR Point Clouds
  Zhen Luo, Junyi Ma, Guangming Xiong*, Xiuzhong Hu, Zijie Zhou, Jiahui Xu
  IEEE International Conference on Unmanned Systems (ICUS), 2022.
  [PDF] [Code]
  

• MUC-LOAM: Multi-uncertainty Captured Multi-robot Lidar Odometry and Mapping Framework for Large-scale Environments
  Guangming Xiong*, Junyi Ma, Huilong Yu, Jingyi Xu, Jiahui Xu
  Unmanned Systems (US).
  [PDF] [Code]
  

• Mutual Pose Recognition Based on Multiple Cues in Multi-robot Systems
  Junyi Ma, Guangming Xiong*, Jingyi Xu, Jiarui Song, and Dong Sun
  Best paper for IEEE International Conference on Unmanned Systems (ICUS), 2021.
  [PDF] [Code]
  

Other Contributions

• Pytorch Version for OverlapNet [Code]
  
• Multiple Lidar Calibration [Code]
  
• Active SLAM Based on Information Theory [Code]
  
• Occupancy Grid Mapping [Code]
  
• Stairs Recognition [Code]
  

Datasets

• Haomo Dataset
  The dataset was collected by a mobile robot built by HAOMO.AI Technology company equipped with a HESAI PandarXT 32-beam LiDAR sensor in urban environments of Beijing.
  [Description]

• Cues-Poses Dataset
  A toy dataset about mapping multiple cues to mutual poses of robots.
  [Description]

Patents

• [China Utility Model] Huilong Yu, Ziang Tian, Junyi Ma, Haotian Dong, Junqiang Xi, and Guangming Xiong. A multifunctional unmanned platform for subterranean space. ZL202123083457.8
• [China Appearance Design] Huilong Yu, Ziang Tian, Junyi Ma, Haotian Dong, Junqiang Xi, and Guangming Xiong. A multifunctional unmanned caterpillar for subterranean space. ZL202130813635.4
• [China Invention Publication] Guangming Xiong, Junyi Ma, Jingyi Xu, and Jiarui Song. A reliability analysis-based multi-robot cooperative localization and mapping method. ZL202110318362.5

Powered by Jekyll and Minimal Light theme.