publications

2025

1. Learning-based GNSS Uncertainty Quantification using Continuous-Time Factor Graph Optimization

   Haoming Zhang

   2025

   DOI Bib

   @misc{zhang_grc2025,
     title = {Learning-based GNSS Uncertainty Quantification using Continuous-Time Factor Graph Optimization},
     author = {Zhang, Haoming},
     booktitle = {2025 1st German Robotics Conference},
     year = {2025},
     eprint = {2503.04933},
     url = {https://arxiv.org/abs/2503.04933},
     doi = {10.48550/arXiv.2503.04933},
   }

2024

1. GNSS/Multisensor Fusion Using Continuous-Time Factor Graph Optimization for Robust Localization

   Haoming Zhang, Chih-Chun Chen, Heike Vallery, and 1 more author

   IEEE Transactions on Robotics, 2024

   DOI Bib Video

   @article{gnssfgo,
     author = {Zhang, Haoming and Chen, Chih-Chun and Vallery, Heike and Barfoot, Timothy D.},
     journal = {IEEE Transactions on Robotics},
     title = {GNSS/Multisensor Fusion Using Continuous-Time Factor Graph Optimization for Robust Localization},
     year = {2024},
     volume = {40},
     number = {},
     pages = {4003-4023},
     keywords = {Global navigation satellite system;Sensors;Sensor fusion;Location awareness;Trajectory;Laser radar;Optimization;Autonomous vehicle navigation;factor graph optimization (FGO);global navigation satellite systems (GNSS);localization;sensor fusion},
     doi = {10.1109/TRO.2024.3443699},
   }

2023

1. Object Detection and Heading Estimation from Radar Raw data

   Ravi Kothari, Ali Kariminezhad, Christian Mayr, and 1 more author

   In 2023 IEEE Intelligent Vehicles Symposium (IV), 2023

   DOI Bib

   @inproceedings{ravi_radar,
     author = {Kothari, Ravi and Kariminezhad, Ali and Mayr, Christian and Zhang, Haoming},
     booktitle = {2023 IEEE Intelligent Vehicles Symposium (IV)},
     title = {Object Detection and Heading Estimation from Radar Raw data},
     year = {2023},
     volume = {},
     number = {},
     pages = {1-7},
     keywords = {Pedestrians;Estimation;Radar detection;Radar;Object detection;Artificial neural networks;Transformers;DNN;cross-attention;raw radar data;object detection;heading forecasting},
     doi = {10.1109/IV55152.2023.10186591},
   }

2. Learning-based NLOS Detection and Uncertainty Prediction of GNSS Observations with Transformer-Enhanced LSTM Network

   Haoming Zhang, Zhanxin Wang, and Heike Vallery

   In 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), 2023

   DOI Bib Video

   @inproceedings{telstm,
     author = {Zhang, Haoming and Wang, Zhanxin and Vallery, Heike},
     booktitle = {2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)},
     title = {Learning-based NLOS Detection and Uncertainty Prediction of GNSS Observations with Transformer-Enhanced LSTM Network},
     year = {2023},
     volume = {},
     number = {},
     pages = {910-917},
     keywords = {Location awareness;Training;Global navigation satellite system;Uncertainty;Urban areas;Transformers;Trajectory},
     doi = {10.1109/ITSC57777.2023.10422672},
   }

2022

1. Predicting basin stability of power grids using graph neural networks

   Christian Nauck, Michael Lindner, Konstantin Schürholt, and 5 more authors

   New Journal of Physics, Apr 2022

   Abs DOI Bib HTML

   The prediction of dynamical stability of power grids becomes more important and challenging with increasing shares of renewable energy sources due to their decentralized structure, reduced inertia and volatility. We investigate the feasibility of applying graph neural networks (GNN) to predict dynamic stability of synchronisation in complex power grids using the single-node basin stability (SNBS) as a measure. To do so, we generate two synthetic datasets for grids with 20 and 100 nodes respectively and estimate SNBS using Monte-Carlo sampling. Those datasets are used to train and evaluate the performance of eight different GNN-models. All models use the full graph without simplifications as input and predict SNBS in a nodal-regression-setup. We show that SNBS can be predicted in general and the performance significantly changes using different GNN-models. Furthermore, we observe interesting transfer capabilities of our approach: GNN-models trained on smaller grids can directly be applied on larger grids without the need of retraining.

   @article{Nauck_2022,
     doi = {10.1088/1367-2630/ac54c9},
     url = {https://dx.doi.org/10.1088/1367-2630/ac54c9},
     year = {2022},
     month = apr,
     publisher = {IOP Publishing},
     volume = {24},
     number = {4},
     pages = {043041},
     author = {Nauck, Christian and Lindner, Michael and Schürholt, Konstantin and Zhang, Haoming and Schultz, Paul and Kurths, Jürgen and Isenhardt, Ingrid and Hellmann, Frank},
     title = {Predicting basin stability of power grids using graph neural networks},
     journal = {New Journal of Physics},
   }

2. Continuous-Time Factor Graph Optimization for Trajectory Smoothness of GNSS/INS Navigation in Temporarily GNSS-Denied Environments

   Haoming Zhang, Xiao Xia, Maximilian Nitsch, and 1 more author

   IEEE Robotics and Automation Letters, Apr 2022

   DOI Bib Video

   @article{fgo_zhang,
     author = {Zhang, Haoming and Xia, Xiao and Nitsch, Maximilian and Abel, Dirk},
     journal = {IEEE Robotics and Automation Letters},
     title = {Continuous-Time Factor Graph Optimization for Trajectory Smoothness of GNSS/INS Navigation in Temporarily GNSS-Denied Environments},
     year = {2022},
     volume = {7},
     number = {4},
     pages = {9115-9122},
     keywords = {Global navigation satellite system;Trajectory;Optimization;Location awareness;Kalman filters;State estimation;Satellites;Localization;Sensor Fusion;Marine Robotics;Factor Graph Optimization;GNSS/INS-Integration},
     doi = {10.1109/LRA.2022.3189824},
   }