Daniele is a Departmental Lecturer in Mobile Robotics and co-leads with Professor Paul Newmand the Mobile Robotics Group. He is also a College Lecturer in Engineering Science at Pembroke College.
Daniele is interested in robust navigation and scene understanding -- from odometry and localisation to detection and segmentation -- enabling the deployment of robots in challenging weather and scenarios. He is exploring techniques to improve robustness either by utilising inherently more robust sensors, focusing on FMCW scanning radar technology, or enhancing the training of perception modules.
Recent Publications
Point-based metric and topological localisation between lidar and overhead imagery
Tang TY, De Martini D & Newman P (2023), AUTONOMOUS ROBOTS
Visuo-tactile recognition of partial point clouds using PointNet and curriculum learning
Parsons C, Albini A, De Martini D & Maiolino P (2022), IEEE Robotics and Automation magazine
RaVÆn: unsupervised change detection of extreme events using ML on-board satellites.
Růžička V, Vaughan A, De Martini D, Fulton J, Salvatelli V et al. (2022), Scientific reports, 12(1), 16939
BibTeX
@article{ravnunsupervise-2022/10,
title={RaVÆn: unsupervised change detection of extreme events using ML on-board satellites.},
author={Růžička V, Vaughan A, De Martini D, Fulton J, Salvatelli V et al.},
journal={Scientific reports},
volume={12},
number={16939},
pages={16939},
publisher={Springer Science and Business Media LLC},
year = "2022"
}
Fast-MbyM: leveraging translational invariance of the fourier transform for efficient and accurate radar odometry
Weston R, Gadd M, De Martini D, Newman P & Posner H (2022), Proceedings of the IEEE International Conference on Robotics and Automation (ICRA 2022), 2186-2192
BibTeX
@inproceedings{fastmbymleverag-2022/7,
title={Fast-MbyM: leveraging translational invariance of the fourier transform for efficient and accurate radar odometry},
author={Weston R, Gadd M, De Martini D, Newman P & Posner H},
booktitle={IEEE International Conference on Robotics and Automation (ICRA 2022)},
pages={2186-2192},
year = "2022"
}
Depth-SIMS: semi-parametric image and depth synthesis
Musat V, De Martini D, Gadd M & Newman P (2022), 2022 International Conference on Robotics and Automation (ICRA), 2388-2394
What goes around: leveraging a constant-curvature motion constraint in radar odometry
Aldera R, Gadd M, De Martini D & Newman P (2022), IEEE Robotics and Automation Letters, 7(3), 7865-7872
The Oxford Road Boundaries Dataset
Suleymanov T, Gadd M, De Martini D & Newman P (2022)
Contrastive learning for unsupervised radar place recognition
Gadd M, De Martini D & Newman P (2022), 2021 20th International Conference on Advanced Robotics (ICAR), 344-349
Unsupervised change detection of extreme events using ML on-board
Ruzicka V, Vaughan A, De Martini D, Fulton J, Salvatelli V et al. (2021)
BibTeX
@inproceedings{unsupervisedcha-2021/12,
title={Unsupervised change detection of extreme events using ML on-board},
author={Ruzicka V, Vaughan A, De Martini D, Fulton J, Salvatelli V et al.},
booktitle={NeurIPS Workshop on Artificial Intelligence for Humanitarian Assistance and Disaster Response Workshop (AI+HADR), 2021},
year = "2021"
}
BoxGraph: semantic place recognition and pose estimation from 3D LiDAR
Pramatarov G, De Martini D, Gadd M & Newman P (2021), Proceedings of IEEE International Conference on Intelligent Robots and Systems, 7004-7011
BibTeX
@inproceedings{boxgraphsemanti-2021/12,
title={BoxGraph: semantic place recognition and pose estimation from 3D LiDAR},
author={Pramatarov G, De Martini D, Gadd M & Newman P},
booktitle={2022 IEEE/RSJ International Conference on Intelligent Robots and Systems},
pages={7004-7011},
year = "2021"
}