Biography
Gadd is a Postdoctoral Research Assistant (PDRA) at the University of Oxford and a Junior Research Fellow at Kellogg College. He works with Professor Paul Newman in the Mobile Robotics Group (MRG), part of the Oxford Robotics Institute (ORI). Gadd originally joined MRG as a student reading for a DPhil in Engineering Science at Keble College. Before arriving in the United Kingdom, he was an undergraduate student at the University of Cape Town, South Africa, where he studied Mechatronics Engineering.
Research Interests
- Robotics,
- Autonomous Vehicles,
- Computer Vision,
- Machine Learning
Research Groups
Current Projects
Sense Assess eXplain (SAX) - acceptably auditable action from autonomous vehicles in formidable environments is only going to be possible with robust sensors and sensing which are nevertheless introspective where unavoidably fallible
Related Academics
Recent Publications
NeuralFloors++: consistent street-level scene generation from BEV semantic maps
Musat V, De Martini D, Gadd M & Newman P (2024), 12872-12879
BibTeX
@inproceedings{neuralfloorscon-2024/12,
title={NeuralFloors++: consistent street-level scene generation from BEV semantic maps},
author={Musat V, De Martini D, Gadd M & Newman P},
booktitle={IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024)},
pages={12872-12879},
year = "2024"
}
What you see is what you get: experience ranking with deep neural dataset-to-dataset similarity for topological localisation
Gadd M, Ramtoula B, De Martini D & Newman P (2024), Experimental Robotics: The 18th International Symposium, 595-607
BibTeX
@inproceedings{whatyouseeiswha-2024/8,
title={What you see is what you get: experience ranking with deep neural dataset-to-dataset similarity for topological localisation},
author={Gadd M, Ramtoula B, De Martini D & Newman P},
booktitle={18th International Symposium on Experimental Robotics (ISER 2023)},
pages={595-607},
year = "2024"
}
Robot-relay:building-wide, calibration-less visual servoing with learned sensor handover networks
Robinson L, Gadd M, Newman P & De Martini D (2024), Experimental Robotics: The 18th International Symposium, 129-140
BibTeX
@inproceedings{robotrelaybuild-2024/8,
title={Robot-relay:building-wide, calibration-less visual servoing with learned sensor handover networks},
author={Robinson L, Gadd M, Newman P & De Martini D},
booktitle={18th International Symposium on Experimental Robotics (ISER 2023)},
pages={129-140},
year = "2024"
}
Masked γ-SSL: learning uncertainty estimation via masked image modeling
Williams DSW, Gadd M, Newman P & De Martini D (2024), 2024 IEEE International Conference on Robotics and Automation (ICRA), 16192-16198
BibTeX
@inproceedings{maskedssllearni-2024/8,
title={Masked γ-SSL: learning uncertainty estimation via masked image modeling},
author={Williams DSW, Gadd M, Newman P & De Martini D},
booktitle={2024 IEEE International Conference on Robotics and Automation (ICRA 2024)},
pages={16192-16198},
year = "2024"
}
VDNA-PR: using general dataset representations for robust sequential visual place recognition
Ramtoula B, De Martini D, Gadd M & Newman P (2024), 2024 IEEE International Conference on Robotics and Automation (ICRA), 15883-15889
BibTeX
@inproceedings{vdnaprusinggene-2024/8,
title={VDNA-PR: using general dataset representations for robust sequential visual place recognition},
author={Ramtoula B, De Martini D, Gadd M & Newman P},
booktitle={2024 IEEE International Conference on Robotics and Automation (ICRA 2024)},
pages={15883-15889},
year = "2024"
}
That's my point: compact object-centric LiDAR pose estimation for large-scale outdoor localisation
Pramatarov G, Gadd M, Newman P & De Martini D (2024), 2024 IEEE International Conference on Robotics and Automation (ICRA), 12276-12282
BibTeX
@inproceedings{thatsmypointcom-2024/8,
title={That's my point: compact object-centric LiDAR pose estimation for large-scale outdoor localisation},
author={Pramatarov G, Gadd M, Newman P & De Martini D},
booktitle={ 2024 IEEE International Conference on Robotics and Automation (ICRA 2024)},
pages={12276-12282},
year = "2024"
}
OORD: the Oxford Offroad Radar Dataset
Gadd M, De Martini D, Bartlett O, Murcutt P, Towlson M et al. (2024), IEEE Transactions on Intelligent Transportation Systems, 25(11), 18779-18790
BibTeX
@article{oordtheoxfordof-2024/8,
title={OORD: the Oxford Offroad Radar Dataset},
author={Gadd M, De Martini D, Bartlett O, Murcutt P, Towlson M et al.},
journal={IEEE Transactions on Intelligent Transportation Systems},
volume={25},
pages={18779-18790},
publisher={IEEE},
year = "2024"
}
Open-RadVLAD: fast and robust radar place recognition
Gadd M & Newman P (2024), 2024 IEEE Radar Conference (RadarConf24)
BibTeX
@inproceedings{openradvladfast-2024/6,
title={Open-RadVLAD: fast and robust radar place recognition},
author={Gadd M & Newman P},
booktitle={2024 IEEE Radar Conference (RadarConf24)},
year = "2024"
}
Mitigating distributional shift in semantic segmentation via uncertainty estimation from unlabeled data
Williams DSW, De Martini D, Gadd M & Newman P (2024), IEEE Transactions on Robotics, 40, 3146-3165
BibTeX
@article{mitigatingdistr-2024/5,
title={Mitigating distributional shift in semantic segmentation via uncertainty estimation from unlabeled data},
author={Williams DSW, De Martini D, Gadd M & Newman P},
journal={IEEE Transactions on Robotics},
volume={40},
pages={3146-3165},
publisher={IEEE},
year = "2024"
}
Watching grass grow: long-term visual navigation and mission planning for autonomous biodiversity monitoring
Gadd M, De Martini D, Pitt L, Tubby W, Towlson M et al. (2024)
BibTeX
@misc{watchinggrassgr-2024/5,
title={Watching grass grow: long-term visual navigation and mission planning for autonomous biodiversity monitoring},
author={Gadd M, De Martini D, Pitt L, Tubby W, Towlson M et al.},
year = "2024"
}
Google Scholar
Awards and Prizes
2013 FirstRand Laurie Dippenaar Scholarship
