Biography
Dr. Jack Collins is a Postdoctoral Researcher in the Applied AI Lab, a lab within the Oxford Robotics Institute. He is also a research member of Kellogg College. Jack received his Ph.D. degree in robotics from the Queensland University of Technology (QUT), Australia, in 2022, and his B.Eng. (Hons.) degree in mechatronic engineering from QUT in 2017.
During his academic career, Jack has collaborated with leading research institutions such as the Commonwealth Scientific and Industrial Research Organisation (CSIRO) in Australia and the Manufacturing Technology Centre (MTC) in the UK, as well as a number of other academic and industry partners. These collaborations have helped ground his research in real-world problems and applications.
Research Interests
Jack's research is at the intersection of machine learning and robotics, in particular, looking at modelling the world for agents, task planning for long-horizon tasks, and scene representation for agents. He aims to apply his work to real-world robots with the intention of enabling robots to interact and manipulate their environment, much like people can.
Research Groups
Related Academics
Publications
DreamUp3D: object-centric generative models for single-view 3D scene understanding and real-to-sim transfer
Wu Y, Sáez de Ocáriz Borde H, Collins J, Jones OP & Posner I (2024), IEEE Robotics and Automation Letters, 9(4), 3291-3298
BibTeX
@article{dreamupdobjectc-2024/2,
title={DreamUp3D: object-centric generative models for single-view 3D scene understanding and real-to-sim transfer},
author={Wu Y, Sáez de Ocáriz Borde H, Collins J, Jones OP & Posner I},
journal={IEEE Robotics and Automation Letters},
volume={9},
pages={3291-3298},
publisher={IEEE},
year = "2024"
}
RAMP: a benchmark for evaluating robotic assembly manipulation and planning
Collins J, Robson M, Yamada J, Sridharan M, Janik K et al. (2023), IEEE Robotics and Automation Letters, 9(1), 9-16
BibTeX
@article{rampabenchmarkf-2023/11,
title={RAMP: a benchmark for evaluating robotic assembly manipulation and planning},
author={Collins J, Robson M, Yamada J, Sridharan M, Janik K et al.},
journal={IEEE Robotics and Automation Letters},
volume={9},
pages={9-16},
publisher={IEEE},
year = "2023"
}
Leveraging scene embeddings for gradient-based motion planning in latent space
Yamada J, Hung CM, Collins J, Havoutis I & Posner I (2023), 2023 IEEE International Conference on Robotics and Automation (ICRA), 5674-5680
BibTeX
@inproceedings{leveragingscene-2023/7,
title={Leveraging scene embeddings for gradient-based motion planning in latent space},
author={Yamada J, Hung CM, Collins J, Havoutis I & Posner I},
booktitle={2023 IEEE International Conference on Robotics and Automation (ICRA)},
pages={5674-5680},
year = "2023"
}
RAMP: A Benchmark for Evaluating Robotic Assembly Manipulation and Planning
Collins J, Robson M, Yamada J, Sridharan M, Janik K et al. (2023)
BibTeX
@misc{rampabenchmarkf-2023/5,
title={RAMP: A Benchmark for Evaluating Robotic Assembly Manipulation and
Planning},
author={Collins J, Robson M, Yamada J, Sridharan M, Janik K et al.},
year = "2023"
}
Follow the Gradient: Crossing the Reality Gap using Differentiable Physics (RealityGrad)
Collins J, Brown R, Leitner J & Howard D (2021)
BibTeX
@misc{followthegradie-2021/9,
title={Follow the Gradient: Crossing the Reality Gap using Differentiable
Physics (RealityGrad)},
author={Collins J, Brown R, Leitner J & Howard D},
year = "2021"
}
A review of physics simulators for robotic applications
Collins J, Chand S, Vanderkop A & Howard D (2021), IEEE Access, 9, 51416-51431
Traversing the Reality Gap via Simulator Tuning
Collins J, Brown R, Leitner J & Howard D (2020)
BibTeX
@misc{traversingthere-2020/3,
title={Traversing the Reality Gap via Simulator Tuning},
author={Collins J, Brown R, Leitner J & Howard D},
year = "2020"
}
Benchmarking Simulated Robotic Manipulation through a Real World Dataset
Collins J, McVicar J, Wedlock D, Brown R, Howard D et al. (2019)
BibTeX
@misc{benchmarkingsim-2019/11,
title={Benchmarking Simulated Robotic Manipulation through a Real World Dataset},
author={Collins J, McVicar J, Wedlock D, Brown R, Howard D et al.},
year = "2019"
}
Comparing Direct and Indirect Representations for Environment-Specific Robot Component Design
Collins J, Cottier B & Howard D (2019), 00, 2705-2712
Quantifying the Reality Gap in Robotic Manipulation Tasks
Collins J, Howard D & Leitner J (2019), 00, 6706-6712