Biography
Driven by an early passion for AI and machine learning in robotics, Ingmar read Electronic Systems Engineering at Aston University before joining Oxford's Department of Engineering Science.
Ingmar's work is frequently covered in the national and international press. In 2014 Ingmar co-founded Oxbotica, a leading provider of mobile autonomy software solutions.
Research Interests
Ingmar leads the Applied Artificial Intelligence Lab (A2I) at Oxford University. He also serves as Deputy Director of the Oxford Robotics Institute, which he co-founded in 2016. Ingmar has a significant track record in designing machine learning approaches (shallow and deep) which address core challenges in AI and machine learning.
His goal is to enable robots to robustly and effectively operate in complex, realworld environments. His research is guided by a vision to create machines which constantly improve through experience. In doing so, Ingmar's work explores a number of intellectual challenges at the heart of robot learning, such as machine introspection in perception and decision making, data efficient learning from demonstration, transfer learning and the learning of complex tasks via a set of less complex ones.
All the while, Ingmar’s intellectual curiosity remains grounded in real-world robotics applications such as autonomous driving, logistics, manipulation and space exploration. In 2014 Ingmar co-founded Oxbotica, a leading provider of mobile autonomy software solutions.
Research Groups
Recent Publications
AutoGraph: Predicting Lane Graphs from Traffic Observations
Zurn J, Posner I & Burgard W (2024), IEEE Robotics and Automation Letters, 9(1), 73-80
RAMP: A Benchmark for Evaluating Robotic Assembly Manipulation and Planning
Collins J, Robson M, Yamada J, Sridharan M, Janik K et al. (2024), IEEE Robotics and Automation Letters, 9(1), 9-16
DreamUp3D: Object-Centric Generative Models for Single-View 3D Scene Understanding and Real-to-Sim Transfer
Wu Y, Saez de Ocariz Borde H, Collins J, Jones OP & Posner I (2024), IEEE Robotics and Automation Letters
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"
}
You Only Look at One: Category-Level Object Representations for Pose Estimation From a Single Example
Goodwin W, Havoutis I & Posner I (2023)
Leveraging Scene Embeddings for Gradient-Based Motion Planning in Latent Space
Yamada J, Hung C-M, Collins J, Havoutis I & Posner I (2023)
DITTO: Offline Imitation Learning with World Models
DeMoss B, Duckworth P, Hawes N & Posner I (2023)
BibTeX
@misc{dittoofflineimi-2023/2,
title={DITTO: Offline Imitation Learning with World Models},
author={DeMoss B, Duckworth P, Hawes N & Posner I},
year = "2023"
}
You Only Look at One: Category-Level Object Representations for Pose Estimation From a Single Example
Goodwin W, Havoutis I & Posner I (2023), Proceedings of Machine Learning Research, 205, 1435-1445
BibTeX
@inproceedings{youonlylookaton-2023/1,
title={You Only Look at One: Category-Level Object Representations for Pose Estimation From a Single Example},
author={Goodwin W, Havoutis I & Posner I},
pages={1435-1445},
year = "2023"
}
Leveraging Scene Embeddings for Gradient-Based Motion Planning in Latent Space
Yamada J, Hung CM, Collins J, Havoutis I & Posner I (2023), Proceedings - IEEE International Conference on Robotics and Automation, 2023-May, 5674-5680
Touching a NeRF: Leveraging Neural Radiance Fields for Tactile Sensory Data Generation
Zhong S, Albini A, Jones OP, Maiolino P & Posner I (2023), Proceedings of Machine Learning Research, 205, 1618-1628
BibTeX
@inproceedings{touchinganerfle-2023/1,
title={Touching a NeRF: Leveraging Neural Radiance Fields for Tactile Sensory Data Generation},
author={Zhong S, Albini A, Jones OP, Maiolino P & Posner I},
pages={1618-1628},
year = "2023"
}