The deadline for application is January 2 2020.

The successful candidate will lead the School���s effort towards the development of human-aware AI for autonomous driving, and will be soon joined by at least one PhD student.

The project concerns the design and development of novel ways for robots and autonomous machines to interact with humans in a variety of emerging scenarios, with a focus on autonomous driving. We believe novel, disruptive applications of AI require neuroscience-inspired forms of communication between humans and machines much beyond the current level of sophistication. Smart cars need to understand that children and construction workers have different reasoning processes that lead to very different observable behaviour, in order to blend in with the road as a human-centred environment. Morally and socially appropriate behaviour is key to build trust and lead to acceptance from the public.

The Fellow will work to design and implement a prototype but complete pipeline in a simulated scenario, including: (i) the design of theory of mind simulations allowing smart cars to understand the reasoning and intentions of other drivers and pedestrians; (ii) the making of decisions based on the results of these simulations; (iii) the actual control and path planning required to pursue the best course of action, with demonstration in a simulated environment.

They will also coordinate the efforts of the three groups in the area by supervising MSc and final year students working on the subject, and liaising with our partners in Oxford, Cambridge and elsewhere.

As the project concerns artificial intelligence, mobile robotics and engineering aspects, the Fellow will work jointly with the Visual Artificial Intelligence, Cognitive Robotics and Autonomous Driving research groups, led by Prof Fabio Cuzzolin, Dr Matthias Rolf and Dr Andrew Bradley. The Visual Artificial Intelligence Laboratory (http://cms.brookes.ac.uk/staff/FabioCuzzolin/) is a thriving unit projected to comprise 25+ members in 2019, which has established itself as one of the top research groups in the world in deep learning for action detection, conducting work at the current boundaries of human action recognition.

The Engineering section has a strong reputation in motorsports and engagement with F1 teams, as demonstrated by Oxford Brookes Racing having been crowned Class 1 Runner Up in the 2018 Formula Student competition. The three groups can provide equipment including a network of GPU servers for a total of around 30 cards, a significant number of humanoid robots (NAO, Baxter, Robothespian) as well as autonomous driving equipment and software.

In 2019 Oxford Brookes, led by Bradley and assisted by Cuzzolin, came 3rd place overall in the first edition of the IMEC-sponsored Formula Student ��� AI competition:

https://www.imeche.org/events/formula-student/team-information/fs-ai

A new dataset in Road Event and Activity Detection (RoAD), the first in the world of its kind, is in the process of being released as a challenge to IROS 2020 and ECCV 2020 (https://arxiv.org/abs/1807.11332).

You are encouraged to contact Prof Cuzzolin at fabio.cuzzolin@brookes.ac.uk for more information and informal feedback on your application.

To formally apply, please follow the instructions provided here:

https://www.jobs.ac.uk/job/BXA814/research-fellow-in-ai-for-autonomous-driving