University of Lincoln RIF Studentships 2014 PROJECT DETAILS Project Title Facilitating Individualised Collaboration with Robots (FInCoR) Project Reference RIF2014S-45 Project Summary A PhD position is available in the Lincoln Centre for Autonomous Systems Research (L-CAS), a thriving research centre based at the University of Lincoln. L-CAS is internationally recognised for its applied autonomous systems research, in domains such as manufacturing, agriculture, security, and care. It specialises in the integration of perception, learning, decision-making and control capabilities in autonomous systems such as mobile robots and smart devices. The Centre benefits from new, modern laboratory facilities, access to state-of-the-art robotic hardware, and offers the successful candidate a strong embedding into existing international research projects with the potential to liaise with highly regarded experts in the field. The candidate will be part of an international and ambitious team, and will benefit from excellent support to produce and disseminate original research contributions. The PhD position is offered in the area of long-term adaptation and learning for human-robot collaboration. The project will bring together aspects of machine learning, AI and human-robot interaction, all with strong links to real-world application in manufacturing and care. The successful applicant will be an excellent student with a very good Bachelors or Masters in Computer Science, Electronic Engineering, Mathematics or Physics who is excited about robots and can evidence relevant coding skills (C++/Python/Java/ROS). A background in machine learning, robotics, and/or AI is desirable. The project start date is 1st September 2014. The FInCoR project will investigate novel ways to facilitate individualised humanrobot collaboration through long-term adaptation on the level of joint tasks. This will enable robots to work with human more effectively in scenario such as high value manufacturing and assistive care. Imagine a robot helping to assemble a car’s dashboard more effectively, knowing that it is working with a left-handed person; or a robot assisting an elderly employee in a car factory who is skilled in fitting a speedometer, but requires a third-hand holding the heavy mounting frame in place. Despite significant progress in humanrobot collaboration, today’s robotic systems still lack the ability to adjust to an individual’s needs. FInCoR will overcome this limitation by developing online, in-situ adaptation, putting the “human in the loop”. It will bring together flexible task representations (eg. Markov Decision Processes), machine learning (eg. reinforcement learning), advanced robot perception (eg. body tracking), and robot control (eg. reactive planning) to make progress from pre-scripted tasks to individualised models. These models account for preferences, abilities, and limitations of each individual human through long-term adaptation. Hence, FInCoR will enable processes known from human-human collaboration, such as two colleagues working together and learning more about each other’s strengths, preferences, and strategies, to take place in human-robot teams. In particular, FInCoR sets out the following objectives: to develop a long-term adaptation framework for task collaboration that is governed by learning signals based on measures of performance, comfort, and ergonomics; to implement the adaptation framework in the de-facto standard for robot software “ROS” to ensure effective dissemination of results and maximise impact; to generate high quality outputs from original research; to explore the potential of individualised adaptation in at least two market domains: high-value manufacturing and (assistive) care, and to validate the framework within these domains, with input from international collaboration partners. Supervisory Team 1. Dr Marc Hanheide, Senior Lecturer, School of Computer Science. http://staff.lincoln.ac.uk/mhanheide 2. Prof Tom Duckett, Professor of Computer Sciences, School of Computer Sciences. http://staff.lincoln.ac.uk/tduckett Informal Enquiries For further information on this project please contact Dr Marc Hanheide by email at: mhanheide@lincoln.ac.uk Eligibility All Candidates must satisfy the University’s minimum doctoral entry criteria for studentships of an honours degree at Upper Second Class (2:1) or an appropriate Masters degree or equivalent. A minimum IELTS (Academic) score of 7 (or equivalent) is essential for candidates for whom English is not their first language. Funded Studentships are open to both UK/EU students unless otherwise specified. How to Apply Please send a covering letter outlining your interest and proposed approach (up to 1 page A4) with an accompanying CV to mhanheide@lincoln.ac.uk by close of day on 18th April 2014. Candidates will be notified w/c 5th May of the outcome of the process and if invited to interview, these are anticipated to take place w/c 26h May.