The overall aim of the project is the development of automated tools for automatic spatio-temporal analysis and understanding of human subtle facial behaviour from 4D facial information (i.e. 3D high-quality video recordings of facial behaviour). Two exemplar applications related to security issues will be specifically addressed in this proposal: (a) person verification (i.e. using facial behaviour as a biometric trait), and (b) deception indication. The importance of non-obtrusive person verification and deception indication is undisputable - every day, thousands of people go through airport security checkpoints, border crossing checkpoints, and other security screening points. Automated, unobtrusive monitoring and assessing of deceptive behaviour will form a valuable tool for end users, such as police, justice and prison services. This is in particular important as currently only informal interpretations for detecting deceptive behaviour are used. In addition, the development of alternative methods for person verification that are not based on physical traits only but on behavioural, easily observable traits like facial expressions, would be of great value for the development of multimodal biometric system. Such multi-modal biometric systems will be of great interested to government agencies such as the Home Office or the UK Border agency. For automatic deception indication we propose to develop methodologies for detecting 4D micro-expressions and their dynamics being typical of deceptive behaviour as reported by research in psychology. For automatic person identification we propose to increase the robustness of static face- image-based verification systems by including facial dynamics as an additional biometric trait. The underlying motivation is that the dynamic 4D facial behaviour is very difficult to imitate and , hence, it has natural resilience against spoof attacks. The project focuses on 3D video recordings rather than on 2D video recordings of facial behaviour due to two main reasons: (1) increased robustness to changes in head-pose, and (2) ability to spot subtle changes in the depth of facial surface such as jaw clench and tremor appearance on the cheeks, which are typical of deceptive behaviour and cannot be spotted in 2D images. The research on 3D facial dynamics is now made possible by the tremendous advance of sensors and devices for the acquisition of 3D face video recordings. The core of the project will deal with both the development of 4D-FAB research platform containing tools for human subtle facial behaviour analysis in 4D videos and the development of annotated data repository consisting of two parts: (1) annotated 4D recordings of deceptive and truthful behavior, and (2) annotated 4D recordings of subjects uttering a sentence, deliberately displaying certain facial actions and expressions, and spontaneously displaying certain facial actions and expressions. The work plan is oriented around this central goal of developing 4D-FAB technology and is carried out in 3 work packages described in the proposal. A team of 3 Research Associates (RAs), led by the PIs, and having the background in computer vision and machine learning, will develop 4D-FAB technology. The team will be closely assisted by 6 members of the Advisory Board: Prof. Burgoon, University of Arizona, advising on psychology of deception and credibility Prof. Cohn, Pittsburgh University / Carnegie Mellon University, advising on face perception and facial behaviometrics Prof. Nunamaker, Director of BORDERS, US Nat'l Center for Border Security and Immigration, advising on making 4D-FAB useful for end users in security domain Dr Hampson, Head of Science & Technology, OSCT, Home Office, advising on making 4D-FAB useful for end users Dr Cohen, Director of United Technologies Research Centre Ireland, advising on making 4D-FAB useful for end users Dr Urquhart, CEO of Dimensional Imaging, advising on 4D recording setup design

Robots will revolutionise the world's economy and society over the next twenty years, working for us, beside us and interacting with us. The UK urgently needs graduates with the technical skills and industry awareness to create an innovation pipeline from academic research to global markets. Key application areas include manufacturing, assistive and medical robots, offshore energy, environmental monitoring, search and rescue, defence, and support for the aging population. The robotics and autonomous systems area has been highlighted by the UK Government in 2013 as one the 8 Great Technologies that underpin the UK's Industrial Strategy for jobs and growth. The essential challenge can be characterised as how to obtain successful INTERACTIONS. Robots must interact physically with environments, requiring compliant manipulation, active sensing, world modelling and planning. Robots must interact with each other, making collaborative decisions between multiple, decentralised, heterogeneous robotic systems to achieve complex tasks. Robots must interact with people in smart spaces, taking into account human perception mechanisms, shared control, affective computing and natural multi-modal interfaces.Robots must introspect for condition monitoring, prognostics and health management, and long term persistent autonomy including validation and verification. Finally, success in all these interactions depend on engineering enablers, including architectural system design, novel embodiment, micro and nano-sensors, and embedded multi-core computing. The Edinburgh alliance in Robotics and Autonomous Systems (EDU-RAS) provides an ideal environment for a Centre for Doctoral Training (CDT) to meet these needs. Heriot Watt University and the University of Edinburgh combine internationally leading science with an outstanding track record of exploitation, and world class infrastructure enhanced by a recent £7.2M EPSRC plus industry capital equipment award (ROBOTARIUM). A critical mass of experienced supervisors cover the underpinning disciplines crucial to autonomous interaction, including robot learning, field robotics, anthropomorphic & bio-inspired designs, human robot interaction, embedded control and sensing systems, multi-agent decision making and planning, and multimodal interaction. The CDT will enable student-centred collaboration across topic boundaries, seeking new research synergies as well as developing and fielding complete robotic or autonomous systems. A CDT will create cohort of students able to support each other in making novel connections between problems and methods; with sufficient shared understanding to communicate easily, but able to draw on each other's different, developing, areas of cutting-edge expertise. The CDT will draw on a well-established program in postgraduate training to create an innovative four year PhD, with taught courses on the underpinning theory and state of the art and research training closely linked to career relevant skills in creativity, ethics and innovation. The proposed centre will have a strong participative industrial presence; thirty two user partners have committed to £9M (£2.4M direct, £6.6M in kind) support; and to involvement including Membership of External Advisory Board to direct and govern the program, scoping particular projects around specific interests, co-funding of PhD studentships, access to equipment and software, co-supervision of students, student placements, contribution to MSc taught programs, support for student robot competition entries including prize money, and industry lead training on business skills. Our vision for the Centre is as a major international force that can make a generational leap in the training of innovation-ready postgraduates who are experienced in deployment of robotic and autonomous systems in the real world.

Robots and autonomous systems (RAS) will revolutionise the world's economy and society for the foreseeable future, working for us, beside us and interacting with us. The UK urgently needs graduates with the technical skills and industry awareness to create an innovation pipeline from academic research to global markets. Key application areas include manufacturing, construction, transport, offshore energy, defence, and health and well-being. The recent Industrial Strategy Review set out four Grand Challenges that address the potential impact of RAS on the economy and society at large. Meeting these challenges requires the next generation of graduates to be trained in key enabling techniques and underpinning theories in RAS and AI and be able to work effectively in cross-disciplinary projects. The proposed overarching theme of the CDT-RAS can be characterised as 'safe interactions'. Firstly, robots must safely interact physically with environments, requiring compliant manipulation, active sensing, world modelling and planning. Secondly, robots must interact safely with people either in face-to-face natural dialogue or through advanced, multimodal interfaces. Thirdly, key to safe interactions is the ability for introspective condition monitoring, prognostics and health management. Finally, success in all these interactions depends on foundational interaction enablers such as techniques for vision and machine learning. The Edinburgh Centre for Robotics (ECR) combines Heriot-Watt University and the University of Edinburgh and has shown to be an effective venue for a CDT. ECR combines internationally leading science with an outstanding track record of exploitation, and world class infrastructure with approximately £100M in investment from government and industry including the National ROBOTARIUM. A critical mass of over 50 experienced supervisors cover the underpinning disciplines crucial to RAS safe interaction. With regards facilities, ECR is transformational in the range of robots and spaces that can be experimentally configured to study both the physical interaction through robot embodiment, as well as, in-field remote operations and human-robot teaming. This, combined with supportive staff and access to Project Partners, provides an integrated capability unique in the world for exploring collaborative interaction between humans, robots and their environments. The reputation of ECR is evidenced by the additional support garnered from 31 industry Project Partners, providing an additional 23 studentships and overall additional support of approximately £11M. The CDT-RAS training programme will align with and further develop the highly successful, well-established CDT-RAS four-year PhD programme, with taught courses on the underpinning theory and state of the art and research training, closely linked to career relevant skills in creativity, RI and innovation. The CDT-RAS will provide cohort-based training with three graduate hallmarks: i) advanced technical training with ii) a foundation international experience, and iii) innovation training. Students will develop an assessed learning portfolio, tailored to individual interests and needs, with access to industry and end-users as required. Recruitment efforts will focus on attracting cohorts of diverse, high calibre students, who have the hunger to learn. The single-city location of Edinburgh enables stimulating, cohort-wide activities that build commercial awareness, cross-disciplinary teamwork, public outreach, and ethical understanding, so that Centre graduates will be equipped to guide and benefit from the disruptions in technology and commerce. Our vision for the CDT-RAS is to build on the current success and ensure the CDT-RAS continues to be a major international force that can make a generational leap in the training of innovation-ready postgraduates, who will lead in the safe deployment of robotic and autonomous systems in the real world.