How do you grasp a bottle of milk, nestling behind some yoghurt pots, within a cluttered fridge? Whilst humans are able to use visual information to plan and select such skilled actions with external objects with great ease and rapidity - a facility acquired in the history of the species and as a child develops - *robots struggle*. Indeed, whilst artificial intelligence has made great leaps in beating the best of humanity in tasks such as chess and Go, the planning and execution abilities of today's robotic technology is trumped by the average toddler. Given the complex and unpredictable world within which we find ourselves situated, these apparently trivial tasks are the product of highly sophisticated neural computations that generalise and adapt to changing situations: continually engaging in a process of selecting between multiple goals and action options. Our aim is to investigate how such computations could be transferred to robots to enable them to manipulate objects more efficiently, in a more human-like way than is presently the case, and to be able to perform manipulation presently beyond the state of the art. Let us return to the fridge example: You need to first decide what yoghurt pot is best to remove to allow access to the milk bottle and then generate the appropriate movements to grasp the pot safely- the *pre-contact *phase of prehension. You then need to decide what type of forces to apply to the pot (push it to the left or the right, nudge it or possibly lift it up and place the pot on another shelf etc) i.e. the *contact* phase. Whilst these steps happen with speed and automaticity in real time, we will probe these processes in laboratory controlled situations to systematically examine the pre-contact and contact phases of prehension to determine what factors (spatial position, size of pot, texture of pot etc) bias humans to choose one action (or series of actions) over other possibilities. We hypothesise that we can extract a set of high level rules, expressed using qualitative spatio-temporal formalisms which can capture the essence of such expertise, in combination with more quantitative lower-level representations and reasoning. We will develop a computational model to provide a formal foundation for testing hypotheses about the factors biasing behaviour and ultimately use this model to predict the behaviour that will most probably occur in response to a given perceptual (visual) input in this context. We reason that a computational understanding of how humans perform these actions can bridge the robot-human skill gap. State-of-the-art robot motion/manipulation planners use probabilistic methods (random sampling e.g. RRTs, PRMs, is the dominant motion planning approach in the field today). Hence, planners are not able to explain their decisions, similar to the "black box" machine learning methods mentioned in the call which produce inscrutable models. However, if robots can generate human-like interactions with the world, and if they can use knowledge of human action selection for planning, then this would allow robots to explain why they perform manipulations in a particular way, and also facilitate "legible manipulation" - i.e. action which is predictable by humans since it closely corresponds to how humans would behave, a goal of some recent research in the robotics community. The work will shed light on the use of perceptual information in the control of action - a topic of great academic interest and simultaneously have direct relevance to a number of practical problems facing roboticists seeking to control robots working in cluttered environments: from a robot picking items in a warehouse, to novel surgical technologies requiring discrimination between healthy and cancerous tissue.

The proposed project is a collaboration between the Universities of Sheffield and Edinburgh, the BBC (CBeebies), children's media industry partners, the companies Foundling Bird and Dubit, and Monteney Primary School in Sheffield. The project has been co-constructed amongst these partners in order to address a gap in knowledge with regard to preschool children's (aged from birth to five) use of tablet apps. The aim of the project is to develop understanding about preschool children's use of tablet apps and identify the ways in which the use of apps may promote play and creativity, and to use this information to inform future app development and future purchases of apps by parents/ caregivers and early years settings/ schools. The project has four distinct but interrelated phases. In the first phase of the project, a survey of 2000 parents of children from birth to 5 will be undertaken by Dubit. Little is known about the most frequently used tablet apps by young children in the UK and the survey will provide information about the extent of children's use of tablet apps, the type of apps used and parents' motivation for buying specific apps. In Phase 2 of the study, six case studies will be undertaken of families with children aged from birth to 5 who use tablet apps. The case studies will develop understanding about parents' motivation for purchasing specific apps and children's responses to a range of apps in terms of their promotion of play and creativity. Four visits will be made to each family in which parents will be interviewed about their children's use of tablet apps and children will be observed using their favourite apps. In the third phase of the project, workshop sessions will be undertaken in a Foundation Stage 1 class and a Foundation Stage 2 class involving children aged three to five, in which children will be observed using a range of apps. The extent to which the apps promote play and creativity will be reviewed. The apps that will be the focus for Phase 3 of the study will be identified as the top six named favourites of children, as recorded in the Phase 1 survey. In addition, children will also be observed using four augmented reality apps identified as being of interest by the research team. In Phase 4, we will analyse the apps used in Phase 3 in order to identify which features were successful in promoting play and creativity The project will have a range of impacts. The information developed regarding this range of apps will be of value for the children's media industry partners involved in the project. The project will inform future development of apps by the children's media industry. In addition, the project will inform educational provision for apps in the early years through the development of a set of criteria for choosing apps and guidelines for practice. Finally, the project will provide guidance for parents and caregivers in terms of selecting apps to be used with young children and in using them to support play and creativity.

Digital games have extraordinary economic, social and cultural impact. The industry is one of the fastest-growing in the world, larger than film or music, with revenues expected to increase from $138 billion in 2018 to $180 billion by 2021. 2.6 billion people worldwide play digital games (21 million in the UK), with an average age of 35 and equal numbers of females and males. The Wellcome Trust-sponsored game Senua's Sacrifice, made in the UK, won 5 Baftas for its interactive and educational portrayal of psychosis. The UK games industry is a global leader - UK game sales are valued at £4.3bn with 12,000 people directly employed. The games industry is innovative and hungry for innovation - recent research breakthroughs in Artificial Intelligence (AI) and Machine Learning (ML) have arisen through games research undertaken at Google DeepMind in the UK. Rolls Royce makes better jet engines using 3D technology pioneered in games. Games are leading the "data and AI revolution" of HM Government's 2017 Industrial Strategy. Games have become a massive lever for social good through applied games for health, education, and science. The mobile game Pokémon Go added 144 billion steps to physical activity in the US alone. The Alzheimer's Research-funded Sea Hero Quest game collected data equivalent to 9,400 years of dementia lab data within 6 months. The EPSRC Centre for Doctoral Training in Intelligent Games and Game Intelligence (IGGI) first received funding in 2014, and has since been a huge success: raising the level of research innovation in games, with the highest-possible ratings in our EPSRC mid-term review. The next phase of IGGI will inject 60+ PhD-qualified research leaders and state of the art research advances into the UK games industry. The two core themes of IGGI are: (1) Intelligent Games: increasing the flow of research into games. IGGI PhD research in topics such as AI, data science, and design will empower the UK games industry to create more innovative and entertaining games. IGGI research has already enhanced the experience for millions of game players. IGGI will create engaging AI agents that are enjoyable to interact with, tackling fundamental challenges for the future of work and society that go beyond games. IGGI will spearhead new AI techniques that augment human creativity by automatically 'filling in the details' of human sketches. (2) Game Intelligence: increasing the use of intelligence from games to achieve scientific and social goals. Every action in a digital game can be logged, creating huge data sets for behavioural science. For example, current IGGI students have assessed traits such as IQ, agreeableness, or attention from large game datasets. IGGI students will investigate more intelligent, adaptive games for education and to improve mental health. IGGI will maximize the enormous opportunity for scientific and social impact from games by laying the research groundwork for further data-driven applied games for health, science, and education. IGGI will massively advance these research themes, and train 60+ PhD students to be future research leaders. To accomplish this, our updated training programme and 60+ research supervisors will provide students with rigorous training and hands-on experience in AI, programming, game design, research methods, and data science, with end user and industry engagement from day one. Recruiting and empowering a diverse student cohort to promote equality, diversity, and inclusion through games, IGGI will drive positive culture change in industry and academia. Students will work with leading UK experts to co-create and disseminate standards for responsible games innovation. Directly working with the UK games industry through placements, workshops, game development challenges, and an annual conference, they will advance research knowledge and translate it into social, cultural and economic impact.