Number Understanding Modelling in Behavioural Embodied Robotic Systems

Mathematical competence can endow robots of the necessary capability for abstract and symbolic processing, which is required for improving their cognitive performance and their social interaction with human beings. But so far, only few attempts have been made to apply mathematical cognition in robots.

The objective of the NUMBERS project is to construct a novel artificial cognitive model of mathematical cognition by imitating human like learning approaches for developing number understanding. This will provide a novel tool for developmental psychology and neuroscience research on the development of mathematical abilities in children.

The objective will be achieved through a highly interdisciplinary research program that will take advantage of the collaboration of leading academics in the fields involved, prof. Cangelosi (Cognitive Developmental Robotics), Plymouth University, and prof. McClelland (Computational Psychology), Stanford University, USA, and the technical support of an industrial partner (NVIDIA Corporation, USA and UK).

The NUMBERS' research activities will exploit the cutting-edge facilities offered by Sheffield Robotics, a joint initiative between the University of Sheffield and Sheffield Hallam University, which will host the project. Indeed, the model will be integrated with one of the most advanced child-like robotic platform (the "iCub") and, therefore, validated through realistic experiments, resembling scientific experiments of mathematical cognition in children.

The validation of the novel model of the numerical cognition in interactive robotic experiments will constitute a proof of concept of the enhanced capabilities offered by a modular approach to bio-inspired artificial intelligence architectures. Furthermore, an optimised implementation for mobile devices will be realised in order to downsize space and power requirements for the computation, increasing application opportunities.

This foundational research will provide the methodological basis and cognitively plausible engineering principles for the next generation of socially interactive robots, mimicking advanced capabilities of the human intelligence for real understanding and interaction with the external world. Results will help the design of more efficient cognitive robotic systems capable of learning abstract symbolic number processing in a more flexible and ecological manner.

The human-like learning and interaction are characteristics that might allow people to more easily identify the desired social overture that the robot is making, or facilitate the transfer of skills learned in human-human interactions to human-robot encounters. This envisioned humanization will positively affect the acceptance of robots in social environments, as they will be perceived as less dangerous, increasing the socio-economic applications of future robots that can take on tasks once thought too delicate or uneconomical to automate. This is particularly relevant in the fields of social care, companionship, therapy, domestic assistance, entertainment, and education.

The NUMBERS project is based on a highly interdisciplinary approach and has an important scientific and technological bearing that will have a significant impact in the technological fields (e.g. service robotics and HRI for interactive systems, GPU accelerated parallel computing, robotics engineering) covered by the project.

From a socio-economic point of view, the technological advances expected will facilitate the design of novel control systems suitable for a wide range of commercial interactive system applications (e.g. social robots, smart intelligent devices, speech interfaces, autonomous and intelligent-assisted transport vehicles). Indeed, the NUMBERS project aims to be one seed for future UK industrial leadership in the emerging social robotics industry, as human-like cognition and interaction will drastically increase the acceptance of robots in social environments, widening future applications, such as care for elderly, child education, entertainment, and domestic use.
In particular, in the field of social care and innovation, the project foresees synergies with the H2020 MSCA CARER-AID project, which has the same host institution (SHU) and supervisor (PI). These synergies will allow extending the contribution to the assessment and therapeutic technologies for cognitively disabled children.

From an industrial point of view, the project will also contribute towards widening the application of deep learning technologies that are currently one of the most vital pieces of work in computing industry of today. Indeed, top industry players like NVIDIA, Google, and Microsoft are strongly investing in expanding this technology for their future products. The sponsorship for the NUMBERS project by the NVIDIA Corporation is evidence of the interest and offers a great opportunity for collaborating towards the development of a profitable technology for the future robotics applications in social environments. In addition, embedded microchip design houses, such as ARM Ltd, can profit from the targeted optimisation of the model for portable devices, which can be more likely to be integrated into mobile socially interactive robotic platforms.

For knowledge transfer into industries, the PI will communicate the project ideas and results to the NVIDIA GTC conferences which can allow for extending the project's impact by interacting with software developers, researchers, and technologists from some of the top companies, universities, research firms, and government agencies from around the world. The PI will organise an Industrial Open House, inviting delegates from NVIDIA Corporation, ARM Ltd and UK robotics companies, e.g. RU Robots Ltd, AA Robotics, Engineered Arts Ltd, and Shadow Robotics.

Public Engagement is one of the objectives of the present project, as more information is needed to overcome the scepticism that currently regards the use of robots in the social context. This will be achieved taking all the available opportunities, such as SHU open days, Sheffield Robotics outreach events and during the UK robotics week.

A dedicated project website will be accelerating dissemination and communication away from academic publications and public events to all relevant parties. An extensive online resource will include videos of the experiments and demonstrators of the advanced robot behaviours, presentations, highlights from publications. The software developed within the project will be available open source through the project website.