New £1.2 million research project to make robots more trustworthy
Press release issued: 2 July 2013
Bristol Robotics Laboratory (BRL) is part of a new £1.2million project which aims to ensure future robotic systems can be trusted by humans. The Engineering and Physical Sciences Research Council (EPSRC) is funding the three-and-a-half-year project, which will explore how robots can interact with humans in a safe and trustworthy manner.
The Engineering and Physical Sciences Research Council (EPSRC) is funding the three-and-a-half-year project, which will explore how robots can interact with humans in a safe and trustworthy manner.
Robots are increasingly being developed to serve as active ‘helpers’ in situations where humans require assistance, such as personal care robots which help patients during recovery.
Although there has been some research carried out on safety of robotic assistants during interaction with humans, it is still crucial to understand not only whether the robot makes safe moves, but whether it knowingly or deliberately makes unsafe moves.
If human-robot teamwork is to become viable and productive, the humans involved must be fully confident in the robot’s behaviour.
Experts from BRL, a collaborative partnership between the University of Bristol and the University of the West of England (UWE, Bristol), will work with industry partners and colleagues at the Universities of Liverpool and Hertfordshire on the 'Trustworthy Robotic Assistants' (TRA) project.
Bristol University’s Dr Kerstin Eder, the principal investigator for the TRA project at the BRL and Leader of the Verification & Validation for Safety in Robots research theme at the BRL, said: “Safety assurance of robots is an urgent research challenge that must be addressed before many products that already exist in labs can be unlocked for mass production. This requires collaboration of verification experts with roboticists and those who specialize in human-robot interaction, so that a human-centric, holistic approach to safety assurance can be developed.”
‘BERT’, one of the robotic platforms being used on the project, was developed as part of a research project on Cooperative Human Robot Interactive Systems, at BRL. BERT has been used to examine manufacturing scenarios in which BERT collaborated with human colleagues to complete manufacturing tasks, including dynamic component handovers and product manufacture. BERT is based at BRL's custom robot test and evaluation facility, at UWE Bristol.
Professor Tony Pipe, Professor of Robotics and Autonomous Systems at UWE, said: “Working on this new research project with colleagues across the UK will enable us to tackle the crucial issue of developing robotic systems which can work safely with humans. This is a vital step in developing robots for a whole range of functions for the future, where they will be useful to humans.”
The project involves teams from the University of Liverpool’s Centre for Autonomous Systems Technology (led by Professor Michael Fisher and Dr Clare Dixon), the University of Hertfordshire’s Adaptive Systems Research Group (led by Professor Kerstin Dautenhahn), the BRL, as well as industrial partners, including the British Automation and Robot Association (BARA) and RU Robots Limited.
Professor Michael Fisher, principal investigator at Liverpool and Director of the University's Centre for Autonomous Systems Technology, said: "The assessment of robotic trustworthiness has many facets, from the safety analysis of robot behaviours, through physical reliability of interactions, to human perceptions of such safe operation."
Liverpool’s researchers are internationally recognised for their research on logic, formal analysis, and the foundations of autonomy and, both within the multidisciplinary Centre for Autonomous Systems Technology and within the "Trustworthy Robotic Assistants" project, their role is to provide a rigorous formal basis for developing reliable, safe and trustworthy autonomous systems.
About Bristol Robotics Lab:
The BRL is a collaborative research partnership between the University of Bristol and UWE Bristol (the University of the West of England). It carries out cutting edge research programmes focused on the development of autonomous robot systems. The BRL’s vision is to transform robotics by pioneering advances in autonomous robot systems through the elucidation of the underpinning mechanisms required to create robot systems, which behave intelligently without human supervision.
Researchers at the BRL are involved in projects funded by a range of national and international sources studying Human-Robot interaction, collective robotics, aerial robotics, neuro-inspired control, haptics, control systems, energy harvesting and self-sustaining systems, rehabilitation robotics, soft robotics and biomedical systems.
The BRL also has strong links with the emerging advanced robotics manufacturing community, and also has regular contact with larger international organisations that have a robotics interest.
The TRA project fits into the scope of the Safe and Trustworthy Autonomous Assistive Robots (STAARs) workshops, initiated by Dr Kerstin Eder, at the University of Bristol.
For further information, please visit www.brl.ac.uk
About the Engineering and Physical Sciences Research Council (EPSRC):
The Engineering and Physical Sciences Research Council (EPSRC) is the UK’s main agency for funding research in engineering and the physical sciences. The EPSRC invests around £800 million a year in research and postgraduate training, to help the nation handle the next generation of technological change.
The areas covered range from information technology to structural engineering, and mathematics to materials science. This research forms the basis for future economic development in the UK and improvements for everyone’s health, lifestyle and culture.
EPSRC also actively promotes public awareness of science and engineering. EPSRC works alongside other Research Councils with responsibility for other areas of research. The Research Councils work collectively on issues of common concern via Research Councils UK.