Developing autonomous systems – execution and design
In May 2012, former Minister of State for Universities and Science, David Willetts, announced £16m in funding from government and industry for high-profile projects in the Autonomous and Intelligent Systems Programme, aimed at developing vital intelligent autonomous systems.
What was the problem?
As part of this, researchers in the Centre for High-Performance Intelligent Computing (CHIC) at the University of Huddersfield have been developing methods of knowledge engineering for intelligent systems, focusing on two types of autonomy:
• Execution Autonomy: a system carries out a process automatically in unpredictable environments, making decisions without human intervention when necessary.
• Design Autonomy: a system is given goals, but then creates the process itself to be carried out within an external environment.
Benefits of this research
In order to provide an experimental environment to encourage the much needed innovative use of knowledge engineering tools in planning systems, Huddersfield has developed a Graphical Interface for Planning with Objects (GIPO) tool. This was awarded first prize for best tools platform at the International Competition on Knowledge Engineering for Planning and Scheduling (ICKEPS) in Monterey, California, in 2005. Subsequently, GIPO led the way in the development of a new range of knowledge engineering tools for use in the automated planning area.
What did we do?
CHIC is currently in collaboration with the University of Edinburgh on the ground-breaking project, Huddersfield and Edinburgh: Learning and Adaptation Models for Planning (HEdLAMP). This Engineering and Physical Sciences Research Council (EPSRC)-funded project aims to develop the capacity for robotic machines to learn and adapt knowledge in order to make their own plans and decisions. Major industrial partners including BAE Systems, Schlumberger, the National Nuclear Laboratory, Sellafield Ltd, Network Rail, SCISYS, Defence Science and Technology Laboratory (DSTL) and the UK Space Agency are providing over £4m in financial support and technical expertise to support the project. HEdLAMP is already encouraging innovative new ways of thinking in relation to encoding information and processes.
What happened next?
To ensure that the research carried out at the University has an impact on relevant industries, our researchers have engaged with a programme of talks which relates their work to a range of industry professionals. Talks have been delivered to transport professionals as part of academic conferences, technology transfer events and professional group events. This has led to the formation of the Intelligent Mobility: future vision collaboration (iMFV) which works alongside researchers to influence change and behaviour in society’s attitudes to transport mobility.
Professor Lee McCluskey’s research focuses on harnessing artificial intelligence (AI) technologies to manifest design autonomy, in particular autonomic properties such as self-management and adaptation, into systems. He has worked on systems which underlie, control and optimise transport networks, for the benefit of improving efficiency, reducing human error and cutting costs.
As Action Chair for Autonomic Road Transport Support Systems (ARTS), McCluskey leads a consortium of members from universities, consultancies, transport authorities and industry from 24 countries across Europe. The organisation aims to advance state-of-the-art developments in engineering transport technologies in order to address problems in road transportation networks including traffic overload and environmental consequence.