Reconfigurable Autonomy

Lead Research Organisation: University of Southampton
Department Name: Faculty of Engineering & the Environment

Abstract

As computational and engineering applications become more sophisticated, the need for autonomous systems that can act intelligently without direct human intervention increases. Yet the autonomous control at the heart of many such systems is often ad-hoc and opaque. Since the cost of failure in critical systems is high, a more reliable, understandable and consistent approach is needed. Thus, in this project we aim to provide a rational agent architecture that controls autonomous decision-making, is re-usable and generic, and can be configured for many different autonomous platforms. In partnership with the industrial collaborators we aim to show how such "reconfigurable autonomy" can be achieved in relevant applications.

Publications

10 25 50
publication icon
Aitken J (2014) Adaptation of System Configuration under the Robot Operating System in IFAC Proceedings Volumes

publication icon
Dennis L (2014) Practical verification of decision-making in agent-based autonomous systems in Automated Software Engineering

publication icon
Dennis L (2014) Reconfigurable Autonomy in KI - Künstliche Intelligenz

publication icon
Lincoln N (2013) Autonomous Asteroid Exploration by Rational Agents in IEEE Computational Intelligence Magazine

publication icon
Lincoln N (2012) Natural Language Programming of Complex Robotic BDI Agents in Journal of Intelligent & Robotic Systems

publication icon
Qu H (2016) Verification of logical consistency in robotic reasoning in Robotics and Autonomous Systems

Related Projects

Project Reference Relationship Related To Start End Award Value
EP/J011843/1 01/06/2012 25/10/2012 £489,242
EP/J011843/2 Transfer EP/J011843/1 24/04/2013 23/11/2016 £443,918
 
Description By the end of May 2016 the following has been achieved: 1. Architecture solutions for reconfigurable rational agent architecture has been defined under the ROS/C++ system using a specific BDI cognitive agent architecture similar to but modified relative to the Jason agent programming language.
2. Architecture has been defined under a sEnglish based algorithmic description of agent programming for embedded applications and is to be made open source and publicly available . By 2018 the applicability of the reasoning methodology has been demonstrated to Sellafield Ltd in terms of a robot arm setup at their Workington Inactive Lab: autonomous waste-object selection, decision making what to do with it, handling and packing it without human intervention. In 2018 new results have been developed on the integration of the theory of degradation, adaptation and self-reconfiguration of autonomous robots, currently being published in journals.
Exploitation Route Carried out work with industrial collaborators on demonstration scenarios: 1. NNL/Sellafield : autonomous robot arms reconfiguration for nuclear decommissioning operations with radioactive waste. 2. Mapping out an area with 3D geometric and functional models using a fleet of cooperative quadrotor vehicles . 3. Methods to be applied in the new EPSRC RAIN Hub until March 2021.
Sectors Digital/Communication/Information Technologies (including Software),Environment,Manufacturing, including Industrial Biotechology,Retail,Transport

URL https://www.sheffield.ac.uk/acse/research/groups/asrg/acl/project2
 
Description Academic impact: ROS based self reconfiguring algorithmic system has been published (IFAC World Congress 2014, leading to journal publications). In 2018 we published paper in the IEEE Intelligent System Journal on the application of our techniques developed in this project to autonomous nuclear robotics. Since the close of the project we continued working towards a joint theory of degradation, adaptation and self-reconfiguration of autonomous robots.This research is also a significant input and starting point of several research activities in the new EPSRC RAIN Hub started in October 2017, part of which is Sheffield as funded partner.
Sector Digital/Communication/Information Technologies (including Software),Energy
Impact Types Cultural,Societal

 
Description EPSRC: Robotics Capital Funding
Amount £1,000,000 (GBP)
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Public
Country United Kingdom
Start 03/2014 
End 04/2017
 
Description NNL: autonomous robots for the nuclear industry 
Organisation National Nuclear Laboratory
Country United Kingdom 
Sector Public 
PI Contribution Under our Reconfigurable Autonomy EPSRC project we have been working on robustly operating autonomous robot arms for sorting and segregating radioactive materials. The methods have been demonstrated in the laboratories of the Department of ACSE at Sheffield. The challenge is to make these arms to need little servicing, which is expensive in an active environment. The methods we developed will enable long term operation of the robots to self-recofigure and maintain themselves thereby providing much needed continuous productivity. The methods we developed are of key importance to the future profitability and ultimately the survival of the UK's nuclear decommissioning industry.
Collaborator Contribution They enables us to understand the problems of the industry. They provided us case study for our research in the form of the sort and segregate problem of nuclear materials. Currently there is £30k on offer from Sellafield/NNL to transfer our methods onto concrete industrial arms at Workington.
Impact We have produced methodology demonstrators with the help of this collaboration, which we recorded in videos. We have written as series of academic papers on our robot self-reconfiguration methodologies, where we refer to the applicability and importance of our methods for the nuclear industry.
Start Year 2015