Verifiable Autonomy
Lead Research Organisation:
University of the West of England
Department Name: Bristol Robotics Laboratory
Abstract
Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.
People |
ORCID iD |
| Alan Winfield (Principal Investigator) |
Publications
Blum C
(2018)
Simulation-Based Internal Models for Safer Robots
in Frontiers in Robotics and AI
Bremner P
(2019)
On Proactive, Transparent, and Verifiable Ethical Reasoning for Robots
in Proceedings of the IEEE
Dennis LA
(2015)
Towards Verifiably Ethical Robot Beheviour
Fisher M
(2017)
Engineering moral machines
in Informatik Spectrum
Nkuba MR
(2023)
Factors associated with farmers' use of indigenous and scientific climate forecasts in Rwenzori region, Western Uganda.
in Regional environmental change
Vanderelst D
(2016)
From Animals to Animats 14
Vanderelst D
(2017)
Rational imitation for robots: the cost difference model
in Adaptive Behavior
Vanderelst D
(2018)
An architecture for ethical robots inspired by the simulation theory of cognition
in Cognitive Systems Research
| Description | We have discovered that in principle it is possible to build an ethical robot. We also demonstrated, in 2014, for the first time a robot facing an ethical dilemma, as reported by the BBC, New Scientist, Nature News, and elsewhere. The core of our ethical robot is a simulation-based internal model - a powerful mechanism enabling a robot to predict the future, see Winfield and Hafner (2018) Anticipation in Robotics, Springer Handbook of Anticipation. We have shown that the same simulation-based internal model can be used (1) to build a robot capable of the imitation of goals, see Vanderelst and Winfield (2017), Rational imitation for robots: the cost difference model, Adaptive Behaviour; (2) to build safer robots, see Blum, Winfield and Hafner (2018), Simulation-based internal models for safer robots, Frontiers in Robotics and AI, and (3) as an embodied computational model for Theory of Mind, see Winfield (2018) Experiments in Artificial Theory of Mind, Frontiers in Robotics and AI. We have also recently shown that the ethical reasoning in the same architecture for ethical robots can be formally proven to be correct, in Bremner, Dennis, Fisher and Winfield (2019) On proactive, transparent and verifiable ethical reasoning for robots, in Proceedings of the IEEE. |
| Exploitation Route | We have shown the potential of robots able to predict the consequences of their own and others actions. This opens the way toward robots that are much safer than at present. An unexpected outcome of this work is that the same simulation-based internal model used in our ethical robots can be used in an 'explainer' system, i.e. to enable a robot to answer questions such as 'why did you just do that?' or 'what would you do if ... ?'. This idea will be developed and tested in our new five-year EPSRC funded project RoboTIPS: Developing Responsible Robots for the Digital Economy. |
| Sectors | Aerospace, Defence and Marine,Communities and Social Services/Policy,Creative Economy,Digital/Communication/Information Technologies (including Software),Healthcare,Leisure Activities, including Sports, Recreation and Tourism,Culture, Heritage, Museums and Collections |
| URL | http://alanwinfield.blogspot.com/search/label/Verifiable%20Autonomy |
| Description | Our work in developing ethical robots has resulted in significant press and media interest, invitations to give public lectures - including at the World Economic Forum 2016 - and hence public debate about the merits and potential value of ethical robots. In turn that led to an invitation to join the WEF Global AI Council. The project has also helped to establish the field of experimental machine ethics. Our leadership in machine ethics led to an invitation for Alan Winfield to lead guest edit a special issue of the Proceedings of the IEEE, on Machine Ethics, see https://proceedingsoftheieee.ieee.org/view-recent-issues/march-2019/ |
| First Year Of Impact | 2016 |
| Sector | Other |
| Impact Types | Cultural,Societal |
| Description | Chair of IEEE Standards Association working group P7001 drafting a new standard on Transparency in Autonomous Systems |
| Geographic Reach | Multiple continents/international |
| Policy Influence Type | Membership of a guideline committee |
| URL | http://sites.ieee.org/sagroups-7001/ |
| Description | Member of British Standards Institute working group on Robot Ethics, part of technical committee AMT/010 on robotics and robot devices |
| Geographic Reach | National |
| Policy Influence Type | Membership of a guideline committee |
| Impact | The work resulted in publication of a new British Standard - BS8611:2016 Robots and robotic devices. Guide to the ethical design and application of robots and robotic systems, in April 2016. |
| URL | http://shop.bsigroup.com/ProductDetail?pid=000000000030320089 |
| Description | RoboTIPS: Developing Responsible Robots for the Digital Economy |
| Amount | £1,723,460 (GBP) |
| Funding ID | EP/S005099/1 |
| Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
| Sector | Public |
| Country | United Kingdom |
| Start | 12/2018 |
| End | 11/2023 |
| Description | Verifiable Autonomy collaboration |
| Organisation | University of Liverpool |
| Department | Department of Computer Science |
| Country | United Kingdom |
| Sector | Academic/University |
| PI Contribution | We have contributed work on ethical robots to this collaboration. |
| Collaborator Contribution | Partner Liverpool has contributed work on verification. |
| Impact | One conference paper to date: Towards Verifiably Ethical Robot Behaviour (2015) |
| Description | Verifiable Autonomy collaboration |
| Organisation | University of Sheffield |
| Country | United Kingdom |
| Sector | Academic/University |
| PI Contribution | We have contributed work on ethical robots to this collaboration. |
| Collaborator Contribution | Partner Liverpool has contributed work on verification. |
| Impact | One conference paper to date: Towards Verifiably Ethical Robot Behaviour (2015) |
| Description | Article in Nautilus magazine |
| Form Of Engagement Activity | A magazine, newsletter or online publication |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Public/other audiences |
| Results and Impact | Brian Gallagher wrote an article called "Robots Show Us Who We Are: What can we learn from machines with imagination and culture?" in online magazine Nautilus, which covers our research in robots with simulation based internal models. |
| Year(s) Of Engagement Activity | 2022 |
| URL | https://nautil.us/robots-show-us-who-we-are-238448/ |
| Description | Blog post reporting on this project (recurring) |
| Form Of Engagement Activity | Engagement focused website, blog or social media channel |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Public/other audiences |
| Results and Impact | A series of 13 blog posts spanning 6 years chronicled major milestones and outcomes of project work in a way accessible to general audiences. These blogposts proved to be valuable to journalists, students and laypeople interested in the project and wanting to find out more. The blogposts also prompted invitations to give talks. |
| Year(s) Of Engagement Activity | 2013,2014,2015,2016,2017,2018 |
| URL | https://alanwinfield.blogspot.com/search/label/Verifiable%20Autonomy |
| Description | DAVOS 2016 |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Other audiences |
| Results and Impact | Invitation by NATURE to present work on Ethical Robots as part of an IdeasLab at the World Economic Forum 2016, in Davos Switzerland. |
| Year(s) Of Engagement Activity | 2016 |
| URL | https://www.youtube.com/watch?v=qZ2zHL4x5r8&index=3&list=PL7m903CwFUgkv0-OOrqJaZNgO4_AhWJWG |
| Description | Invited public talk and panel by Alan Winfield - Oxford Brookes' AI Festival |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Public/other audiences |
| Results and Impact | Prof. Alan Winfield gave a talk entitled "How to make an ethical robot, and why we probably shouldn't" at Oxford Brookes' AI Festival (online) on 21 February 2023 |
| Year(s) Of Engagement Activity | 2023 |
| URL | https://www.brookes.ac.uk/about-brookes/events/2023/02/festival-of-ai |
| Description | Invited talk at Royal Society workshop |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Other audiences |
| Results and Impact | I was invited to give a talk at the Royal Society scientific meeting on The emergence of collective knowledge and cumulative culture in animals, humans and machines, held at the Royal Society London, 13-14 March 2022. |
| Year(s) Of Engagement Activity | 2022 |
| URL | https://royalsociety.org/science-events-and-lectures/2022/03/knowledge-culture/ |
| Description | Invited talk at the Bristol conference on the Science and Philosophy of Imagination |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | I gave an invited talk entitled 'Robots with an Artificial Imagination' at the University of Bristol hosted conference on the Science and Philosophy of Imagination. on 17 September 2021. |
| Year(s) Of Engagement Activity | 2021 |
| URL | https://sites.google.com/view/science-philosophy-imagination/home |
| Description | Keynote lecture at the Rutherford Space Conference, December 2019 |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Alan Winfield gave the invited keynote 'Appleton Lecture' at the 15th Appleton Space Conference on 5 December 2019, at the Rutherford Appleton Labs. The lecture was entitled 'The Ethical Roboticist: a journey from robot ethics to ethical robots', in which RoboTIPS and the ethical black box were featured. |
| Year(s) Of Engagement Activity | 2019 |
| URL | https://www.ralspace.stfc.ac.uk/Pages/15th-Appleton-Space-Conference.aspx |