Safely responding to critical events in industrial processes
Lead Research Organisation:
University of Bristol
Department Name: Computer Science
Abstract
Drilling wells is a complex and potentially dangerous process in which equipment failures, unexpected environmental effects due to the poorly understood subsurface, and human errors can lead to potentially catastrophic outcomes. In an effort to reduce the likelihood of these as well as the cost of drilling, Schlumberger is developing systems that can operate autonomously or semi-autonomously as part of human machine teams in complex, dangerous and uncertain environments. Such systems must be able to respond appropriately to unexpected events and one significant challenge in deploying them is in verifying that the system is safe, and that it will detect and respond to critical events appropriately. This is particularly challenging in drilling as the systems tend to be sensor poor and even leaving the system in a safe state in response to an event often involves a non-trivial sequence of activities.
In this project we aim to provide automated support that helps operators to make decisions when unexpected events occur during operations. We will explore techniques to support decision making in critical situations. In particular, we will focus on verifying that proposed sequences of actions that would lead to a safe state once unexpected events have been detected are in fact safe. Our approach will exploit recent developments in model-based test generation, especially the use of multi-agent systems combined with machine learning for test generation and for online testing of complex human-interactive systems.
In this project we aim to provide automated support that helps operators to make decisions when unexpected events occur during operations. We will explore techniques to support decision making in critical situations. In particular, we will focus on verifying that proposed sequences of actions that would lead to a safe state once unexpected events have been detected are in fact safe. Our approach will exploit recent developments in model-based test generation, especially the use of multi-agent systems combined with machine learning for test generation and for online testing of complex human-interactive systems.
People |
ORCID iD |
Kerstin Eder (Primary Supervisor) | |
Anas Shrinah (Student) |
Studentship Projects
Project Reference | Relationship | Related To | Start | End | Student Name |
---|---|---|---|---|---|
EP/P510427/1 | 30/09/2016 | 31/12/2021 | |||
1953100 | Studentship | EP/P510427/1 | 30/09/2017 | 25/09/2021 | Anas Shrinah |
Description | "Dynamic Testing for the Verification of Autonomous Intelligent Systems workshop |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Other audiences |
Results and Impact | The aim of the workshop is to develop links between communities (including structural testing,simulation-based testing, safety-critical testing and safety case construction, and formal methods) so that we can join forces in addressing the intellectual challenges that lead to safe and trustworthy autonomous systems. |
Year(s) Of Engagement Activity | 2018 |
URL | https://www-users.cs.york.ac.uk/~rda/Dynamic%20Testing%20for%20the%20V&V%20of%20Autonomous%20Systems... |
Description | Formal Verification Theory and Applications - Schlumberger Gould Research Centre (SGR) |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | Regional |
Primary Audience | Industry/Business |
Results and Impact | Give overview about formal verification theory and applications - Schlumberger Gould Research Centre (SGR) |
Year(s) Of Engagement Activity | 2018 |
Description | Introduction to Drilling Operation and Well Control |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | Local |
Primary Audience | Professional Practitioners |
Results and Impact | To provide an introduction to drilling operation and well control |
Year(s) Of Engagement Activity | 2017 |
Description | Introduction to Formal Verification - MSc Robotics seminar |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | Local |
Primary Audience | Postgraduate students |
Results and Impact | Introduction to Formal Verification to the MSc Robotics students at the University of Bristol |
Year(s) Of Engagement Activity | 2018 |
Description | Introduction to Planning Domain Definition Language (PDDL) - Trustworthy system research group |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | Local |
Primary Audience | Postgraduate students |
Results and Impact | Give an introduction to Planning Domain Definition Language (PDDL) - Trustworthy system research group |
Year(s) Of Engagement Activity | 2018 |
Description | Navigating the Landscape of Artificial Intelligence (AI) Research |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | Local |
Primary Audience | Postgraduate students |
Results and Impact | Navigating the Landscape of Artificial Intelligence (AI) Research is a workshop at the University of Bristol. Provided a quick yet comprehensive overview of AI research fields offered by Chair of AI at the University of Bristol and the Engineering Faculty Research Director |
Year(s) Of Engagement Activity | 2019 |
Description | Robotics and Autonomous Systems: Innovations, Implications and Applications |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | Local |
Primary Audience | Other audiences |
Results and Impact | Fast paced developments in research and industry offer new opportunities for robots to help us in our homes, transport us and our goods, and collaborate with us in new and rich ways. To bring these possibilities to life, a range of expertise is required from the engineers developing and designing new technology, to those applying these systems to their research and to those exploring how robots can be designed and brought into use in ways that ensure fair and prosperous outcomes for all. This workshop will bring together researchers across UoB and UWE, including engineers who draw on other disciplines for inspiration, those who look to robotics for solutions to enable advances in their own field and those who are investigating the legal, ethical, social and political aspects of robotics. The scope of the workshop is intentionally broad, to bring together researchers who would not normally have a chance to interact and to develop interdisciplinary conversations in this area. |
Year(s) Of Engagement Activity | 2018 |
Description | STEM Outreach - Introduction and programming of robots workshop using Mindstorms EV3 Lego kit |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | Local |
Primary Audience | Schools |
Results and Impact | Redfield Educate Together Primary Academy - robots introduction and programming workshop using Mindstorms EV3 Lego kit |
Year(s) Of Engagement Activity | 2018 |
Description | Schlumberger Cambridge Research PhD Cohort Workshop |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Postgraduate students |
Results and Impact | This workshop was a great opportunity to meet fellow PhDs supported by Schlumberger , find out more about Schlumberger, present and discuss our work in an informal environment to an engaged technical community. In addition to posters from all students, oral presentations from later stage students. |
Year(s) Of Engagement Activity | 2019 |
Description | The 28th International Conference on Automated Planning and Scheduling (ICAPS 2018) |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Other audiences |
Results and Impact | The International Conference on Automated Planning and Scheduling (ICAPS) is the premier forum for exchanging news and research results on theory and applications of intelligent planning and scheduling technology. |
Year(s) Of Engagement Activity | 2018 |
URL | http://icaps18.icaps-conference.org/ |
Description | Verification Futures Europe 2018 - Dynamic Testing for the Verification of Autonomous Systems |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Other audiences |
Results and Impact | The development of autonomous intelligent systems is bringing new intellectual challenges to the verification field. The Dynamic Testing Workshop identified challenges such as safety assurance, definition of coverage metrics, regulation concerns and utilisation of artificial intelligence in the verification process. Addressing these challenges provides the basis for an autonomous system testing framework, ultimately leading to safer and more trustworthy autonomous systems. Top 3 Challenges: 1- Metrics for verification completeness and quality - How do we know we are done, and what assurances can we give? 2- Scalability - Exhaustive simulation of autonomous systems is not tractable. How can we leverage artificial intelligence with existing verification techniques to make them scale better? 3- System integrity - How can we continuously ensure that an autonomous system (which is constantly adapting) is operating as safely and capably as it initially did, considering that this depends on several factors such as incoming data quality, in-field learning and various emergent properties? |
Year(s) Of Engagement Activity | 2018 |
URL | https://www.testandverification.com/conferences/verification-futures/vf2018/dynamic-testing-for-the-... |
Description | Workshop on Knowledge Engineering for Planning and Scheduling (KEPS) - ICAPS 2019 |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | Despite the progress in automated planning and scheduling systems, these systems still need to be fed by carefully engineered domain and problem description and they need to be fine-tuned for particular domains and problems. Knowledge engineering for AI planning and scheduling deals with the acquisition, design, validation and maintenance of domain models, and the selection and optimization of appropriate machinery to work on them. These processes impact directly on the success of real-world planning and scheduling applications. The importance of knowledge engineering techniques is clearly demonstrated by a performance gap between domain-independent planners and planners exploiting domain dependent knowledge. The workshop shall continue the tradition of several International Competitions on Knowledge Engineering for Planning and Scheduling (ICKEPS) and KEPS workshops. Rather than focusing only on software tools and domain encoding techniques -which are topics of ICKEPS- the workshop will cover all aspects of knowledge engineering for AI planning and scheduling. |
Year(s) Of Engagement Activity | 2019 |
URL | https://icaps19.icaps-conference.org/workshops/KEPS/ |