Trust in Human-Machine Partnership (ThUMP)
(EPSRC/UKRI: £1.2m, 2019-2022)
The goal of this project is to advance the state-of-the-art in trustworthy human-AI decision-support systems. The Trust in Human-Machine Partnerhsip (ThUMP) project will address the technical challenges involved in creating explainable AI (XAI) systems so that people using the system can understand the rationale behind and trust suggestions made by the AI. ThUMP will also investigate the legal and ethical challenges involved in instantiating an XAI system for solving resource allocation problems in critical domains, based on varied data from multiple sources, with different levels of reliability and completeness. This project is done in collaboration with three project partners: Save the Children and Schlumberger that provided use cases for the project, and the law firm Hogan Lovells that will cooperate in investigating the legal implications of enhancing machines with transparency and explanations, and how this affects liability and accountability of machines and shared responsibilities.Explaining the Space of Plans
(AFOSR: $1m, 2018-2023)
This project is conducted jointly with Jorg Hoffmann at Saarland University. It is funded by AFOSR (U.S. Air Force Office of Scientific Research). Explainability of AI methods is one of the grand challenges at this time. Model-based AI lends itself naturally to this purpose, as it takes decisions based on explicit reasoning about world behaviour as captured in the model. The difficulty then lies in actually making such reasoning -- enumerating vast spaces of alternate possibilities -- amenable to human users. Our central thesis in this project is that this can be naturally done in terms of explaining the space of plans, pointing out the most relevant plan properties and their dependencies.Intelligent Situational Awareness Platform
(InnovateUK: £130k, 2018-2019)
This project is funded by InnovateUK and in collaboration with Sirius Constellation Ltd. The ambitious goal of this project is to create an intelligent situational awareness platform, in the domain of real-time satellite data, where the operator will be able to understand why the platform has drawn a particular conclusion or recommended response. This project will develop the use of explainable planning for use with near-real-time situational awareness information, demonstrating the commercial and operational benefits.A Realtime Autonomous Robot Navigation Framework
(Korea Evaluation Institute of Industrial Technology, 2018-2021)
This project is in collaboration with Sungkyunkwan University and Redone Technologies. The goal of the project is to apply Artificial Intelligence Planning to long-term missions in several robotics scenarios. The project will develop new planning techniques based on strategic-tactical decomposition, in order to scale to large domains and long-horizon missions.KCL/NASA Collaboration on Planning Technologies
(KCL Impact Acceleration Grant: 2018-2020)
This project is funded by KCL. The ambitious goal of this project is to develop new advanced functionalities for the framework ROSPlan in order to allow its use for robot task planning for robotic assistants used inside human spacecraft.NASA and ESA are planning to launch new robots on board the ISS, for assisting the astronauts, and this project will enable ROSPlan to be used for the control of these robots. These robotic assistants include CIMON (developed for ESA), Astrobee (developed for NASA), and other in-vehicle robots are expected to follow.