PhD on 'Robust and Explainable Mission Planning and Scheduling'

University of Strathclyde

PhD Fixed Term Glasgow, UK

Uploaded 10 Jun 2020

Job Description

The Department of Mechanical & Aerospace Engineering and The Department of Computer Science at the University of Strathclyde (Glasgow, UK) are looking for two motivated students to be enrolled in their PhD program.

Projects Aims and Objectives

This research proposal is aiming at bringing together the latest research in explainable AI and probabilistic planning to equip future on-board autonomous spacecrafts with robust and interpretable mission planning and scheduling systems.

Space systems capable of autonomously creating plans from sensing information, or re-planning in response to failures or unexpected events, would greatly improve the scientific return of a mission as well as increase system safety. AI techniques has been largely applied to the design of autonomous systems that are able to cope with various level of uncertainties in the system, surrounding environment or mission goals. However, AI models generally lack of human interpretability.

Addressing the "explainability” problem can provide insight on the autonomous planning and scheduling process, and its environment, by answering questions such as: how should a planning system explain particular ordering decisions, or resource choices? For humans, to be able to trust an AI system, they have to understand the underlying AI reasoning process in a way that is transparent and comprehensible.

Addressing the “robustness” problem can produce task plans and schedules that are robust to uncertainties. Incorporating probabilistic reasoning into the planning and scheduling system would lead to the generation of dynamically controllable strategies.

This is achieved by including an intermediate layer between the planning and scheduling algorithm and the mission controller, called Abstract Argumentation (AA). AA will be able to justify robust solutions taken autonomously by the system both in terms of robustness as well as in terms of optimality in natural language.

Two case studies will be simulated and analysed: fault recovery plan and observation plan for natural disaster monitoring.

The enrolled students will have the opportunity to spend a period of time (6 months) at the European Space Agency during their research study.

The two PhD students will work in collaboratively on the two distinct projects:

Project 1: the aim of the first half of the project is designing and developing an interface for the explainable planner that is able to provide feedback on automatic schedules related to cause-effect of planner actions and system reactivity to uncertainties for the planned solution initially and for direct queries afterwards. In the first case ground operators can have a better knowledge and understanding on the decision taken by the autonomous systems, in the second case they can explore different solutions to increase the knowledge of the environment in which the system is operating

Project 2: The aim of this part of the project is to deploy integrated AI planning and execution systems, with temporal and discrete uncertainty, using new formalisms for plan execution that incorporate both temporally flexible execution (e.g. as STNUs) and probabilistic reasoning over the uncertainties that are inherent in the real world. This will be done through the incorporation of “robust envelopes” of allowed execution. As a result, it will be possible to (i) perform robust dispatch with dynamic consistency in probabilistic plans; (ii) create user-defined envelopes of permitted activity; and (iii) explicitly represent plan risk, fragility, and critical paths, which can be leveraged for explicability.

Person Specification

Qualifications
Master degree in computer science, applied mathematics or aerospace/electronics and electrical engineering

Experience
Experience in the field of machine learning, deep learning, natural language processing, optimisation, discrete optimisation and robust optimisation are desirable