Robust and Explainable Mission Planning and Scheduling (REMPS)

Working in collaboration the European Space Agency, this project brings 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. The project consists of two main tasks: First, to design formalisms for probabilistic plan execution that will allow operators to create user-defined envelopes of permitted activity and explicitly represent plan risk, fragility, and critical paths. Second, to design and develop an argumentation-based interface for that provides feedback on autonomously devised plans to queries from ground operators.

Care & Equity - Healthcare Logistics UAS Scotland (CAELUS)

This project will develop and trial what will be the UK’s first national distribution network to use drones to transport essential medicines, blood, organs and other medical supplies throughout Scotland. The AGS led consortium, which brings together 14 organisations including the University of Strathclyde, and leading air traffic control provider NATS, successfully secured £1.5 million from the UK Industrial Strategy Future Flight Challenge Fund to demonstrate how autonomous drone technology can enhance access to essential medical supplies, particularly in rural parts of Scotland. You can find more details and news on the project website:

Data Driven Automated Scheduling under Correlated Uncertainty

The project will design and development data-driven automated scheduling under correlated uncertainty. Correlated uncertainty frequently arises in practice, such as in routing under uncertain traffic, weather dependent scheduling, sensor placement and measurement of pollution, and diffusion in social networks. This project aims to bring together recent advances in automated planning and scheudling under probabilistic uncertainty with techniques from robust optimisation to build scheduling models that enable robust decision-making, even out of sample, without becoming too conservative.


The ROSPlan framework provides a generic method for task planning in a ROS system. ROSPlan encapsulates both planning and dispatch. ROSPlan has a modular design, intended to be modified. It serves as a framework to test new modules with minimal effort. Alternate approaches to state estimation, plan representation, dispatch and execution can be tested without having to write an entire framework.

You can find more details about this on the ROSPlan website:

Hybrid Planning with SMTPlan

SMTPlan+ is a planner for hybrid systems. It supports all the features of PDDL+, including exogenous events and continuous processes, providing an SMT encoding of the PDDL+ models. SMTPlan+ can handle linear domains as well as domains with nonlinear polynomial change.

PDDL+ is the extension of PDDL that allows modelling of mixed discrete-continuous domains, and it follows the Hybrid Automata semantics. Dealing with hybrid systems is becoming more and more an important challenge, as many real-world scenarios feature a mixture of discrete and continuous behaviours.

You can find more details about SMTPlan+ and source code on the project website: