About the Project
Project description
Robot Autonomy will require the systems or robots to set up their own agenda (in line with the tasks they are meant to do), defining the next goals to achieve and discarding those who can’t be completed. However, this may create misunderstandings with the users interacting with the system, who may expect something different from the robot, or may be confused if the robot behaved in a non-legible manner.
Therefore, it is important that these autonomous systems are able to explain why they achieved one task and not another, or why some new (unexpected) task was achieved that was not scheduled. Other sources of misunderstandings may come from action failures and replanning, where the robot finds a new plan to complete an on-going task. In this case, the new plan may be different to the original one, thus changing the behavior that the robot was performing.
This project will explore how to generate goal-based explanations for planning-based robots in assistive/service scenarios, extracted from goal-reasoning techniques. It will also look at plan repair to enforce cohesion after a replanning to ideally increase the trust and understanding of the users about the system. Those explanations should also contemplate unforeseen circumstances, therefore explaining things based on “excuses” that the robot may give to the user. Finally, we will investigate how to obtain and provide those explanations at execution time, so explaining on-the-go. The methods developed shall be integrated into a robotic system, in an assistive/service robot scenario.
The methodology will be based on AI Planning techniques, where task domains are represented in PDDL. The project will first delve in the literature of goal generation and reasoning for robots, and explore the explainability opportunities in such methods. Afterwards, it will explore extensions to such methods to generate better goals, ideally being self-explanatory. The project will evaluate the different methods with both objective metric-based assessments and user study that will focus on trust enhancement and understanding of robot’s motives.
Explanations are crucial in Human Autonomy Teaming, as they have been proved to enhance trust. This work is highly novel, both in terms of goal-based explanations and generation of goals for planning-based robots.
Programme details
The successful candidate will be registered on the Computer Science Research MPhil/PhD in the Department of Informatics at King’s College London. They will be part of the King’s Prize Doctoral Programme in Safe, Trusted and Responsible AI.
Eligibility criteria
For entry requirements, see the Computer Science Research MPhil/PhD information.
To be eligible to apply you must (1) qualify for home fee status, and (2) be a UK National.
The PhD is funded by the UK Government’s Defence Science and Technology Laboratory (Dstl). The successful candidate’s offer will be conditional on them passing Dstl’s security clearance checks.
Application process
How to apply
Preparing your application
Prepare the following to submit with your application:
Personal statement (max 2 pages). Include your motivation for pursuing a PhD and for joining the King’s Prize Doctoral Programme in Safe, Trusted and Responsible AI, and explain concisely how your skills and experience relate to the project.
Research proposal (max 4 pages, not including references). This should include:
- Your initial ideas about the challenges you wish to address within the project
- A brief review of the relevant state of the art, identifying limitations or open questions
- Your initial ideas for research directions to address these challenges, referring to relevant literature
Previous academic study. Provide official academic transcript(s) showing subjects studied and marks obtained. If you have completed your degree, include your official degree certificate. If your documents are not in English, include both the original and an official translation.
References. Two references are required, at least one academic. Professional references are acceptable if you completed your qualifications more than five years ago.
You may include a CV (optional, up to two pages) or evidence of professional registration.
Extenuating Circumstance Statement (optional, up to one page). Use this if significant personal or medical challenges have impacted your academic performance or experience. Examples include caring responsibilities, chronic illness or disability, experience of the care system, or socio economic disadvantage. Clearly explain your circumstances and their impact. You may be asked to provide supporting evidence.
Submitting your application
Apply via the application portal: https://apply.kcl.ac.uk/
- Programme name: Computer Science Research MPhil/PhD (Full-time)
- Start date: 1 October 2026
Project Title/Reference section: Goal-Based Explanations for Autonomous Systems and Robotics
Brief synopsis of your research proposal: leave this section blank.
Required documents: ensure all required items listed above under “Preparing your application” are uploaded.
Funding section:
- Select: “6. Other”
- In the “Organisation Name” box, enter: 26KSTAI
IMPORTANT: you must enter the code 26KSTAI accurately otherwise your application may not be processed.
Any questions?
- Questions about the project should be emailed to the supervisor, Dr Gerard Canal
- Questions about the King’s Prize Doctoral Programme in Safe, Trusted and Responsible AI should be sent to star-ai@kcl.ac.uk
- General questions about applying to King’s should be submitted through the King’s application portal https://apply.kcl.ac.uk/
Funding Notes
A four-year studentship that covers the following.
- Stipend: £25,000 per annum with a 5% inflationary rise for each year of study, with an additional £5,000 per annum London weighting (so the total stipend to be received in 2026-27 is £30,000).
- Tuition fees: covered at the home rate.
- RTSG (Research Training and Support Grant): A generous allowance for things like research costs, additional training, attending conferences.
References
- Canal, G., Borgo, R., Coles, A., Drake, A., Huynh, T. D., Keller, P., Krivic, S., Luff, P., Mahesar, Q-A., Moreau, L., Parsons, S., Patel, M., & Sklar, E. (2020). Building Trust in Human-Machine Partnerships. Computer Law & Security Review, 39.
- Hawes, N., et al. (2017). The strands project: Long-term autonomy in everyday environments. IEEE Robotics & Automation Magazine, 24(3), 146-156.
- Aha, D. W. (2018). Goal reasoning: Foundations, emerging applications, and prospects. AI Magazine, 39(2), 3-24.
- Bercher, P., et al. (2014). Plan, repair, execute, explain—how planning helps to assemble your home theater. Proceedings of the International Conference on Automated Planning and Scheduling. Vol. 24. No. 1. 2014.
- Chakraborti, Tathagata, Sarath Sreedharan, and Subbarao Kambhampati. "The emerging landscape of explainable AI planning and decision making. IJCAI 2020.
- Göbelbecker, M., Keller, T., Eyerich, P., Brenner, M., & Nebel, B. (2010, April). Coming up with good excuses: What to do when no plan can be found. In Proceedings of the International Conference on Automated Planning and Scheduling (Vol. 20, No. 1
