Don't miss our weekly PhD newsletter | Sign up now Don't miss our weekly PhD newsletter | Sign up now

  Neurosymbolic Goal and Plan Recognition


   School of Natural and Computing Sciences

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
  Prof Felipe Meneguzzi, Dr Leonardo Amado  Applications accepted all year round  Self-Funded PhD Students Only

About the Project

These projects are open to students worldwide, but have no funding attached. Therefore, the successful applicant will be expected to fund tuition fees at the relevant level (home or international) and any applicable additional research costs. Please consider this before applying. 

Goal recognition (GR) is a key task in artificial intelligence, where a recognizer infers the goal of an actor based on a sequence of observations. As a running example, consider a service robot that wishes to assist a person in the kitchen by fetching appropriate utensils without interrupting the human's task or demanding attention for specifying instructions. A common approach to enable the robot to perceive and infer the person's goal in this situation consists of a pipeline of activity recognition (the act of recognizing the action being performed) from raw images and translation into actions for a symbolic GR algorithm [1].

Most GR approaches rely on an arduous process to inform the recognizer about the feasibility and likelihood of the different actions that the actor can execute. This process might include manually crafting elaborate domain theories, running a planning algorithm multiple times, performing intricate domain optimizations, or any combination of these tasks. This way of designing and deploying goal recognition approaches is clearly infeasible for real-world applications, especially when the observations made by the recognizer rely primarily on image-based sensing [2].

To address limitations of current Goal Recognition you will investigate novel goal recognition techniques capable of recognizing goals in real-world scenarios. We aim to replace manually crafted representations and online execution with model-free Reinforcement Learning (RL) techniques that allow most of the computation to be done a-priori. Thus, we must revisit the GR problem definition to accommodate RL-based domains and develop a new framework for GR that relies on policies or utility functions derived from any model-free RL technique [3].

Essential Background:

Decisions will be based on academic merit. The successful applicant should have, or expect to obtain, a UK Honours Degree at 2.1 (or equivalent) in computer science, mathematics or a related discipline is essential. We will give priority to candidates with experience with at least one of the following topics:

- Automated Planning algorithms (e.g. heuristic search) and formalisms (e.g., PDDL)

- Reinforcement Learning

- Goal and Plan Recognition.

Application Procedure:

Formal applications can be completed online: https://www.abdn.ac.uk/pgap/login.php.

You should apply for Computing Science (PhD) to ensure your application is passed to the correct team for processing.

Please clearly note the name of the lead supervisor and project title on the application form. If you do not include these details, it may not be considered for the studentship.

Your application must include: A personal statement, an up-to-date copy of your academic CV, and clear copies of your educational certificates and transcripts.

Please note: you DO NOT need to provide a research proposal with this application.

If you require any additional assistance in submitting your application or have any queries about the application process, please don't hesitate to contact us at [Email Address Removed]

Computer Science (8) Politics & Government (30)

Funding Notes

This is a self-funding project open to students worldwide. Our typical start dates for this programme are February or October.

Fees for this programme can be found here Finance and Funding | Study Here | The University of Aberdeen (abdn.ac.uk)

Additional research costs / bench fees may be required and can be discussed at interview stage


References

1. AMADO, Leonardo R.; PEREIRA, Ramon F.; and MENEGUZZI, Felipe. Robust Neuro-Symbolic Goal and Plan Recognition. In 37th AAAI Conference on Artificial Intelligence (AAAI), Washington D.C, USA, 2023.
2. DANN, Michael; YAO, Yuan; ALECHINA, Natasha; LOGAN, Brian; MENEGUZZI, Felipe; and THANGARAJAH, John. Multi-Agent Intention Recognition and Progression. In 32nd International Joint Conference on Artificial Intelligence (IJCAI), Macau, China, 2023.
3. AMADO, Leonardo R.; PEREIRA, Ramon F.; AIRES, João Paulo; MAGNAGUAGNO, Maurício C.; GRANADA, Roger Leitzke; and MENEGUZZI, Felipe. Goal Recognition in Latent Space. In Proceedings of the 31st International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil, 2018.
4. AMADO, Leonardo R.; MIRSKY, Reuth; MENEGUZZI, Felipe. Goal Recognition as Reinforcement Learning. In 36th AAAI Conference on Artificial Intelligence (AAAI), Worldwide, 2022.
5. MENEGUZZI, Felipe; and PEREIRA, Ramon F. A Survey on Goal Recognition as Planning. In 30th International Joint Conference on Artificial Intelligence (IJCAI), Montreal, Canada, 2021.

Where will I study?

Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.