Supervisor: Dr Daniela Mihai
Application deadline: [contact details available in the full listing]
Competition Funded PhD Project (UK Students Only)
Location: Southampton, United Kingdom
Subjects: Artificial Intelligence, Computer Vision, Human Computer Interaction, Machine Learning, Robotics
About the Project
Supervisory team: Dr Daniela Mihai and Professor Jonathon Hare
Robots and embodied agents that collaborate need ways to share what they perceive, intend and need. This PhD investigates how embodied agents learn to communicate through the modalities available to them, such as vision, sound, touch, and gesture, to collaborate effectively with one another and people, without a pre-designed language.
Most research on emergent communication takes place in abstract, disembodied settings using discrete tokens. Real collaborative systems, such as robot teams, human–robot teams and autonomous vehicles, act in physical or simulated space with different sensors, bodies and constraints, and cannot assume a pre-shared language. Recent work shows that agents with different perceptual modalities invent different, grounded protocols, raising the question of how heterogeneous embodied agents learn to coordinate.
Communication in these settings is shaped by what each agent can sense, do and afford to transmit, so effective protocols must be grounded in the body and the task rather than imposed from outside. Understanding how they arise is a prerequisite for deploying collaborative robots that people can understand and trust.
This project will study how embodied agents develop communication through interaction in collaborative tasks, in simulation and potentially on physical robots. Possible directions include:
- how protocols interoperate across heterogeneous entities and sensors
- how agents choose a modality (visual, auditory, gestural, spatial) to suit the task, partner and environment
- how teams communicate plans, intentions and spatial information
- how communication strategies adapt when partners, tasks or conditions change
- how emergent communication can be made transparent and interpretable to human collaborators
You will shape the project towards your strengths, whether in multi-agent reinforcement learning, robot learning, human–robot interaction or the theory of language emergence. The project benefits from links with the University's robotics community and interdisciplinary connections in cognitive science and linguistics, and contributes to the trustworthy deployment of collaborative AI and robotic systems.
The School of Electronics & Computer Science is committed to promoting equality, diversity inclusivity as demonstrated by our Athena SWAN award. We welcome all applicants regardless of their gender, ethnicity, disability, sexual orientation or age, and will give full consideration to applicants seeking flexible working patterns and those who have taken a career break. The University has a generous maternity policy, onsite childcare facilities, and offers a range of benefits to help ensure employees’ well-being and work-life balance. The University of Southampton is committed to sustainability and has been awarded the Platinum EcoAward.
Entry requirements
You must have a UK 2:1 honours degree, or its international equivalent, in one of the following:
- computer science
- robotics
- engineering
- mathematics
- physics
- cognitive science
- a related field
Essential skills:
- good programming skills (Python and Deep Learning frameworks)
Desiderable skills:
- experience with reinforcement learning, robotics or simulation environments, multi-agent systems or human–robot interaction
We particularly welcome applicants with interdisciplinary backgrounds.
Fees and funding
We offer a range of funding opportunities for both UK and international students. Horizon Europe fee waivers automatically cover the difference between overseas and UK fees for qualifying students.
Competition-based Presidential Bursaries from the University cover the difference between overseas and UK fees for top-ranked applicants.
Competition-based studentships offered by our schools typically cover UK-level tuition fees and a stipend for living costs for top-ranked applicants.
Funding will be awarded on a rolling basis, so apply early for the best opportunity to be considered.
For more information, please visit our postgraduate research funding pages.
How to apply
You need to:
- choose programme type (Research), 2027/28, Faculty of Engineering and Physical Sciences
- select Full time or Part time
- search for programme PhD Computer Science (7089)
- add name of the supervisor in section 2 of the application
Applications should include:
- research proposal
- your CV (resumé)
- 2 academic references
- degree transcripts and certificates to date
- English language qualification (if applicable)
Contact us
Faculty of Engineering and Physical Sciences
For questions about applying, [contact details available in the full listing].
Project leader
For an initial conversation, [contact details available in the full listing].
