About the project
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.
