View Proposal
-
Proposer
-
Oliver Lemon
-
Title
-
Collaborative AI: generative AI systems capable of teamwork
-
Goal
-
Develop and evaluate a system able to collaborate and negotiate with humans and other AIs and/or robots on shared tasks
-
Description
- Consider the different scenarios where AI agents need to collaborate with unfamiliar teammates (other robots, AI systems, and humans) who possess varying knowledge, skills, and capabilities. This is the problem of `ad-hoc teamwork' (AHT), which requires agents with the ability to dynamically agree and coordinate on a `common-ground' understanding of the domain and tasks at hand.
You will investigate the extent to which current generative AI systems (LLMs and VLMs) have such collaborative skills, and develop new methods to support AHT within generative AI systems. You will investigate tools such as CoELA, ( https://github.com/UMass-Embodied-AGI/CoELA ) AutoGen ( https://microsoft.github.io/autogen/ ) and LangChain Agents.
This project can also involve collaboration with Toshiba (Cambridge Research Lab).
You should take the course F20/21CA Conversational Agents.
- Resources
-
LLMs and VLMs such as LLAMA and LLAVA etc, CoELA, AutoGen, LangChain Agents
https://github.com/UMass-Embodied-AGI/CoELA
-
Background
-
AI, NLP
-
Url
-
External Link
-
Difficulty Level
-
Challenging
-
Ethical Approval
-
InterfaceOnly
-
Number Of Students
-
2
-
Supervisor
-
Oliver Lemon
-
Keywords
-
ai, teamwork, generative ai
-
Degrees
-
Bachelor of Science in Computer Science
Master of Engineering in Software Engineering
Master of Science in Artificial Intelligence
Master of Science in Artificial Intelligence with SMI
Master of Science in Data Science
Master of Science in Human Robot Interaction
Master of Science in Robotics
Bachelor of Engineering in Robotics
Master of Science in Robotics with Industrial Application