The topics below are guaranteed funding and interest. That said, we are open to other topics!
LLM Agents and Robots that Reason, Plan, Act, and Learn
The phenomenal success of applications using LLMs for question answering leads to challenges in using natural and artificial languages to describe knowledge, as a basis for reasoning and inference. We are very interested in investigating how LLMs can be used in the construction of intelligent agents and robots.
Recognizing Goals and Plans Interactively
We are developing the next generation of algorithms for plan recognition (inferring someone’s plan from observations of their actions), and goal recognition (inferring their goal). Two particularly interesting open challenges are:
- Novel goal recognition: Current algorithms assume that the set of goals (and their priors) are known in advance, but humans infer goals from the actions. How can we recognize goals unknown to us?
- Epistemic goal recognition: If we someone looking through drawers, we understand they are looking for something. Their goal is one of knowledge. Yet almost all existing research ignores such goals.
AI for Medical Nanorobot Swarms
Molecular robots are the future of medicine. They work as swarms, trillions of small machines that interact with each other locally. By using different types of nanorobots, we can create very complex interactions and very effective medications. But the complexity is too difficult to plan by humans. The Tolkien Project) investigates use of AI to do this, personalizing medical treatment and creating medications that work in combinations.
Reinforcement Learning, and Rational Swarms
Using reinforcement learning in robot swarms, our robots learn to coordinate with each other, despite being only capable of local interactions. This works really well in some tasks, but in others… Not so much. We are investigating new algorithms and methods for reinforcement learning in robot swarms. We are also investigating how mixed swarms of robots and animals can be used to learn from robots and to learn from animals.
Predicting the Future: Social Simulation with Qualitative Reasoning
The goal of the thesis would be to explore the use of qualitative modeling methods (an established area of AI) to model and predict social phenomena. Qualitative modeling allows scientists to represent the qualitative factors that influence the system, and their interactions, without using exact measures (which they don’t have). Fridman and Kaminka (TIST 2013) showed that this can be done to predict the level of violence in demonstrations.
This is a good topic for someone with political science, social sciences, or macro-level economics background. It would involve: finding what to model (e.g., peace negotiations? economic crises? urbanization?), modeling using existing tools, and then extending the tools with new algorithms. It does not require a lot of programming or heavy computer science background.