667476 event 1682115070 1682115070 <![CDATA[Ph.D. Dissertation Defense - Esmaeil Seraj]]> Title:  Enhancing Teamwork in Multi-Robot Systems: Embodied Intelligence via Model- and Data-Based Approaches

Committee:

Dr. Matthew Gombolay, IC, Chair, Advisor

Dr. Seth Hutchinson, ECE

Dr. Chaouki Abdallah, ECE

Dr. Harish Ravichandar, IC

Dr. Marynel Vasquez, Yale

]]> High-performing human teams leverage intelligent and efficient communication and coordination strategies to collaboratively maximize their joint utility. Inspired by teaming behaviors among humans, I seek to develop computational methods for synthesizing intelligent communication and coordination strategies for collaborative multi-robot systems. In my thesis, I leverage both classical model-based control and planning approaches as well as data-driven methods such as Multi-Agent Reinforcement Learning (MARL) and Learning from Demonstration (LfD) to provide several contributions towards enabling emergent cooperative teaming behavior across robot teams. In my thesis, I first leverage model-based methods for coordinated control and planning under uncertainty for multi-robot systems o study and develop techniques for efficiently incorporating environment models in multi-robot planning and decision making. In these contributions, I design centralized and decentralized coordination frameworks, at the control-input and the high-level planning stages, which are informed by and have access to the model of the world. Model-based approaches provide the ability to derive performance and stability guarantees. However, can be sensitive to the accuracy of the model and the quality of the heuristic algorithm. As such, I leverage data-driven and Machine Learning (ML) approaches, such as MARL, to provide several contributions towards learning emergent cooperative behaviors. I design a graph-based architecture to learn efficient and diverse communication models for coordinating cooperative heterogeneous teams. Finally, inspired by the theory of mind in humans' strategic decision-making model, I develop an iterative model to learn deep decision-rationalization for optimizing action selection in collaborative, decentralized teaming. As multi-robot systems become increasingly prevalent in our communities and workplace, aligning the values motivating their behavior with human values is critical. As such, in the last portion of my thesis, I propose a novel Multi-agent LfD approach to learning high-quality collaborative multi-robot policies directly from human-expert generated data, which can result in lower sample complexity and directly learning human's preferred strategy.

]]> <![CDATA[]]> https://gatech.zoom.us/j/94177027379 434381 1788 192484