Data-driven Learning and Control Seminar: Eric Eaton (UPenn)

About

Data Driven Learning and Control seminar series is organized by the Information and Decision Science Lab at Cornell University and aims to explore the latest advancements and interdisciplinary approaches to data-driven learning and control systems.

Watch on YouTube Live

Bio: Eric Eaton’s research seeks to develop artificial intelligence systems that can continuously learn, adapt, and build upon their experiences over time. Unlike traditional machine learning models designed for specific tasks, his work explores how intelligent systems can acquire new skills, transfer knowledge between different challenges, and retain what they have previously learned. Combining lifelong learning, reinforcement learning, and collaborative AI, Eaton develops computational methods that allow machines to operate more effectively in complex, changing environments. His research also investigates ways to make AI learning more consistent and reliable, particularly when these technologies are deployed in real-world settings.

Robotics provides an important foundation for translating these advances into practical applications. Eaton develops machine learning techniques that enable autonomous robots to navigate unfamiliar environments, recognize objects, and coordinate with other intelligent systems. Recent research explores how robots can learn to perform new combinations of tasks with limited training data, improving their adaptability and efficiency. He also leads Penn’s PRONTO initiative, which brings together aerial and ground robots to locate victims, assess injuries, and assist emergency responders during large-scale disasters. This work demonstrates how intelligent machines can collaborate with humans to address challenging situations where timely decisions are critical.

Eaton extends these approaches into precision medicine, exploring how AI can support more informed and personalized health care. Working alongside medical researchers, he develops systems that integrate information from medical imaging, video, speech, and patient records to improve clinical understanding and decision-making. His recent projects investigate methods for analyzing surgical procedures, identifying potential cognitive impairment through speech patterns, and protecting patient privacy in clinical recordings. Through these efforts, Eaton aims to advance adaptable, trustworthy AI technologies that can assist professionals, improve patient care, and expand the capabilities of intelligent systems across disciplines.