Lifelong learning is a key characteristic of human intelligence, enabling us to continually acquire and refine our knowledge and abilities over a lifetime of experience across diverse domains. However, lifelong learning for intelligent systems remains a largely unsolved problem.

The Lifelong Machine Learning Research Group, led by Eric Eaton seeks to develop a comprehensive approach to lifelong learning for autonomous systems.  The group’s research addresses fundamental issues of continual learning and transfer across diverse tasks, scalable knowledge maintenance, self-directed learning, adaptation to changing environments with guaranteed performance and safety, and interaction with end-users and other agents.  These techniques are applied to problems in autonomous service robots and precision medicine.