The Collaborative Learning and Autonomy Research Lab (CLEAR Lab) focuses on developing autonomous agents that effectively learn to perform tasks for, with, and around people. We strive to ensure seamless interactions between humans and AI, with agents whose behavior aligns with human expectations -- whether the human is an expert designer, a novice end-user, or another AI stakeholder. Our research combines cross-disciplinary expertise in robotics, human modeling, deep learning, probabilistic reasoning, and cognitive psychology to create more human-centered, generalizable, and robust learning algorithms and agents. We ground our work in experiments and user studies with AI systems like personal robot arms or LLM assistants.

We are part of the MIT Computer Science and AI Lab (CSAIL).