Negar Mehr

Negar Mehr is an assistant professor in UC Berkeley’s Department of Mechanical Engineering and director of the Berkeley Intelligent Control (ICON) Lab. Her research focuses on interactive autonomy, developing learning and control algorithms that help autonomous robots and multi-agent systems interact safely and intelligently with humans and other agents.

Robots Need Game-Theoretic Planning to Navigate Human Interaction

UC Berkeley roboticist Negar Mehr uses a Stanford robotics seminar on interactive autonomy to argue that robots cannot handle shared spaces by treating people and other robots as moving obstacles. She frames interaction as a coupled decision problem: agents must predict how others will respond to their own actions, coordinate across multiple possible equilibria, and learn from demonstrations of interaction rather than isolated behavior. Her broader case is that game-theoretic structure, multi-agent learning, and training-time foundation-model coaching can make that coupling tractable without replacing deployed control policies.

Stanford OnlineMay 20, 202619 min read