Gon-Woo Kim
Professor
Department of Intelligent Systems and Robotics
SLAM & State Estimation · Autonomous Navigation · Vision-Language-Action (VLA) · Reinforcement Learning
View full profile
Vision-Language-Action (VLA)
Bridging vision, language and action
SAMPLE TEXT. We develop models that connect what a robot sees with what it is told and what it should do. The goal is a system that can follow an instruction it has never heard before, in a scene it has never visited.
Team
Phan Thanh Danh
Ph.D. Student
Vision-Language-Action (VLA)