• 강사 : 박대형 교수 (KAIST 전산학부)
• 일시 : 2023. 10. 23 (월) 16:00~17:30

While there are successful standalone or coexistence robotic systems in human environments, robots are not yet intelligent enough to directly collaborate with humans, especially non-expert users. However, I believe that by bridging the knowledge gap between humans and robots, we can develop highly-capable robotic companions that can assist humans in various tasks. In this talk, I will present our cognitive architecture, which utilizes learned knowledge models to produce two essential capabilities: natural language grounding and skill learning-and-execution. By integrating these capabilities, we can create a robotic teammate that can provide highly scalable and reliable assistance even in novel environments. Our ultimate goal is to develop a robot that is safe, intelligent, and easy to work with, and that can effectively collaborate with humans in various settings.