● 주제 : Representation Learning and Language Grounding for Robots (로보틱스를 위한 표현 학습 및 자연 언어 구현)
● 연사 : Nakul Gopalan (아리조나 주립대학 컴퓨팅 및 인공지능 학부 (SCAI) 조교수)
● 일시 : 2023년 7월 17일(월) 16시
● 장소 : 서울대학교 942동 2층 메이커스페이스 / 온라인 생중계 (생중계 링크는 포스터 하단 참고)
● 사전신청 : https://forms.gle/Zyv9t9SHv3i4YLqz5
● 본 세미나는 영어로 진행합니다.
Robots are increasingly present in our lives, from cleaning our houses to automating logistics. However, these robots are still present in our lives as solitary agents, performing structured tasks, without the power to collaborate and learn with humans. A key challenge here is that robots perceive the world and operate in it using sensors and actuators that are continuous, low-level and noisy. However, people on the other hand, reason, plan, specify and teach tasks using high-level concepts without worrying about the low-level continuous nature of the world. To address this challenge, I develop computational methods that firstly, allow robots to learn representations, and skills to solve novel tasks. Moreover, these methods, and representations also enable robots to be taught and programmed using natural language communication, allowing robots to understand a human partner's intent. In this talk I first demonstrate how representations for planning and language understanding can be learned jointly to follow commands in novel environments. I discuss practical approaches with which language can be grounded to pre-trained deep policy representations to solve novel task specifications. Together, these approaches empower robots to learn unstructured tasks via language and demonstrations. I will then discuss the implications of such approaches in collaborative task solving with robots in homes, offices and industries.