[20210226 : 수학과세미나]
Deep Reinforcement Learning for Legged Robots
1. 일시 : 2021년 2월 26일 (금) 13:00-14:00
2. 장소 : 아산이학관 525호 및 Zoom을 이용한 실시간 온라인 강연 동시 진행
- Zoom링크 :
https://korea-ac-kr.zoom.us/j/83235264438?pwd=blRkM0VMSUdLc1VqbFRiaHRJM0U0UT09
3. 연사 : 황보제민 박사 (KAIST 기계공학과 조교수)
4. 제목 : Deep Reinforcement Learning for Legged Robots
5. 초록 : Legged robots pose one of the greatest challenges in robotics. Dynamic and agile maneuvers of animals cannot be imitated by existing methods that are crafted by humans. A compelling alternative is reinforcement learning, which requires minimal craftsmanship and promotes the natural evolution of a control policy. However, so far, reinforcement learning research for legged robots is mainly limited to simulation, and only few and comparably simple examples have been deployed on real systems. The primary reason is that training with real robots, particularly with dynamically balancing systems, is complicated and expensive. Recent algorithmic improvements have made simulation even cheaper and more accurate at the same time. Leveraging such tools to obtain control policies is thus a seemingly promising direction. However, a few simulation-related issues have to be addressed before utilizing them in practice. The biggest obstacle is the so-called reality gap -- discrepancies between the simulated and the real system. Hand-crafted models often fail to achieve a reasonable accuracy due to the complexities of actuation systems of existing robots. This talk will focus on how such obstacles can be overcome. The main approaches are twofold: a fast and accurate algorithm for solving contact dynamics and a data-driven simulation-augmentation method using deep learning. These methods are applied to the ANYmal robot, a sophisticated medium-dog-sized quadrupedal system. Using policies trained in simulation, the quadrupedal machine achieves locomotion skills that go beyond what had been achieved with prior methods: ANYmal is capable of precisely and energy-efficiently following high-level body velocity commands, running faster than ever before, and recovering from falling even in complex configurations.
6. 연사소개 :
- Univ. of Toronto 기계공학 학사 (2011) / ETH Zurich 기계공학 석박사 (2019)
- 보행 로봇, 물리엔진, 강화학습 분야에 세계적으로 다수 인용된 논문들과 소프트웨어 보유
- 주요논문 1: Science Robotics 2019 (Learning agile and dynamic motor skills for legged robots), Science Robotics 역사상 가장 많이 읽혔으며 Nature 에서 선정한 2019년도 주목할만한 논문 10선에 선정
- 주요논문 2: Robotics and Automation Letter 2017 (Control of a quadrotor with reinforcement learning), 강화학습 기반 드론 모션제어분야 최다 인용수 논문 중 하나 (204회).
- 시뮬레이션 물리엔진 RaiSim (raisim.com) 개발
- ETH Zurich의 최우수 박사학위논문상인 ETH Medal 수상