본문 바로 가기

로고

국내 최대 기계 및 로봇 연구정보
통합검색 화살표
  • 스마트트랙
  • 우수 논문

    뷰페이지 제목 게시판 내용

    Learning agile and dynamic motor skills for legged robots  
    Hwangbo, Jemin(ETH Zurich)
    United States | Science Robotics
    2019-01-16 | 바로가기
    robots
    Cited by 246

    ■  View full text

    Science Robotics

    16 Jan 2019

    https://doi.org/10.1126/scirobotics.aau5872

     

    ■  Researchers

    Jemin Hwangbo1,*, Joonho Lee1, Alexey Dosovitskiy2, Dario Bellicoso1, Vassilios Tsounis1, Vladlen Koltun3 and Marco Hutter1

     

    1  Robotic Systems Lab, ETH Zurich

    2  Intelligent Systems Lab, Intel, Munich, Germany.

    3  Intelligent Systems Lab, Intel, Santa Clara, CA, USA.

     

     

     

    ■  Abstract

    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. In the present work, we introduce a method for training a neural network policy in simulation and transferring it to a state-of-the-art legged system, thereby leveraging fast, automated, and cost-effective data generation schemes. The approach is 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 before, and recovering from falling even in complex configurations.

     

     

     

     

     

    * 관련 자료 

    [신진연구자 인터뷰] 강화학습을 이용한 보행 로봇 제어

    전체댓글0

    댓글 입력란
    프로필 이미지
    0/250자

    서브 사이드

    서브 우측상단1