본문 바로가기

Team THOR’s entry in the DARPA robotics challenge finals 2015

문서 유형
연구출판물 · 저서
등재
Scopus
저널 순위
Scopus Q2
저널
Springer Tracts in Advanced Robotics121 · pp.381 · 2018
피인용
Scopus 2
FWCI (Scopus)
0.79
ISSN
1610-7438

저자

  1. McGill, Stephen G.제1저자GRASP Lab, University of Pennsylvania, Philadelphia, United States
  2. 이승준교신저자School of Electrical Engineering, Pusan National University, Busan, South Korea
  3. Yi, HakSchool of Mechanical Engineering, Kyungpook National University, Daegu, South Korea
  4. Ahn, Min SungRoMeLa Lab, University of California at Los Angeles, Los Angeles, United States
  5. Cho, SanghyunRoMeLa Lab, University of California at Los Angeles, Los Angeles, United States
  6. Liu, KevinRoMeLa Lab, University of California at Los Angeles, Los Angeles, United States
  7. Sun, DanielRoMeLa Lab, University of California at Los Angeles, Los Angeles, United States
  8. Lee, BhoramGRASP Lab, University of Pennsylvania, Philadelphia, United States
  9. Jeong, HeejinGRASP Lab, University of Pennsylvania, Philadelphia, United States
  10. Huh, JinwookGRASP Lab, University of Pennsylvania, Philadelphia, United States
  11. Hong, DennisRoMeLa Lab, University of California at Los Angeles, Los Angeles, United States
  12. Lee, Daniel D.GRASP Lab, University of Pennsylvania, Philadelphia, United States

초록

This paper describes Team THOR’s approach to human-in-the-loop disaster response robotics for the 2015 DARPA Robotics Challenge (DRC) Finals. Under the duress of unpredictable networking and terrain, fluid operator interactions and dynamic disturbance rejection become major concerns for effective teleoperation. We present a humanoid robot designed to effectively traverse a disaster environment while allowing for a wide range of manipulation abilities. To complement the robot hardware, a hierarchical software foundation implements network strategies that provide real-time feedback to an operator under restricted bandwidth using layered user interfaces. Our strategy for humanoid locomotion includes a backward facing knee configuration paired with specialized toe and heel lifting strategies that allow the robot to traverse difficult surfaces while rejecting external perturbations. With an upper body planner that encodes operator preferences, predictable motion plans are executed in unforeseen circumstances that are critical for manipulation in unknown environments. Our approach was validated during the DRC Finals competition, where Team THOR scored three points in 18 min of operation time, and the results are presented with analysis of each task.

식별자

Scopus EID
2-s2.0-85045412340