TY - JOUR
T1 - Team WPI-CMU
T2 - Achieving Reliable Humanoid Behavior in the DARPA Robotics Challenge
AU - DeDonato, Mathew
AU - Polido, Felipe
AU - Knoedler, Kevin
AU - Babu, Benzun P.W.
AU - Banerjee, Nandan
AU - Bove, Christoper P.
AU - Cui, Xiongyi
AU - Du, Ruixiang
AU - Franklin, Perry
AU - Graff, Joshua P.
AU - He, Peng
AU - Jaeger, Aaron
AU - Li, Lening
AU - Berenson, Dmitry
AU - Gennert, Michael A.
AU - Feng, Siyuan
AU - Liu, Chenggang
AU - Xinjilefu, X.
AU - Kim, Joohyung
AU - Atkeson, Christopher G.
AU - Long, Xianchao
AU - Padır, Taşkın
N1 - Publisher Copyright:
© 2017 Wiley Periodicals, Inc.
PY - 2017/3/1
Y1 - 2017/3/1
N2 - In the DARPA Robotics Challenge (DRC), participating human-robot teams were required to integrate mobility, manipulation, perception, and operator interfaces to complete a simulated disaster mission. We describe our approach using the humanoid robot Atlas Unplugged developed by Boston Dynamics. We focus on our approach, results, and lessons learned from the DRC Finals to demonstrate our strategy, including extensive operator practice, explicit monitoring for robot errors, adding additional sensing, and enabling the operator to control and monitor the robot at varying degrees of abstraction. Our safety-first strategy worked: we avoided falling, and remote operators could safely recover from difficult situations. We were the only team in the DRC Finals that attempted all tasks, scored points (14/16), did not require physical human intervention (a reset), and did not fall in the two missions during the two days of tests. We also had the most consistent pair of runs.
AB - In the DARPA Robotics Challenge (DRC), participating human-robot teams were required to integrate mobility, manipulation, perception, and operator interfaces to complete a simulated disaster mission. We describe our approach using the humanoid robot Atlas Unplugged developed by Boston Dynamics. We focus on our approach, results, and lessons learned from the DRC Finals to demonstrate our strategy, including extensive operator practice, explicit monitoring for robot errors, adding additional sensing, and enabling the operator to control and monitor the robot at varying degrees of abstraction. Our safety-first strategy worked: we avoided falling, and remote operators could safely recover from difficult situations. We were the only team in the DRC Finals that attempted all tasks, scored points (14/16), did not require physical human intervention (a reset), and did not fall in the two missions during the two days of tests. We also had the most consistent pair of runs.
UR - http://www.scopus.com/inward/record.url?scp=85013096189&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85013096189&partnerID=8YFLogxK
U2 - 10.1002/rob.21685
DO - 10.1002/rob.21685
M3 - Article
AN - SCOPUS:85013096189
SN - 1556-4959
VL - 34
SP - 381
EP - 399
JO - Journal of Field Robotics
JF - Journal of Field Robotics
IS - 2
ER -