Achieving reliable humanoid robot operations in the DARPA robotics challenge: Team WPI-CMU’s approach. Atkeson, C., Benzun, P., Banerjee, N., Berenson, D., Bove, C., Cui, X., DeDonato, M., Du, R., Feng, S., Franklin, P., Gennert, M., Graff, J., He, P., Jaeger, A., Kim, J., Knoedler, K., Li, L., Liu, C., Long, X., Polido, F., Xinjilefu, X., & Padır, T. Volume 121 , 2018.
abstract   bibtex   
© Springer International Publishing AG, part of Springer Nature 2018. The DARPA Robotics Challenge (DRC) required participating human-robot teams to integrate mobility, manipulation, perception and operator interfaces to complete a simulated disaster mission. We describe our approach to the development of manipulation and locomotion capabilities for 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. We ranked 3rd out of 23 teams when the scores from two official runs were averaged.
@book{
 title = {Achieving reliable humanoid robot operations in the DARPA robotics challenge: Team WPI-CMU’s approach},
 type = {book},
 year = {2018},
 source = {Springer Tracts in Advanced Robotics},
 identifiers = {[object Object]},
 volume = {121},
 id = {4b203f1d-1538-30c3-b738-b56106d7f11c},
 created = {2019-02-19T15:46:50.820Z},
 file_attached = {false},
 profile_id = {956ec342-5e72-3417-993f-8fa9639c2f45},
 last_modified = {2019-02-19T15:46:50.820Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 abstract = {© Springer International Publishing AG, part of Springer Nature 2018. The DARPA Robotics Challenge (DRC) required participating human-robot teams to integrate mobility, manipulation, perception and operator interfaces to complete a simulated disaster mission. We describe our approach to the development of manipulation and locomotion capabilities for 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. We ranked 3rd out of 23 teams when the scores from two official runs were averaged.},
 bibtype = {book},
 author = {Atkeson, C.G. and Benzun, P.W.B. and Banerjee, N. and Berenson, D. and Bove, C.P. and Cui, X. and DeDonato, M. and Du, R. and Feng, S. and Franklin, P. and Gennert, M.A. and Graff, J.P. and He, P. and Jaeger, A. and Kim, J. and Knoedler, K. and Li, L. and Liu, C. and Long, X. and Polido, F. and Xinjilefu, X. and Padır, T.}
}

Downloads: 0