Effective teleoperated manipulation for humanoid robots in partially unknown real environments: team AIST-NEDO's approach for performing the Plug Task during the DRC Finals

This paper introduces the approach used by AIST-NEDO team during the DARPA Robotics Challenge (DRC) Finals to perform the Plug Task, which is taken as a case study to show how we dealt, in general, with the manipulation tasks proposed by this challenge, using similar strategies. For that purpose, this paper also describes the system used to teleoperate our humanoid robot, HRP-2Kai, in a disaster-hit scenario that is partially unknown, inherently non-structured and where communications are not reliable. This description includes an overview of our robotic platform, as well as the overall structure of the teleoperation interface and the algorithms behind. Also, the way the Plug Task was performed using these algorithms as operation units is explained in detail, by means of a high-level description. Finally, this paper presents the results for this task obtained during the actual competition, as well as a comparison with the performance achieved by other teams that performed the Plug Task in the DRC Finals.