4 August 2020 in IEEE Robotics and Automation Letters
In this article, we describe a system design approach for the teleoperation of a whole-body bilateral humanoid robot. The conventional approach for the teleoperation of a unilateral/bilateral humanoid robot has several problems related to bipedal locomotion. In this work, we have focused on the bipedal stability and 2D/3D locomotion space problems. Our proposed system is primarily composed of bipedal-oriented assistive subsystems and a seat-type whole-body exoskeleton cockpit called "TABLIS". The bipedal-oriented assistive subsystems prevent the humanoid from falling down in cases where an operator provides an inaccurate input. TABLIS reproduces a remote 2D/3D ground surface and overcomes the space limitation of locomotion, such as the use of treadmills. We have achieved bilateral quasi-3D step traversing using our system in a demonstration experiment.
7 March 2018 in Advanced Robotics
This paper describes an approach to estimating the progress in a task executed by a humanoid robot and to synthesizing motion based on the current progress so that the robot can achieve the task. The robot observes a human performing whole body motion for a specific task, and encodes these motions into a hidden Markov model (HMM). The current observation is compared with the motion generated by the HMM, and the task progress can be estimated during the robot performing the motion. The robot subsequently uses the estimate of the task progress to generate a motion appropriate to the current situation with the feedback rule. We constructed a bilateral remote control system with humanoid robot HRP-4 and haptic device Novint Falcon, and we made the humanoid robot push a button. Ten trial motions of pushing a button were recorded for the training data. We tested our proposed approach on the autonomous execution of the pushing motion by the humanoid robot, and confirmed the effectiveness of our task progress feedback method.