Abstract

For a humanoid robot, both locomotion and object manipulation include contact state changes between the robot, an object, and an environment. It is important for the humanoid's controller system to know the actual contact states. In this paper, we propose a method to describe and execute humanoid's behavior including both object manipulation and locomotion by focusing on contact states. We represent contact states transition as a graph. We utilize Robot-Environment (RE) contact states for locomotion graph and Robot-Object (RO) and Object-Environment (OE) contact states for object manipulation graph. We construct humanoid's behavior by cascading a locomotion graph and a manipulation graph. By using cascaded graph description, we can use the same methods to observe contact states, execute motions autonomously, and recover from errors regardless of whether the current behavior is locomotion or object manipulation. Finally, we evaluate our proposed system through the experiments in which a life-sized humanoid performs 3D climbing and manipulation of an object with an unknown mass.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.