Not checkedNot checked for notices yet.
Task description based on coordination of primitive actions
Kazuyuki NAGATA, Ryo HANAI, Natsuki YAMANOBE and 2 more
Nihon Kikai Gakkai ronbunshu · 2019
doi:10.1299/transjsme.18-00232 (opens in a new tab)
We email you when a new notice or a question about this paper appears.
Abstract
Tasks using a multi-fingered hand are performed by sequentially applying functional finger actions to an object. We refer to a functional finger action as a “primitive action.” Various manipulations can be realized by coordinating the primitive actions. Multi-fingered hands are expected to realize various tasks, and for this purpose, it is necessary to configure software which has high reusability and efficiently for implementing many tasks. In this paper, we describe primitive actions as highly reusable software modules, and we outline the process of implementing tasks through a coordination of these primitive actions. First, we describe the configuration of a multi-fingered hand system and demonstrate how coordinations of the primitive actions are performed within the system. Then, we provide symbolic descriptions of coordination of primitive actions, and we describe tasks for the multi-fingered hand by an action network of which the nodes show coordination of primitive actions. This facilitates reuse of the task description, and provides efficient implementation of the task. As an example, the task of picking up a towel from a stack is described. Furthermore, we demonstrate that the basic specification of the robotic hand required for the task can be derived by analyzing the primitive action sequence.
Abstract licence: CC BY-NC-ND
References11
11 more references, whose wording the paper’s licence keeps private.
Reads
Read by people on this page
None yet.
Checked or read by AI through naulon
None yet.
A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.
Are you an author?
Is this your paper?
Claim it to add your note and be paid when agents cite it. Free.