A Continuous Teleoperation Subspace With Empirical and Algorithmic Mapping Algorithms for Nonanthropomorphic Hands
A Continuous Teleoperation Subspace With Empirical and Algorithmic Mapping Algorithms for Nonanthropomorphic Hands
复制标题
DOI：
10.1109/tase.2020.3035156
复制
发表时间：
2022-01-01
影响因子：
5.6
通讯作者：
Ciocarlie, Matei
中科院分区：
文献类型：
--
作者：
Meeker, Cassie;Haas-Heger, Maximilian;Ciocarlie, Matei
远程操作是高度非结构化环境中机器人操作的重要工具。然而，由于人手的运动学不同，在人手和非拟人化机器人手之间找到直观的映射可能是困难的。在这篇文章中，我们试图在人手和一个完全驱动的、非拟人化的机械手之间创建一个映射，这个映射足够直观，可以实现有效的实时远程操作，即使对于新手用户也是如此。为了实现这一点，我们提出了一个低维遥操作子空间，它可以用作手姿空间之间映射的中介。我们提出了两种不同的方法来定义遥操作子空间：一种是经验定义，它要求一个人以一种直观的、特定于手的方式定义手部运动；另一种是算法定义，它是运动学独立的，使用对象来定义子空间。我们使用这些定义来为不同的手创建远程操作映射。本文的主要贡献之一是通过十名新手控制的遥操作实验验证了经验和算法映射，并在两个运动不同的手上进行了遥操作实验。实验表明，所提出的子空间与遥操作相关，具有足够的直观性，可以让新手控制，并且可以推广到具有不同运动学的非拟人化手。从业人员注意事项——随着机器人进入我们的仓库、工作场所和家庭，开发对新手来说直观且易于使用的机器人控制非常重要。特别是，当机器人遇到自主程序没有准备好处理的情况时，远程操作对于指导机器人是有价值的。在这篇文章中，我们特别关注使用非拟人化手的机器人抓取。我们的方法旨在让新手用户直观地远程操作此类机器人。我们表明，我们使用的远程操作子空间可以有效地实现取放任务和手持操作任务，并且对于新手操作员来说是直观的。我们的子空间在拾取和放置任务方面优于最先进的方法，并且在手持操作方面表现良好。
Teleoperation is a valuable tool for robotic manipulators in highly unstructured environments. However, finding an intuitive mapping between a human hand and a nonanthropomorphic robot hand can be difficult, due to the hands' dissimilar kinematics. In this article, we seek to create a mapping between the human hand and a fully actuated, nonanthropomorphic robot hand that is intuitive enough to enable effective real-time teleoperation, even for novice users. To accomplish this, we propose a low-dimensional teleoperation subspace that can be used as an intermediary for mapping between hand pose spaces. We present two different methods to define the teleoperation subspace: an empirical definition, which requires a person to define hand motions in an intuitive, hand-specific way, and an algorithmic definition, which is kinematically independent and uses objects to define the subspace. We use each of these definitions to create a teleoperation mapping for different hands. One of the main contributions of this article is the validation of both the empirical and algorithmic mappings with teleoperation experiments controlled by ten novices and performed on two kinematically distinct hands. The experiments show that the proposed subspace is relevant to teleoperation, intuitive enough to enable control by novices, and can generalize to nonanthropomorphic hands with different kinematics. Note to Practitioners-As robots move into our warehouses, workplaces, and homes, it is important to develop robotic controls that are intuitive and easy for novices to use. In particular, teleoperation can be valuable to guide robots when they encounter situations that autonomous programs are not prepared to deal with. In this article, we focus specifically on robotic grasping using nonanthropomorphic hands. Our method is intended for novice users to intuitively teleoperate such robots. We show that the teleoperation subspace we use can effectively enable pick-and-place tasks and in-hand manipulation tasks and that it is intuitive for novice operators. Our subspace outperforms state-of-the-art methods for pick-and-place tasks and performs as well as state-of-the-art methods for in-hand manipulation.