论文标题
F1手：一种多功能的固定手指抓手，可用于细腻的远程操作和自动抓握
F1 Hand: A Versatile Fixed-Finger Gripper for Delicate Teleoperation and Autonomous Grasping
论文作者
论文摘要
远程运行通常受操作员反应和预测机器人与环境相互作用的行为的能力的限制。例如，要掌握桌子上的小物体，远程操作员需要在闭合手指之前预测指尖的位置，以避免它们击中桌子。因此，我们开发了F1手，这是一种单电机抓手，可通过使用固定手指来促进远距离运行。该手能够抓住像纸夹一样薄的物体，并且像无绳钻一样重且大。可以通过用不同的形状代替固定的手指来扩展手的适用性。这种灵活性使手用途广泛，同时又易于开发。但是，由于非典型的不对称结构和手动施加策略的致动，不再适用。因此，我们提出了一个控制器，该控制器通过使用整个臂的运动来近似驱动对称性。 F1手及其控制器并排与原始的Toyota人类支持机器人（HSR）抓手进行了比较，该机器人使用YCB数据集中的22个对象除了小对象外。抓地力时间和峰接触力可以分别降低20％和70％，同时将成功率提高5％。该系统使用现成的掌握姿势估计器进行自动抓握，以80％的订单获得了与原始HSR抓手相似的成功率。
Teleoperation is often limited by the ability of an operator to react and predict the behavior of the robot as it interacts with the environment. For example, to grasp small objects on a table, the teleoperator needs to predict the position of the fingertips before the fingers are closed to avoid them hitting the table. For that reason, we developed the F1 hand, a single-motor gripper that facilitates teleoperation with the use of a fixed finger. The hand is capable of grasping objects as thin as a paper clip, and as heavy and large as a cordless drill. The applicability of the hand can be expanded by replacing the fixed finger with different shapes. This flexibility makes the hand highly versatile while being easy and cheap to develop. However, due to the atypical asymmetric structure and actuation of the hand usual grasping strategies no longer apply. Thus, we propose a controller that approximates actuation symmetry by using the motion of the whole arm. The F1 hand and its controller are compared side-by-side with the original Toyota Human Support Robot (HSR) gripper in teleoperation using 22 objects from the YCB dataset in addition to small objects. The grasping time and peak contact forces could be decreased by 20% and 70%, respectively while increasing success rates by 5%. Using an off-the-shelf grasp pose estimator for autonomous grasping, the system achieved similar success rates to the original HSR gripper, at the order of 80%.
