通过一只多指机械手来观测对象效能的方法

通过一只多指机械手来观测对象效能的方法(中文4700字,英文3100字)
本文提出了一种通过多指灵活机械手来观测对象效能的方法。目前的任务目标是如何从一个瓶子上一只瓶盖。假设是通过其他方法比如说观察示范操作来初步制定计划，该系统适用于比较简单的抓取行动。为响应这种探索行动，对象沿物理约束（螺钉）移动（旋转）。机器人通过手指来检测由此产生的结果。并且应用一种非监督型的统计学方法将结果分类，这种方法结合了高要求自相关，主部件分析，均值漂移聚类三种方法，因为试验了真实的机械手和不同直径的瓶盖所以该方法能够检测和分类不同的旋转类型。
关键词：模拟，功效，操纵，运动约束，兼容手指。
1•导言
对机器人执行有用任务来说，对象操纵能力是一种至关重要的能力。为扩大未来机器人的机械效能，他们应该配备一些手段来发现和了解如何操纵它们碰到的不同物体，对象操作的理论和应用是一个拥有大量固态结果的确定的领域。但是，它们通常能够提供目标对象精确地几何信息和手指动作的精确控制，甚至所给的目标对象的理想的运动。
HAPTIC DETECTION OF OBJECT AFFORDANCES
BY A MULTI-FINGERED ROBOT HAND
This paper proposes a learning method for detecting object affordances through haptic exploration by a multi-fingered robot hand. Learning how to remove a screw cap from a bottle is the present target task. Assuming that coarse manipulation strategy is given by other methods, such as visual observation of a model task, the system applies coarse grabbing actions to the target object. In response to the exploratory actions, the object
moves (rotates, in this case) along the physical constraint (screw). The robot detects the resulting motion through proprioception of the compliant fingers. A non-supervised statistical learning method is applied to categorize the resulting motion. The method is a combination of high-order local autocorrelation (HLAC), principal components analysis (PCA), and mean-shift clustering. Experiments with a real multi-fingered robot hand
and bottle caps of different diameters confirm that the proposed method can detect and categorize rotational constraints.
Keywords: Imitation; affordances; manipulation; motion constraint; compliant fingers;
statistical learning.
1. Introduction
Object manipulation is a crucial capability for robots to perform useful tasks. In order to expand the utility of future robots, they should be equipped with some means to discover and learn how to manipulate arbitrary objects they come across.Theory and application of object manipulation is an established field with a large body of solid results. However, they typically assume the availability of precise geometrical information about the target object and precision control of finger motion. Moreover, the desired motion of the target object is given.Primarily affiliated with National Institute for Advanced Industrial Science and Technology.