通過(guò)一只多指機(jī)械手來(lái)觀測(cè)對(duì)象效能的方法(外文翻譯)

包含中文翻譯和英文原文，內(nèi)容詳細(xì)完整，建議下載參考！

中文： 4780 字
英文： 17440 字符



本文提出了一種通過(guò)多指靈活機(jī)械手來(lái)觀測(cè)對(duì)象效能的方法。目前的任務(wù)目標(biāo)是如何從一個(gè)瓶子上一只瓶蓋。假設(shè)是通過(guò)其他方法比如說(shuō)觀察示范操作來(lái)初步制定計(jì)劃，該系統(tǒng)適用于比較簡(jiǎn)單的抓取行動(dòng)。為響應(yīng)這種探索行動(dòng)，對(duì)象沿物理約束（螺釘）移動(dòng)（旋轉(zhuǎn)）。機(jī)器人通過(guò)手指來(lái)檢測(cè)由此產(chǎn)生的結(jié)果。并且應(yīng)用一種非監(jiān)督型的統(tǒng)計(jì)學(xué)方法將結(jié)果分類，這種方法結(jié)合了高要求自相關(guān)，主部件分析，均值漂移聚類三種方法，因?yàn)樵囼?yàn)了真實(shí)的機(jī)械手和不同直徑的瓶蓋所以該方法能夠檢測(cè)和分類不同的旋轉(zhuǎn)類型。
關(guān)鍵詞：模擬，功效，操縱，運(yùn)動(dòng)約束，兼容手指。



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.