本文選題：機(jī)器人抓取 + 番茄�。� 參考：《農(nóng)業(yè)機(jī)械學(xué)報》2017年08期

【摘要】：為了使采摘機(jī)器人在抓取過程中能夠?qū)Ρ蛔ス叩恼硰椥粤W(xué)參數(shù)進(jìn)行快速估計(jì),實(shí)時優(yōu)化抓取過程,減少末端執(zhí)行器對被抓取對象造成機(jī)械損傷,以抓取力、變形量、作用時間為輸入,建立了番茄粘彈性參數(shù)估計(jì)的人工神經(jīng)網(wǎng)絡(luò)模型。運(yùn)用質(zhì)構(gòu)儀蠕變試驗(yàn)所測的力、變形和時間,以及粘彈性參數(shù)E_1、E_2、η_1、η_2作為訓(xùn)練數(shù)據(jù)集,確定了人工神經(jīng)網(wǎng)絡(luò)的拓?fù)浣Y(jié)構(gòu)和參數(shù),并測試了網(wǎng)絡(luò)模型的粘彈性參數(shù)估計(jì)性能。利用二指機(jī)器人末端執(zhí)行器對隨機(jī)番茄樣本進(jìn)行抓取試驗(yàn),并在抓取過程中用此模型來在線估計(jì)粘彈性參數(shù)。通過與質(zhì)構(gòu)儀的實(shí)測值進(jìn)行對比發(fā)現(xiàn),當(dāng)時間t≥0.2 s時,各參數(shù)的估計(jì)值與實(shí)測值之間的相對誤差均在25%以內(nèi),并根據(jù)0.2 s時得到的粘彈性參數(shù)對機(jī)器人抓取力范圍進(jìn)行了估計(jì)。結(jié)果表明,利用此方法在機(jī)器人抓取過程中可以對被抓番茄粘彈性特性進(jìn)行估計(jì),為在線優(yōu)化抓取力提供了依據(jù)。
[Abstract]:In order to estimate the viscoelastic mechanical parameters of fruits and vegetables quickly, optimize the grabbing process in real time, and reduce the mechanical damage caused by the end actuators, the grabbing force and deformation can be obtained. An artificial neural network model for the estimation of viscoelastic parameters of tomato was established. The topological structure and parameters of artificial neural network are determined by using the force, deformation and time, and viscoelastic parameters E _ 1C _ 2, 畏 _ 1 and 畏 _ 2 as training data set, and the viscoelastic parameter estimation performance of the network model is tested. A two-finger robot end effector was used to grab random tomato samples and the model was used to estimate the viscoelastic parameters online. By comparing with the measured value of the qualitative structure instrument, it is found that the relative error between the estimated value and the measured value of each parameter is within 25% when the time t 鈮，

本文編號：1940874