本文選題：多臂溫室機(jī)器人　切入點(diǎn)：決策規(guī)劃　出處：《農(nóng)業(yè)機(jī)械學(xué)報(bào)》2017年03期

【摘要】：針對(duì)目前棚室內(nèi)機(jī)器人作業(yè)分析算法智能性不足、準(zhǔn)確作業(yè)率較低,且一次巡航過程只能進(jìn)行單一作業(yè),存在使用效率不高的問題,提出了一種搭載在三臂棚室機(jī)器人上,基于體感操控作業(yè)的決策規(guī)劃算法,用Kinect采集含操作人員位姿信息的深度圖像,結(jié)合隨機(jī)森林統(tǒng)計(jì)學(xué)習(xí)理論和基于高斯核函數(shù)的Mean shift算法,確定了代表人體位姿的20個(gè)關(guān)鍵骨骼點(diǎn)坐標(biāo),在此基礎(chǔ)上提出了一種基于模式切換的三臂映射關(guān)系,將骨骼點(diǎn)信息映射到機(jī)器人工作空間,使人的兩只手臂能自如的控制三臂機(jī)器人,在一次巡航中完成多種棚室作業(yè);此外,還提出了一種結(jié)合骨骼追蹤技術(shù)和YCb Cr顏色空間的手勢(shì)特征分割方法,實(shí)現(xiàn)了用手勢(shì)控制機(jī)器人末端執(zhí)行器作業(yè)。最后,搭建了用于測(cè)試體感決策算法的三臂機(jī)器人樣機(jī),進(jìn)行了針對(duì)該決策算法的精確性試驗(yàn),根據(jù)試驗(yàn)誤差數(shù)據(jù)對(duì)肩部關(guān)節(jié)夾角采用離散化取值識(shí)別,解決了肩部關(guān)節(jié)識(shí)別誤差,結(jié)果表明:測(cè)試者被捕捉到的關(guān)節(jié)處夾角和機(jī)器人對(duì)應(yīng)關(guān)節(jié)夾角的最大映射誤差為1.90°,上位機(jī)發(fā)送夾角值與機(jī)器人實(shí)際轉(zhuǎn)動(dòng)的夾角值最大誤差為0.80°,在誤差允許范圍內(nèi),同時(shí)在該精度下完成一套采摘加噴施作業(yè)指令,平均耗時(shí)13.34 s,且操作者還可通過體感操控訓(xùn)練進(jìn)一步提高機(jī)器人作業(yè)性能,表明該算法具有準(zhǔn)確性和實(shí)用性。
[Abstract]:Aiming at the problem that the analysis algorithm of indoor robot in greenhouse is not intelligent enough, the rate of accurate operation is low, and only a single operation can be carried out in one cruise process, and there is not high efficiency in use, a kind of robot mounted on a three-arm shed room robot is put forward in this paper. Based on the decision planning algorithm of somatosensory manipulation, the depth images of operators' position and pose information are collected by Kinect, combined with stochastic forest statistics learning theory and Mean shift algorithm based on Gao Si kernel function. The coordinates of 20 key skeletal points representing human posture are determined. Based on this, a three-arm mapping relationship based on pattern switching is proposed, which maps the information of skeletal points to the robot workspace. In addition, a method of hand gesture feature segmentation combining bone tracking technology and YCb Cr color space is proposed. Finally, a prototype of a three-arm robot used to test the body sense decision algorithm is built, and the precision test of the decision algorithm is carried out. According to the experimental error data, the angle of shoulder joint is recognized by discretization, and the recognition error of shoulder joint is solved. The results show that the maximum mapping error between the joint angle captured by the tester and the corresponding joint angle of the robot is 1.90 擄, and the maximum error between the transmitting angle of the upper computer and the actual rotation angle of the robot is 0.80 擄. At the same time, a set of picking and spraying instructions is completed with this precision, which takes an average time of 13.34 seconds, and the operator can further improve the performance of the robot through the training of body sense control, which shows that the algorithm is accurate and practical.
【作者單位】： 東北農(nóng)業(yè)大學(xué)工程學(xué)院;
【基金】：黑龍江省普通高等學(xué)校青年創(chuàng)新人才培養(yǎng)計(jì)劃項(xiàng)目(LR-356214) 國(guó)家自然科學(xué)基金項(xiàng)目(51405078) 黑龍江省博士后基金項(xiàng)目(LBH-Z13022) 東北農(nóng)業(yè)大學(xué)“青年才俊”項(xiàng)目(518020)
【分類號(hào)】：S625.3;TP212;TP242

【參考文獻(xiàn)】

相關(guān)期刊論文 前7條

1 王凱;么鴻雁;劉劍君;;蔬菜大棚微環(huán)境對(duì)人體健康的影響[J];疾病監(jiān)測(cè);2015年06期

2 羅陸鋒;鄒湘軍;楊洲;李國(guó)琴;宋西平;張叢;;基于改進(jìn)人工蜂群模糊聚類的葡萄圖像快速分割方法[J];農(nóng)業(yè)機(jī)械學(xué)報(bào);2015年03期

3 朱鳳武;于豐華;鄒麗娜;岳仕達(dá);;農(nóng)業(yè)機(jī)器人研究現(xiàn)狀及發(fā)展趨勢(shì)[J];農(nóng)業(yè)工程;2013年06期

4 張凱良;楊麗;張鐵中;;草莓收獲機(jī)器人采摘執(zhí)行機(jī)構(gòu)設(shè)計(jì)與試驗(yàn)[J];農(nóng)業(yè)機(jī)械學(xué)報(bào);2011年09期

5 馮青春;袁挺;紀(jì)超;李偉;;黃瓜采摘機(jī)器人遠(yuǎn)近景組合閉環(huán)定位方法[J];農(nóng)業(yè)機(jī)械學(xué)報(bào);2011年02期

6 劉繼展;李萍萍;倪齊;李智國(guó);;番茄采摘機(jī)器人真空吸盤裝置設(shè)計(jì)與試驗(yàn)[J];農(nóng)業(yè)機(jī)械學(xué)報(bào);2010年10期

7 趙金英;張鐵中;楊麗;;西紅柿采摘機(jī)器人視覺系統(tǒng)的目標(biāo)提取[J];農(nóng)業(yè)機(jī)械學(xué)報(bào);2006年10期

【共引文獻(xiàn)】

相關(guān)期刊論文 前10條

1 肖英奎;李永強(qiáng);謝龍;付英達(dá);;新型具有力感知的柔性果蔬采摘機(jī)械手研究[J];農(nóng)機(jī)化研究;2017年10期

2 伍坪;;基于DSP圖像處理和HPI通信接口的采摘機(jī)器人設(shè)計(jì)[J];農(nóng)機(jī)化研究;2017年10期

3 張青;林桂潮;蘇金文;呂小蓮;劉瑞;辜松;;水中成堆草莓力學(xué)特性試驗(yàn)研究[J];農(nóng)機(jī)化研究;2017年09期

4 秦華;康朝紅;劉鑫淼;孔令美;;基于BTO多目標(biāo)遺傳算法的播種機(jī)性能優(yōu)化設(shè)計(jì)[J];農(nóng)機(jī)化研究;2017年06期

5 林宏;靳繼紅;禹sリ，

本文編號(hào)：1681972