智能軌跡控制割草機(jī)器人設(shè)計(jì)——基于FPGA神經(jīng)網(wǎng)絡(luò)
發(fā)布時(shí)間：2018-10-23 12:57
【摘要】：為了提高割草機(jī)器人自主導(dǎo)航和定位的精確性和智能性,設(shè)計(jì)了一種新型的基于FPGA神經(jīng)網(wǎng)絡(luò)算法的割草機(jī)器人。該設(shè)計(jì)采用FPGA可重構(gòu)技術(shù),以3層誤差反向傳播神經(jīng)網(wǎng)絡(luò)作為典型的模型來(lái)展開;利用成熟的BP算法公式,設(shè)計(jì)了割草機(jī)器人智能控制的模型;利用FPGA技術(shù),設(shè)計(jì)了割草機(jī)器人的硬件系統(tǒng);最后采用文本輸入的設(shè)計(jì)方法,利用田間試驗(yàn)的方式,對(duì)機(jī)器人的軌跡規(guī)劃能力和控制精度進(jìn)行了驗(yàn)證。試驗(yàn)結(jié)果表明:利用FPGA和神經(jīng)網(wǎng)絡(luò)模型可以有效地穿越5個(gè)障礙物,并可得到滿意的軌跡規(guī)劃結(jié)果。將普通的PID控制器和神經(jīng)網(wǎng)絡(luò)PID控制器得到的控制結(jié)果誤差進(jìn)行了對(duì)比,結(jié)果表明:神經(jīng)網(wǎng)絡(luò)PID控制器得到的割草機(jī)器人控制誤差明顯比傳統(tǒng)的PID控制器誤差小。該方法為神經(jīng)網(wǎng)絡(luò)的硬件實(shí)現(xiàn)提供了可靠的理論基礎(chǔ)。
[Abstract]:In order to improve the accuracy and intelligence of autonomous navigation and localization of grass mowing robot, a new kind of grass mowing robot based on FPGA neural network algorithm is designed. The design adopts FPGA reconfigurable technology, takes 3-layer error back propagation neural network as the typical model, uses mature BP algorithm formula, designs the intelligent control model of mowing robot, and makes use of FPGA technology. The hardware system of the mowing robot is designed, and the trajectory planning ability and control precision of the robot are verified by using the design method of text input and the way of field experiment. The experimental results show that the FPGA and neural network models can effectively cross five obstacles and obtain satisfactory trajectory planning results. The error of the conventional PID controller and the neural network PID controller is compared. The results show that the error of the neural network PID controller is obviously smaller than that of the traditional PID controller. This method provides a reliable theoretical basis for the hardware implementation of neural network.
【作者單位】： 河南工業(yè)職業(yè)技術(shù)學(xué)院;
【基金】：河南省自然科學(xué)基金項(xiàng)目(2015ZCB115) 南陽(yáng)市科技攻關(guān)項(xiàng)目(2012GG029)
【分類號(hào)】：S817.111;TP242
本文編號(hào)：2289312
[Abstract]:In order to improve the accuracy and intelligence of autonomous navigation and localization of grass mowing robot, a new kind of grass mowing robot based on FPGA neural network algorithm is designed. The design adopts FPGA reconfigurable technology, takes 3-layer error back propagation neural network as the typical model, uses mature BP algorithm formula, designs the intelligent control model of mowing robot, and makes use of FPGA technology. The hardware system of the mowing robot is designed, and the trajectory planning ability and control precision of the robot are verified by using the design method of text input and the way of field experiment. The experimental results show that the FPGA and neural network models can effectively cross five obstacles and obtain satisfactory trajectory planning results. The error of the conventional PID controller and the neural network PID controller is compared. The results show that the error of the neural network PID controller is obviously smaller than that of the traditional PID controller. This method provides a reliable theoretical basis for the hardware implementation of neural network.
【作者單位】： 河南工業(yè)職業(yè)技術(shù)學(xué)院;
【基金】：河南省自然科學(xué)基金項(xiàng)目(2015ZCB115) 南陽(yáng)市科技攻關(guān)項(xiàng)目(2012GG029)
【分類號(hào)】：S817.111;TP242
【相似文獻(xiàn)】
相關(guān)期刊論文 前2條
1 胡建平;嚴(yán)宵月;何俊藝;關(guān)靜;;缽苗移栽機(jī)器人控制系統(tǒng)設(shè)計(jì)研究[J];農(nóng)機(jī)化研究;2014年12期
2 ;[J];;年期
相關(guān)會(huì)議論文 前1條
1 康惠春;王建軍;馬春慶;王衛(wèi)星;賈天義;閆立峰;尹德秀;范巧變;谷書偉;楊文娟;楊大芳;;大型拖拉機(jī)底盤機(jī)器人自動(dòng)噴涂集成系統(tǒng)[A];第十五屆全國(guó)涂料與涂裝技術(shù)信息交流會(huì)暨商用車、工程機(jī)械、軌道交通涂裝技術(shù)研討會(huì)論文集[C];2012年
相關(guān)碩士學(xué)位論文 前2條
1 董碩;林區(qū)巡防監(jiān)測(cè)機(jī)器人研究[D];中國(guó)林業(yè)科學(xué)研究院;2013年
2 崔軍;噴霧機(jī)器人運(yùn)動(dòng)控制與重噴漏噴顯示[D];江蘇大學(xué);2006年
，本文編號(hào)：2289312
本文鏈接：http://www.sikaile.net/kejilunwen/zidonghuakongzhilunwen/2289312.html
最近更新
教材專著
