In present-day industrial settings,where robot arms performtasks in an unstructured environment,theremay exist numerousobjects of various shapes scattered in randompositions,making it challenging for a robot armtoprec...In present-day industrial settings,where robot arms performtasks in an unstructured environment,theremay exist numerousobjects of various shapes scattered in randompositions,making it challenging for a robot armtoprecisely attain the ideal pose to grasp the object.To solve this problem,a multistage robotic arm flexible grasp detection method based on deep learning is proposed.This method first improves the Faster RCNN target detection model,which significantly improves the detection ability of the model for multiscale grasped objects in unstructured scenes.Then,a Squeeze-and-Excitation module is introduced to design a multitarget grasping pose generation network based on a deep convolutional neural network to generate a variety of graspable poses for grasped objects.Finally,a multiobjective IOU mixed area attitude evaluation algorithm is constructed to screen out the optimal grasping area of the grasped object and obtain the optimal grasping posture of the robotic arm.The experimental results show that the accuracy of the target detection network improved by the method proposed in this paper reaches 96.6%,the grasping frame accuracy of the grasping pose generation network reaches 94%and the flexible grasping task of the robotic arm in an unstructured scene in a real environment can be efficiently and accurately implemented.展开更多
In order to study the dynamic characteristics of hydro-mechanical continuously variable transmission(HMCVT)under ploughing and sowing conditions,a complete simulation model of HMCVT is established based on AMESim soft...In order to study the dynamic characteristics of hydro-mechanical continuously variable transmission(HMCVT)under ploughing and sowing conditions,a complete simulation model of HMCVT is established based on AMESim software,including mechanical transmission model,pump controlled hydraulic motor speed control model and section changing hydraulic system model.In addition,the dynamic model of tractor is established.In order to verify the correctness of the simulation model,a test-bed is established.The test of tractor running speed and the test of pump controlled hydraulic motor system were carried out on the test-bed.The test results show that the simulation model of pump control hydraulic system can correctly reflect the change of transmission ratio of pump controlled hydraulic motor,and the simulation model can reflect the actual working condition change of clutch.Thus,the correctness of the previous simulation model based on AMESim is verified.Based on the simulation model established by AMESim,the dynamic characteristics of HMCVT under ploughing and sowing conditions are studied.The results show that:Under ploughing condition,the planetary platoon will have strong impact at the moment of throttle opening and changing section.Under sowing condition,the HMCVT will have a great impact at the time of variable cross section,but the variation range of rodent force decreases and the changing trend tends to be stable.展开更多
基金supported in part by the National Natural Science Foundation of China(No.52165063)Guizhou Provincial Science and Technology Projects(Qiankehepingtai-GCC[2022]006-1,Qiankehezhicheng[2021]172,[2021]397,[2021]445,[2022]008,[2022]165)+1 种基金Natural Science Research Project of Guizhou Provincial Department of Education(Qianjiaoji[2022]No.436)Guizhou Province Graduate Research Fund(YJSCXJH[2021]068).
文摘In present-day industrial settings,where robot arms performtasks in an unstructured environment,theremay exist numerousobjects of various shapes scattered in randompositions,making it challenging for a robot armtoprecisely attain the ideal pose to grasp the object.To solve this problem,a multistage robotic arm flexible grasp detection method based on deep learning is proposed.This method first improves the Faster RCNN target detection model,which significantly improves the detection ability of the model for multiscale grasped objects in unstructured scenes.Then,a Squeeze-and-Excitation module is introduced to design a multitarget grasping pose generation network based on a deep convolutional neural network to generate a variety of graspable poses for grasped objects.Finally,a multiobjective IOU mixed area attitude evaluation algorithm is constructed to screen out the optimal grasping area of the grasped object and obtain the optimal grasping posture of the robotic arm.The experimental results show that the accuracy of the target detection network improved by the method proposed in this paper reaches 96.6%,the grasping frame accuracy of the grasping pose generation network reaches 94%and the flexible grasping task of the robotic arm in an unstructured scene in a real environment can be efficiently and accurately implemented.
基金The research is funded partially by the Jiangsu International Cooperation Project(Grant No.BZ2021007)the Modern Agricultural Machinery Equipment and Technology Promotion Project in Jiangsu Province(Grant No.NJ2021-06)+2 种基金the Nanjing International Science and Technology Cooperation Project(Grant No.202002049)the Xuzhou key research and development projects(Grant No.KC21136)The Fundamental Research Funds for the Central Universities(Grant No.KYGD202105).
文摘In order to study the dynamic characteristics of hydro-mechanical continuously variable transmission(HMCVT)under ploughing and sowing conditions,a complete simulation model of HMCVT is established based on AMESim software,including mechanical transmission model,pump controlled hydraulic motor speed control model and section changing hydraulic system model.In addition,the dynamic model of tractor is established.In order to verify the correctness of the simulation model,a test-bed is established.The test of tractor running speed and the test of pump controlled hydraulic motor system were carried out on the test-bed.The test results show that the simulation model of pump control hydraulic system can correctly reflect the change of transmission ratio of pump controlled hydraulic motor,and the simulation model can reflect the actual working condition change of clutch.Thus,the correctness of the previous simulation model based on AMESim is verified.Based on the simulation model established by AMESim,the dynamic characteristics of HMCVT under ploughing and sowing conditions are studied.The results show that:Under ploughing condition,the planetary platoon will have strong impact at the moment of throttle opening and changing section.Under sowing condition,the HMCVT will have a great impact at the time of variable cross section,but the variation range of rodent force decreases and the changing trend tends to be stable.
