The performance of deep learning(DL)networks has been increased by elaborating the network structures. However, the DL netowrks have many parameters, which have a lot of influence on the performance of the network. We...The performance of deep learning(DL)networks has been increased by elaborating the network structures. However, the DL netowrks have many parameters, which have a lot of influence on the performance of the network. We propose a genetic algorithm(GA) based deep belief neural network(DBNN) method for robot object recognition and grasping purpose. This method optimizes the parameters of the DBNN method, such as the number of hidden units, the number of epochs, and the learning rates, which would reduce the error rate and the network training time of object recognition. After recognizing objects, the robot performs the pick-andplace operations. We build a database of six objects for experimental purpose. Experimental results demonstrate that our method outperforms on the optimized robot object recognition and grasping tasks.展开更多
A surgical manipulator has widely been used for laparoscopic surgery. It has been chosen mainly for the use in supporting human operations and in robot systems like the da Vinci surgical system. These manipulator syst...A surgical manipulator has widely been used for laparoscopic surgery. It has been chosen mainly for the use in supporting human operations and in robot systems like the da Vinci surgical system. These manipulator systems are suitable for careful work, but they have a few problems. One of the problems is that the manipulator is not equipped with haptic sensing functions. Therefore, the operator must know the advanced techniques for visually detecting the physical contact state during surgical operations. These haptic sensing functions thus need to be incorporated into a surgical manipulator. We have developed hydraulic-driven forceps with a micro bearing and a bellows tube that can convey haptic sense to the operator. This system can measure the small forces acting on the tips of the forceps using Pascal＇s principle. A model of the system is provided from the relationship between the internal pressure of the bellows tube and the refraction angles of the forceps. It was confirmed using this model that the developed system makes it possible to estimate both the strength and the direction of the external force applied to the forceps by measuring the internal pressure of the bellows tube. An operator using a three-dimensional haptic device was able to feel the force response during an experiment in which they used the forceps to hold a blood vessel. This report describes the most appropriate method for letting the operator feel the force conveyed by using our system.展开更多
The micro-ring like structured zinc oxide(ZnO) film was deposited on SnO_2: F coated glass substrate by sol-gel dip-coating technique with 1.0 g polyethylene glycol(PEG) content. The surface morphology of micro-ring s...The micro-ring like structured zinc oxide(ZnO) film was deposited on SnO_2: F coated glass substrate by sol-gel dip-coating technique with 1.0 g polyethylene glycol(PEG) content. The surface morphology of micro-ring structured ZnO film has been confirmed by the scanning electron microscope. This ZnO film is used to fabricate the solar cell with the help of ruthenium based dye and carbon counter electrode. The photoelectric and incident photon-to-current conversion efficiency was 1.17% and 48.4%, respectively. The DSC results have been compared with ZnO films prepared without PEG contents.展开更多
文摘The performance of deep learning(DL)networks has been increased by elaborating the network structures. However, the DL netowrks have many parameters, which have a lot of influence on the performance of the network. We propose a genetic algorithm(GA) based deep belief neural network(DBNN) method for robot object recognition and grasping purpose. This method optimizes the parameters of the DBNN method, such as the number of hidden units, the number of epochs, and the learning rates, which would reduce the error rate and the network training time of object recognition. After recognizing objects, the robot performs the pick-andplace operations. We build a database of six objects for experimental purpose. Experimental results demonstrate that our method outperforms on the optimized robot object recognition and grasping tasks.
文摘A surgical manipulator has widely been used for laparoscopic surgery. It has been chosen mainly for the use in supporting human operations and in robot systems like the da Vinci surgical system. These manipulator systems are suitable for careful work, but they have a few problems. One of the problems is that the manipulator is not equipped with haptic sensing functions. Therefore, the operator must know the advanced techniques for visually detecting the physical contact state during surgical operations. These haptic sensing functions thus need to be incorporated into a surgical manipulator. We have developed hydraulic-driven forceps with a micro bearing and a bellows tube that can convey haptic sense to the operator. This system can measure the small forces acting on the tips of the forceps using Pascal＇s principle. A model of the system is provided from the relationship between the internal pressure of the bellows tube and the refraction angles of the forceps. It was confirmed using this model that the developed system makes it possible to estimate both the strength and the direction of the external force applied to the forceps by measuring the internal pressure of the bellows tube. An operator using a three-dimensional haptic device was able to feel the force response during an experiment in which they used the forceps to hold a blood vessel. This report describes the most appropriate method for letting the operator feel the force conveyed by using our system.
基金the Ministry of EducationCulture,Sports,Science and Technology,Japan for financial support
文摘The micro-ring like structured zinc oxide(ZnO) film was deposited on SnO_2: F coated glass substrate by sol-gel dip-coating technique with 1.0 g polyethylene glycol(PEG) content. The surface morphology of micro-ring structured ZnO film has been confirmed by the scanning electron microscope. This ZnO film is used to fabricate the solar cell with the help of ruthenium based dye and carbon counter electrode. The photoelectric and incident photon-to-current conversion efficiency was 1.17% and 48.4%, respectively. The DSC results have been compared with ZnO films prepared without PEG contents.
