Wavelet network, a class of neural network consisting of wavelets, is proposed to solve the inverse kinematics problem in robotic manipulator. A wavelet network suitable for dealing with multi-input and multi-output s...Wavelet network, a class of neural network consisting of wavelets, is proposed to solve the inverse kinematics problem in robotic manipulator. A wavelet network suitable for dealing with multi-input and multi-output system is constructed. The network is optimized by reducing the number of wavelets handling large dimension problem according to the sample data. The algorithms for sparseness analysis of input data and fitting wavelets to the output data with orthogonal method are introduced. Then Levenberg-Marquardt algorithm is used to train the network. Simulation results showed that this method is capable of solving the inverse kinematics problem for PUMA560.展开更多
In the underwater environment, many visual sensors don’t work, and many sensors which work well for robots working in space or on land can not be used underwater. Therefore, an optical fiber slide tactile sensor was ...In the underwater environment, many visual sensors don’t work, and many sensors which work well for robots working in space or on land can not be used underwater. Therefore, an optical fiber slide tactile sensor was designed based on the inner modulation mechanism of optical fibers. The principles and structure of the sensor are explained in detail. Its static and dynamic characteristics were analyzed theoretically and then simulated. A dynamic characteristic model was built and the simulation made using the GA based neural network. In order to improve sensor response, the recognition model of the sensor was designed based on the ‘inverse solution’ principle of neural networks, increasing the control precision and the sensitivity of the manipulator.展开更多
In multi-agent systems, joint-action must be employed to achieve cooperation because the evaluation of the behavior of an agent often depends on the other agents’ behaviors. However, joint-action reinforcement learni...In multi-agent systems, joint-action must be employed to achieve cooperation because the evaluation of the behavior of an agent often depends on the other agents’ behaviors. However, joint-action reinforcement learning algorithms suffer the slow convergence rate because of the enormous learning space produced by joint-action. In this article, a prediction-based reinforcement learning algorithm is presented for multi-agent cooperation tasks, which demands all agents to learn predicting the probabilities of actions that other agents may execute. A multi-robot cooperation experiment is run to test the efficacy of the new algorithm, and the experiment results show that the new algorithm can achieve the cooperation policy much faster than the primitive reinforcement learning algorithm.展开更多
Due to high competition of the agriculture machines sector, the auto parts suppliers are investing in research to promote the development and reduce the costs of the products, passing these results to their clients wh...Due to high competition of the agriculture machines sector, the auto parts suppliers are investing in research to promote the development and reduce the costs of the products, passing these results to their clients who are the automakers. It was identified the need to redesign the regulation sieve system harvester, which is a compound assembly in the harvester＇s grain cleaning system, with the objective to reduce the costs and improve the ergonomic aspect, keeping the same efficiency from the original project. The improvement was developed by studying the original design and identifying possible project fails, such as components and manufacturing process which could be eliminated. For this, it was needed to do a research about rules and project considerations that must be applied in the products development and ergonomic too, specifically about geometric forms and anthropometric measures. From the redesign of this system, it is verified that it is possible by a study to identify possible improvements, and to develop a new system by a simple project, improving the ergonomic, reducing the cost and keeping the same efficacy from the original project.展开更多
·Prof.XIONG,could you please give us a brief introduction to SKLMCMS？Director XIONG Ke：The State Key Laboratory of Mechanics and Control of Mechanical Structures（SKLMCMS）was established with the approval of t...·Prof.XIONG,could you please give us a brief introduction to SKLMCMS？Director XIONG Ke：The State Key Laboratory of Mechanics and Control of Mechanical Structures（SKLMCMS）was established with the approval of the Ministry of Science and Technology of the People’s Republic of China in October 2011.The laboratory is located at Nanjing University of Aeronautics and Astronautics（NUAA）.展开更多
The chemical structure evolution of coal,which is important for understanding coalification and the accompanying volatile and possible oil generation,is generally thought to be influenced by temperature,time and confi...The chemical structure evolution of coal,which is important for understanding coalification and the accompanying volatile and possible oil generation,is generally thought to be influenced by temperature,time and confining pressure.Though evidence concerning the impacts of stress on the chemical structure has accumulated for many years and some hypotheses have been proposed,the mechanism remains controversial.Recent years have seen a breakthrough in mechanochemistry,which proves that stress can act on the molecule directly to initiate or accelerate reactions by deforming the chemical bonds.The progress in mechanochemistry gives researchers incentive to consider how stress works on the chemical structure of coals.Preliminary quantum chemical calculations have been performed on the macromolecule of anthracite to explain the mechanism of gas generation during the deformation experiments at low temperatures.This paper briefly reviews the evidence regarding the impacts of stress on the chemical structure of coals and introduces the recent achievements in the mechanism research.To further investigate this problem,more work should be undertaken by researchers from both geology and quantum chemistry fields.展开更多
文摘Wavelet network, a class of neural network consisting of wavelets, is proposed to solve the inverse kinematics problem in robotic manipulator. A wavelet network suitable for dealing with multi-input and multi-output system is constructed. The network is optimized by reducing the number of wavelets handling large dimension problem according to the sample data. The algorithms for sparseness analysis of input data and fitting wavelets to the output data with orthogonal method are introduced. Then Levenberg-Marquardt algorithm is used to train the network. Simulation results showed that this method is capable of solving the inverse kinematics problem for PUMA560.
文摘In the underwater environment, many visual sensors don’t work, and many sensors which work well for robots working in space or on land can not be used underwater. Therefore, an optical fiber slide tactile sensor was designed based on the inner modulation mechanism of optical fibers. The principles and structure of the sensor are explained in detail. Its static and dynamic characteristics were analyzed theoretically and then simulated. A dynamic characteristic model was built and the simulation made using the GA based neural network. In order to improve sensor response, the recognition model of the sensor was designed based on the ‘inverse solution’ principle of neural networks, increasing the control precision and the sensitivity of the manipulator.
文摘In multi-agent systems, joint-action must be employed to achieve cooperation because the evaluation of the behavior of an agent often depends on the other agents’ behaviors. However, joint-action reinforcement learning algorithms suffer the slow convergence rate because of the enormous learning space produced by joint-action. In this article, a prediction-based reinforcement learning algorithm is presented for multi-agent cooperation tasks, which demands all agents to learn predicting the probabilities of actions that other agents may execute. A multi-robot cooperation experiment is run to test the efficacy of the new algorithm, and the experiment results show that the new algorithm can achieve the cooperation policy much faster than the primitive reinforcement learning algorithm.
文摘Due to high competition of the agriculture machines sector, the auto parts suppliers are investing in research to promote the development and reduce the costs of the products, passing these results to their clients who are the automakers. It was identified the need to redesign the regulation sieve system harvester, which is a compound assembly in the harvester＇s grain cleaning system, with the objective to reduce the costs and improve the ergonomic aspect, keeping the same efficiency from the original project. The improvement was developed by studying the original design and identifying possible project fails, such as components and manufacturing process which could be eliminated. For this, it was needed to do a research about rules and project considerations that must be applied in the products development and ergonomic too, specifically about geometric forms and anthropometric measures. From the redesign of this system, it is verified that it is possible by a study to identify possible improvements, and to develop a new system by a simple project, improving the ergonomic, reducing the cost and keeping the same efficacy from the original project.
文摘·Prof.XIONG,could you please give us a brief introduction to SKLMCMS？Director XIONG Ke：The State Key Laboratory of Mechanics and Control of Mechanical Structures（SKLMCMS）was established with the approval of the Ministry of Science and Technology of the People’s Republic of China in October 2011.The laboratory is located at Nanjing University of Aeronautics and Astronautics（NUAA）.
基金supported by the National Key Research and Development Program of China(2016YFC0600401)the National Natural Science Foundation of China(41030422)
文摘The chemical structure evolution of coal,which is important for understanding coalification and the accompanying volatile and possible oil generation,is generally thought to be influenced by temperature,time and confining pressure.Though evidence concerning the impacts of stress on the chemical structure has accumulated for many years and some hypotheses have been proposed,the mechanism remains controversial.Recent years have seen a breakthrough in mechanochemistry,which proves that stress can act on the molecule directly to initiate or accelerate reactions by deforming the chemical bonds.The progress in mechanochemistry gives researchers incentive to consider how stress works on the chemical structure of coals.Preliminary quantum chemical calculations have been performed on the macromolecule of anthracite to explain the mechanism of gas generation during the deformation experiments at low temperatures.This paper briefly reviews the evidence regarding the impacts of stress on the chemical structure of coals and introduces the recent achievements in the mechanism research.To further investigate this problem,more work should be undertaken by researchers from both geology and quantum chemistry fields.
