The PBJ- 01 robot is a kind of mobile robot featuring six wheels and two swing arms which can help it to fit many terrains. The robot has a sophisticated sensor system, which includes ultrasonic sensors, tentacle sens...The PBJ- 01 robot is a kind of mobile robot featuring six wheels and two swing arms which can help it to fit many terrains. The robot has a sophisticated sensor system, which includes ultrasonic sensors, tentacle sensors and a vision sensor. The PBJ- 01 adopts behavior-based reactive control architecture in which the key part is an object recognition system based on a fuzzy neural network. Simulation validates that this system can conclude the obstacle type from the sensor data, and help the robot decide whether to negotiate or to avoid obstacles.展开更多
Configuration information acquisition and matching are two important steps in the self-reconfiguring process of self-reconfigurable robots. The process of configuration information acquisition was introduced, and a se...Configuration information acquisition and matching are two important steps in the self-reconfiguring process of self-reconfigurable robots. The process of configuration information acquisition was introduced, and a self-reconfiguring configuration matching strategy based on graded optimization mechanism was proposed. The first-grade optimization was to search common connection between matching scheme and goal configuration. The second-grade optimization, whose object function was constructed in terms of configuration connectivity, was to search connnon topology according to the results of the first-grade optimization. The entire process of configuration information acquisition and matching was verified by an experiment and genetic algorithm （GA）. The result shows the accuracy of the configuration information acquisition and the effectiveness of the configuration matching method.展开更多
To build robots that engage in intuitive communication with people by natural language, we are developing a new knowledge representation called conceptual network model. The conceptual network connects natural languag...To build robots that engage in intuitive communication with people by natural language, we are developing a new knowledge representation called conceptual network model. The conceptual network connects natural language concepts with visual perception including color perception, shape perception, size perception, and spatial perception. In the implementation of spatial perception, we present a computational model based on spatial template theory to interpret qualitative spatial expressions. Based on the conceptual network model, our mobile robot can understand user's instructions and recognize the object referred to by the user and perform appropriate action. Experimental results show our approach promising.展开更多
Linguistic-value appraisement extensively exists in artificial intelligence and social system. In the appraisement of enterprise human resource, there is a great amount of linguistic-value information. In order to imp...Linguistic-value appraisement extensively exists in artificial intelligence and social system. In the appraisement of enterprise human resource, there is a great amount of linguistic-value information. In order to improve the reasonability of the result of appraisement of enterprise human resource, we need to study the methods for processing the linguistic-value information. In this paper, a 2-stages method is proposed for processing the linguistic-value appraisement of enterprise human resource. At the first stage, we choose the experts familiar with the related field according to the appraisement goal and problem. At the second stage, we combine the appraisement results by D-S evidence theory or LOWA operator according to the nature of linguistic variable.展开更多
Sensorial information is very difficult to elicit, to represent and to manage because of its complexity. Fuzzy logic provides an interesting means to deal with such information, since it allows us to represent impreci...Sensorial information is very difficult to elicit, to represent and to manage because of its complexity. Fuzzy logic provides an interesting means to deal with such information, since it allows us to represent imprecise, vague or incomplete descriptions, which are very common in the management of subjective information. Aggregation methods proposed by fuzzy logic are further useful to combine the characteristics of the various components of sensorial information.展开更多
Ever since the Victorian era, montage, the process of pictorial composition made by juxtaposing or superimposing photographs, has been a very popular post-editing imaging technique. Despite showing a strong power in d...Ever since the Victorian era, montage, the process of pictorial composition made by juxtaposing or superimposing photographs, has been a very popular post-editing imaging technique. Despite showing a strong power in demonstrating complex wave field effects, this technique has neither been fully explored in acoustic imaging nor been realized in real-time systems with the capability beyond diffraction limits.On the other hand, the recent prospect of metamaterials has shown their great potentials in superresolution acoustic imaging. However, the miracle jigsaw of more advanced functional modulation of acoustic wave fields at deep subwavelength scale still remains elusive. Here we report the experimental implementation of super-resolution acoustic image montage through a judiciously designed biaxial metamaterial lens. Based on the non-diffraction birefringence in the biaxial metamaterials, we realized various montage functionalities such as duplication, composition, and decomposition of sound images with distinctive deep subwavelength features. Our work represents an important step in developing versatile functional acoustic metamaterial devices for imaging purposes, as it provides on-demand editing of sound field patterns beyond diffraction limits.展开更多
文摘The PBJ- 01 robot is a kind of mobile robot featuring six wheels and two swing arms which can help it to fit many terrains. The robot has a sophisticated sensor system, which includes ultrasonic sensors, tentacle sensors and a vision sensor. The PBJ- 01 adopts behavior-based reactive control architecture in which the key part is an object recognition system based on a fuzzy neural network. Simulation validates that this system can conclude the obstacle type from the sensor data, and help the robot decide whether to negotiate or to avoid obstacles.
基金the National High Technology Research and Development Programme of China(No.2006AA04Z220)National Natural Science Foundation of China(No.60705027)Program for Changjiang Scholars and Innovative Research Team in University(PCSIRT)(No.IRT0423)
文摘Configuration information acquisition and matching are two important steps in the self-reconfiguring process of self-reconfigurable robots. The process of configuration information acquisition was introduced, and a self-reconfiguring configuration matching strategy based on graded optimization mechanism was proposed. The first-grade optimization was to search common connection between matching scheme and goal configuration. The second-grade optimization, whose object function was constructed in terms of configuration connectivity, was to search connnon topology according to the results of the first-grade optimization. The entire process of configuration information acquisition and matching was verified by an experiment and genetic algorithm （GA）. The result shows the accuracy of the configuration information acquisition and the effectiveness of the configuration matching method.
文摘To build robots that engage in intuitive communication with people by natural language, we are developing a new knowledge representation called conceptual network model. The conceptual network connects natural language concepts with visual perception including color perception, shape perception, size perception, and spatial perception. In the implementation of spatial perception, we present a computational model based on spatial template theory to interpret qualitative spatial expressions. Based on the conceptual network model, our mobile robot can understand user's instructions and recognize the object referred to by the user and perform appropriate action. Experimental results show our approach promising.
基金support of National Social Science Foundation of China(Grant No.03CJL004)National Natural Science Foundation of China(Grant No.60074014).
文摘Linguistic-value appraisement extensively exists in artificial intelligence and social system. In the appraisement of enterprise human resource, there is a great amount of linguistic-value information. In order to improve the reasonability of the result of appraisement of enterprise human resource, we need to study the methods for processing the linguistic-value information. In this paper, a 2-stages method is proposed for processing the linguistic-value appraisement of enterprise human resource. At the first stage, we choose the experts familiar with the related field according to the appraisement goal and problem. At the second stage, we combine the appraisement results by D-S evidence theory or LOWA operator according to the nature of linguistic variable.
文摘Sensorial information is very difficult to elicit, to represent and to manage because of its complexity. Fuzzy logic provides an interesting means to deal with such information, since it allows us to represent imprecise, vague or incomplete descriptions, which are very common in the management of subjective information. Aggregation methods proposed by fuzzy logic are further useful to combine the characteristics of the various components of sensorial information.
基金supported by the National Natural Science Foundation of China (11674119, 11774297, 11690030, 11690032)the support from the General Research Fund (GRF) scheme of Research Grants Council of Hong Kong (Poly U 152119/18E)。
文摘Ever since the Victorian era, montage, the process of pictorial composition made by juxtaposing or superimposing photographs, has been a very popular post-editing imaging technique. Despite showing a strong power in demonstrating complex wave field effects, this technique has neither been fully explored in acoustic imaging nor been realized in real-time systems with the capability beyond diffraction limits.On the other hand, the recent prospect of metamaterials has shown their great potentials in superresolution acoustic imaging. However, the miracle jigsaw of more advanced functional modulation of acoustic wave fields at deep subwavelength scale still remains elusive. Here we report the experimental implementation of super-resolution acoustic image montage through a judiciously designed biaxial metamaterial lens. Based on the non-diffraction birefringence in the biaxial metamaterials, we realized various montage functionalities such as duplication, composition, and decomposition of sound images with distinctive deep subwavelength features. Our work represents an important step in developing versatile functional acoustic metamaterial devices for imaging purposes, as it provides on-demand editing of sound field patterns beyond diffraction limits.
