In recent studies, authors have revealed that robots can form concepts and understand the meaning of words through inference. The key idea behind these is “multimodal categorization” of robot's experience. However, previous studies considered only nonhierarchical categorization methods, which lead to nonhierarchical concept structure. Obviously, our concepts have hierarchical structure that makes our inference more efficient and accurate. In this paper, we propose a novel hierarchical categorization method. The method is an extension of multimodal latent Dirichlet allocation (MLDA) to hierarchical MLDA using nested Chinese restaurant process, which makes it possible for robots to acquire concepts in hierarchical structure. We show that a robot can from the hierarchical concept structure based on the multimodal information, which is captured by the robot itself. Moreover, by focusing on the common features of each category in the hierarchy, the robot is able to infer unobserved information including the meaning of words.
This paper proposes a bilateral control for master and slave systems with different degrees of freedom (DOF). In this paper, it is assumed that the number of DOF on the master side is smaller than that on the slave side. In addition, the slave system is divided into slave subsystems according to the number of DOF on the master side. Each slave subsystem accomplishes two kinds of distinctive functions; “task realization by bilateral control between a master robot and a slave subsystem” and “adaptation to environment in contact with a slave subsystem by automation control.” The task realization is achieved within the range of the number of DOF on the master side. On the other hand, the adaptation to environment in contact with the slave subsystem is achieved by using the DOF not to be utilized for the task realization. In the results, the proposed controller actualizes both functions. In addition, a human operator can carry out the desired task of the slave system without the consideration of environmental surface. The validity of the proposed method is confirmed by experimental results.
The purpose of this study is to develop a portable air supply system for a wearable device driven with a pneumatic actuator. It is effective for downsizing a whole system to introduce a small size air compressor. On the other hand, output pressure and flow rate are also decreased as a whole system is downsized because of a small motor and a decrease in volume of air chamber. The air supply system using the variable volume tank is developed in this study in order to combine with a small size compressor. The variable volume tank composed of rubbers can store pneumatic energy by converting it to elastic energy. The variable volume tank can decrease a pressure drop in tank when supplying compressed air to an actuator. Therefore, output pressure from a compressor when charging compressed air to tank can decrease by using this tank. In addition, pneumatic energy in an actuator is retrieved by this tank as the retrieval tank in re-compression system. Energy consumption can be decreased by retrieving pneumatic energy. In this paper, the composition and structure of the developed system are described, and then energy consumption is discussed to verify the developed system.
Recently, several heavy-duty robots using hydraulic actuators have been developed to support rescue operations. However, hydraulic actuators have nonlinear characteristics such as deadzone due to frictions which makes precise rescue operations difficult. To solve this problem, we already proposed a new control method for hydraulic actuator systems by using feedback modulators with equally quantized inputs. However, this method is difficult to set appropriate parameters due to the restriction of equal quantization. In this paper, we propose a new control system for hydraulic actuator systems by using feedback modulator with unequally quantized inputs and nonlinear element model of the actuator witch gives more accurate feedback values to the modulator. The effectiveness of the proposed method is shown by comparing with the previously proposed method.
This paper addresses sound source localization using an aerial vehicle with a microphone array in an outdoor environment to realize outdoor auditory scene analysis. It, for instance, aims at finding distressed people in a disaster situation. In such an environment, noise is quite loud and dynamically-changing, and conventional microphone array techniques studied in the field of indoor robot audition are of less use. We, thus, proposed MUltiple SIgnal Classification based on incremental Generalized EigenValue Decomposition (iGEVD-MUSIC). It can deal with dynamically-changing high power noise by introducing incrementally-estimated noise correlation matrices. We developed a prototype system for the outdoor auditory scene analysis based on the proposed method using the Parrot AR.Drone with an 8ch microphone array and a Kinect device. Experimental results using the prototype system showed that dynamically-changing noise is properly suppressed with the proposed method even when the signal-to-noise ratio is less than 0dB in an outdoor/indoor environment with the hovering/moving AR.Drone.
In this paper, we presented the 4.0, 2.7, 2.5[mm], width, length, height size biomimetics micro robot system which was inspired by insects. The micro robot system was made from silicon wafer fabricated by micro electro mechanical systems (MEMS) technology. The mechanical system of the robot was equipped with small size rotary type actuators, link mechanisms and six legs to realize the insect-like switching behaviour. In addition, we constructed the artificial intelligence (AI) controlling circuit which were hardware neural networks (HNN) by analog CMOS circuits as a locomotion controlling system. The HNN utilized the pulse-type hardware neuron model (P-HNM) as a basic component. The HNN outputs the driving pulses using synchronization phenomena such as biological neural networks. The driving pulses can operate the actuators of the biomimetics micro robot directly. Therefore, the HNN realized the robot control without using any software programs or A/D converters. The micro robot emulated the locomotion method and the neural networks of an insect with rotary type actuators, link mechanisms and HNN. The micro robot performed forward and backward locomotion, and also changed direction by inputting an external trigger pulse. The locomotion speed was 26.4[mm/min] when the step width was 0.88[mm].
In order for mobile robots to move in convoy, a small platooning technique based on adaptive cruise control (ACC) and a simple clustering method among adjacent robots have been proposed by the author. In the previous works, however, homogeneous mobile robots have been assumed in terms of controllers. In this paper, on the other hand, heterogeneous mobile robots depending on different controllers are assumed. For these robots, a more powerful small platooning technique focusing on a velocity distribution is proposed. In the small platooning methodology, variable time headway in ACC model and dynamic environmental rule are presented. The former is for adjusting a time headway of robots in a congested segment in a lane according to the congestion degree, and the latter is provided into a bottleneck lane where the robots move most slowly so as to externally regulate the behavior. In simulation experiments, the previous and proposed small platooning techniques are applied to heterogeneous mobile robots, and finally, the effectiveness of the proposed small platooning technique is shown.
In FA industry, recently, it has been getting more and more difficult for system integrators to check all collision cases among robots and peripherals before the operation. It is because that robotic production system gets more complex and intelligent, therefore, robots sometimes move on the defferent trajectories and timing in each bin picking motion or recovery sequence from irregular state. A new on-line collision check method for robots is proposed by using each approach speed among the collision check models. We show the algorithm of this method and confirm the effect of it by simulation.
In order to establish a secure communication network during periodic inspection of hydroelectric power stations, the thesis conducts the radio propagation experiment in penstocks. To begin with, using an experimental apparatus which produces multi-path environment of line-of-sight area, transmission characteristics of a wireless LAN are measured. Next, based on the results, a set of antenna system which reduces the communication failure in line-of-sight area is developed. Then, the effectiveness of the system is experimentally confirmed in the straight section of a penstock. Furthermore, the means added to the system in order to solve problems of wireless LAN communication of over-the-horizon area are devised, and the performance of the advanced system is evaluated with an experimental apparatus which produces multi-path environment of over-the-horizon area. Finally, the effectiveness of the proposed system is experimentally verified in whole penstocks including bend.
In recent years, there has been an increasing demand to digitize a huge number of books. A promising new approach for meeting this demand, called Book Flipping Scanning, has been proposed. This is a new style of scanning in which all pages of a book are captured while a user continuously flips through the pages without stopping at each page. Although this new technology has had a tremendous impact in the field of book digitization, page turning is still done manually, which acts as a bottleneck in the development of high-speed book digitization. Against this background, this paper proposes a newly designed high-speed, high-precision book page turner machine. Our machine turns the pages in a contactless manner by utilizing the elastic force of the paper and an air blast. This design enables high-speed performance that is ten times faster than conventional approaches and, in addition, causes no obstruction in the digitization process. This paper reports the evaluation of the proposed machine using various types of paper with different qualities. Our machine achieved high success rate when turning pages at around 300 pages/min, showing that it is a promising technology for turning pages at high-speed and with high precision.