Search

In this paper, a novel reinforcement learning method that enables a humanoid robot to learn bipedal walking using a simple reference motion is proposed. Reinforcement learning has recently emerged as a useful method for robots to learn bipedal walking, but, in many studies, a reference motion is necessary for successful learning, and it is laborious or costly to prepare a reference motion. To overcome this problem, our proposed method uses a simple reference motion consisting of three sine waves and automatically sets the waveform parameters using Bayesian optimization. Thus, the reference motion can easily be prepared with minimal human involvement. Moreover, we introduce two means to facilitate reinforcement learning: (1) we combine reinforcement learning with inverse kinematics (IK), and (2) we use the reference motion as a bias for the action determined via reinforcement learning, rather than as an imitation target. Through numerical experiments, we show that our proposed method enables bipedal walking to be learned based on a small number of samples. Furthermore, we conduct a zero-shot sim-to-real transfer experiment using a domain randomization method and demonstrate that a real humanoid robot, KHR-3HV, can walk with the controller acquired using the proposed method.

Robotic process automation (RPA) is automating various job processes in many offices. However, most existing RPA systems automate only processes that are performed on computers. It is highly desirable to develop physical RPA systems that incorporate real robots to automate physical job processes. When developing physical RPA systems, handling paper is particularly important because many physical office jobs involve handling paper documents. However, it is not easy for robots to handle paper because paper is fragile. To address this issue, we propose an electroadhesive paper gripper in this study. The use of electroadhesion enables a robot to handle paper in a simple, non-destructive, and quiet manner. We provide (1) a mechanism for lifting a sheet of paper without accurate control of robot hands, (2) a mechanism for a small gripper to hold a large sheet of paper without bending it, and (3) a method for quickly releasing a sheet of paper. Furthermore, we apply the proposed paper gripper to a document-sorting robot. The robot that we have developed automatically arranges a given stack of paper documents in a predetermined order (e.g., alphabetical or numerical). Experimental results show the validity of the paper gripper and the sorting robot.

In the preceding studies, an analysis of Saga Prefectural sightseeing information by a Self-Organizing Map (SOM) has been tried. And recent development on Information and Communication Technology (ICT) will help us to access any results via the mobile devices easily. This is why the mobile devices, e.g., smartphones and tablet computers, have an operating system installed, and we can improve their functions by downloading any applications on the Web. Then, in order to realize this basic idea, development of an application for the mobile devices is investigated through some computer simulations on the standard desktop PC in this paper. As a result, it is found that i) a developed feature map is useful to identify some candidate topics, ii) a touchscreen is suitable to show the feature map, and iii) arrangement of the feature map can be modified based on our interests. Then, it is concluded that the proposed idea seems to be applicable, even though further consideration is required to brush it up. [ABSTRACT FROM AUTHOR]

This paper describes design and development of a system that supports continuous creation of hazard maps by local residents in their daily life. We made an interview survey to design our system in a model traditional town in Saga, Japan. The results show that in spite of continuous efforts, many practical problems remain and residents feel unsafe. Based on these results, we designed and developed a unique ICT-based support system which contributes to community-based disaster prevention/reduction. The continuous resident participation and posting design are core concept for our sustainable community-based approach. Our system continues to support making a hazard map by integrating the community-based hazard information. Local residents register information about the spot (disaster types, a risk level, a photograph, comments, positional information) that can be dangerous in case of disaster. We have evaluated the usefulness and possibilities of our prototype system implemented as an iOS application. [ABSTRACT FROM AUTHOR]

"Hahoe Village" in Andong region is an UNESCO World Heritage Site. It should be protected against various disasters such as fire, flooding, earthquake, etc. Among these disasters, flooding has drastic impact on the lives and properties in a wide area. Since "Hahoe Village" is adjacent to Nakdong River, it is important to monitor the water level near the village. In this paper, we developed a hydrological modelling using multi-layer perceptron (MLP) to predict the water level of Nakdong River near "Hahoe Village". To develop the prediction model, error back-propagation (EBP) algorithm was used to train the MLP with water level data near the village and rainfall data at the upper reaches of the village. After training with data in 2012 and 2013, we verified the prediction performance of MLP with untrained data in 2014. [ABSTRACT FROM AUTHOR]

The theory of partially observable Markov decision processes (POMDPs) is a useful tool for developing various intelligent agents, and learning hierarchical POMDP models is one of the key approaches for building such agents when the environments of the agents are unknown and large. To learn hierarchical models, bottom-up learning methods in which learning takes place in a layer-by-layer manner from the lowest to the highest layer are already extensively used in some research fields such as hidden Markov models and neural networks. However, little attention has been paid to bottom-up approaches for learning POMDP models. In this paper, we present a novel bottom-up learning algorithm for hierarchical POMDP models and prove that, by using this algorithm, a perfect model (i.e., a model that can perfectly predict future observations) can be learned at least in a class of deterministic POMDP environments. [ABSTRACT FROM AUTHOR]

Relative entropy is a divergence measure between two probability density functions of a random variable. Assuming that the random variable has only two alphabets, the relative entropy becomes a cross-entropy error function that can accelerate training convergence of multi-layer perceptron neural networks. Also, the n-th order extension of cross-entropy (nCE) error function exhibits an improved performance in viewpoints of learning convergence and generalization capability. In this paper, we derive a new divergence measure between two probability density functions from the nCE error function. And the new divergence measure is compared with the relative entropy through the use of three-dimensional plots. [ABSTRACT FROM AUTHOR]

When developing a classifier using various objective functions, it is important to compare the performances of the classifiers. Although there are statistical analyses of objective functions for classifiers, simulation results can provide us with direct comparison results and in this case, a comparison criterion is considerably critical. A Receiver Operating Characteristics (ROC) graph is a simulation technique for comparing classifiers and selecting a better one based on a performance. In this paper, we adopt the ROC graph to compare classifiers trained by mean-squared error, cross-entropy error, classification figure of merit, and the n-th order extension of cross-entropy error functions. After the training of feed-forward neural networks using the CEDAR database, the ROC graphs are plotted to help us identify which objective function is better. [ABSTRACT FROM AUTHOR]

In this paper, a novel reinforcement learning method that enables a humanoid robot to learn bipedal walking using a simple reference motion is proposed. Reinforcement learning has recently emerged as a useful method for robots to learn bipedal walking, but, in many studies, a reference motion is necessary for successful learning, and it is laborious or costly to prepare a reference motion. To overcome this problem, our proposed method uses a simple reference motion consisting of three sine waves and automatically sets the waveform parameters using Bayesian optimization. Thus, the reference motion can easily be prepared with minimal human involvement. Moreover, we introduce two means to facilitate reinforcement learning: (1) we combine reinforcement learning with inverse kinematics (IK), and (2) we use the reference motion as a bias for the action determined via reinforcement learning, rather than as an imitation target. Through numerical experiments, we show that our proposed method enables bipedal walking to be learned based on a small number of samples. Furthermore, we conduct a zero-shot sim-to-real transfer experiment using a domain randomization method and demonstrate that a real humanoid robot, KHR-3HV, can walk with the controller acquired using the proposed method. [ABSTRACT FROM AUTHOR]

Humanoid robots are expected to perform various jobs replacing human beings, but it is difficult for non-expert users to control them. To control humanoid robots easily, various motion imitation systems, in which a humanoid robot does the same motion as a human teacher, have been studied. In the present study, we make two contributions to building easy-to-use imitation systems. The first contribution is a flexible learning system that enables both synchronous real-time imitation, in which the robot imitates human motion almost immediately, and batch imitation, in which the robot's motion is optimized more accurately after longer measurement of human motion. We use an efficient inference-based optimization method to enable both learning modes. The other contribution is an auditory user interface that accepts voice commands from the user and at the same time identifies the target person to be imitated. This enables the user to easily use the imitation system even when other people are present. Experimental results show that the proposed system can be used in both imitation modes and that it can identify the target person. [ABSTRACT FROM AUTHOR]

One of the attractive features which a self-organizing map (SOM) possesses is a topology-preserving projection from the input layer to the competitive layer. Generally speaking, its correspondence is developed through training based on information representations of the applied multi-dimensional data. A developed feature map in the competitive layer enables us easy to understand some underlying rules visually. By the way, an analysis of Saga Prefectural sightseeing information by a SOM has been tried so far. According to the results of preceding studies, applied various topics are divided into several groups successfully. Nevertheless, there are some items not reflected in them at all. This fact implies that representations of the applied data are not appropriate to develop the feature map which we have intended in advance. Then, to overcome this tough problem, a simple idea to emphasize particular items depending on our interests is introduced as pre-synaptic processing. As a result of some computer simulations, it is confirmed that the developed feature maps are modified adaptively depending on the emphasized coefficient. And, it is concluded that the proposed simple method is effective. [ABSTRACT FROM AUTHOR]

This paper presents a novel concept of Disaster Prevention Design (DPD) and its derived subjects and topics for the safety of folk villages in both Korea and Japan. Nowadays, design concepts are focused on 'human-oriented nature' as a whole and this tendency fits to be appropriate for disaster prevention against real dangers of a future society, which is expected to have far more complicated features. On the other hand, convergences have performed with other areas in the field of Information Communication Technology (ICT) so that we can easily find examples like 'the strategy of ICT-based convergence' of the Korean Government in 2014. Modern content designs including UI (user interface) and USN (ubiquitous sensor network) have been developed as one of the representative areas of ICT & UD (universal design) convergences. These days this novel concept of convergence is overcoming the existing limitations of the conventional design concept focused on product and/or service. First of all, from that point our deduced topic or subject would naturally be a monitoring system design of constructional structures in folk villages for safety. We offer an integrated model of maintenance and a management-monitoring scheme. Another important point of view in the research is a safety sign or sign system installed in folk villages or traditional towns and their standardization. We would draw up and submit a plan that aims to upgrade signs and sign systems applied to folk villages in Korea and Japan. According to our investigations, floods in Korea and earthquakes in Japan are the most harmful disasters of folk villages. Therefore, focusing on floods in the area of traditional towns in Korea would be natural. We present a water-level expectation model using deep learning simulation. We also apply this method to the area of 'Andong Hahoe' village which has been registered with the World Cultural Heritage of UNESCO. Folk village sites include 'Asan Oeam', 'Andong Hahoe' and 'Chonju Hanok' villages in Korea and 'Beppu Onsen' village in Japan. Traditional Streets and Markets and Safe Schools and Parks are also chosen as nearby test-beds for DPD based on ICT. Our final goal of the research is to propose and realize an integrated disaster prevention and/or safety system based on big data for both Korea and Japan. [ABSTRACT FROM AUTHOR]

Numerous studies on time series prediction have been undertaken by a variety of researchers. Most of them typically used unidirectional computation flow, that is, present signals are applied to the model as an input and predicted future signals are derived from the model as an output. On the contrary, bidirectional computation style has been proposed recently and applied to prediction tasks. A bidirectional neural network model consists of two mutually connected subnetworks and performs direct and inverse transformations bidirectionally. To apply this model to time series prediction tasks, one subnetwork is trained a conventional future prediction task and the other is trained an additional task for past prediction. Since the coupling effects between the future and past prediction subsystems promote the model's signal processing ability, bidirectionalization of the computing architecture makes it possible to improve its performance. Furthermore, in order to investigate the acquired signal transformation, two kinds of chaotic time series—the Mackey–Glass time series and “Data Set A”—are adopted in this paper. As a result of computer simulations, it has been found experimentally that the direct and inverse transformations developed independently and their information integration give the bidirectional model an advantage over the unidirectional one. © 2003 Wiley Periodicals, Inc. Electr Eng Jpn, 145(3): 50–60, 2003; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/eej.10232 [ABSTRACT FROM AUTHOR]