The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
The aim of our project is to develop a robot to manipulate an object in human environment. In this paper, as a first step, we focus on opening paper box such as tea box, and present a method to plan grasp motion by 2 arms with multi-fingered hands. we propose a task priority based scheme to plan grasping area consistent with whole steps of the given task procedure. Based on the grasping area and the...
This article is concerned with autonomous planning of diverse cooperative robot actions. In this work complex cooperative actions are realized based upon the intelligent composite motion control, which is a learning methodology for intelligent robots that gradually realize complex actions from fundamental motions. For efficient construction of action intelligence multi-stage genetic algorithm, MGA,...
As the applications of mobile robot teams become more complex, the impracticality of designing custom solutions is becoming increasingly obvious. A new approach to control system design is required to facilitate the development of modular and scalable systems. Control ad libitum is an approach that decouples the software and hardware design of robot teams, allowing the system to adapt to changing...
Recurrent neural networks (RNNs) have good modeling capability for nonlinear dynamic systems, but due to the difficulties for training this superiority is discounted. Echo state network (ESN) is a new paradigm for using RNNs with a simpler training method, where an RNN is generated randomly and only a readout is trained. ESN method has quickly become popular in robotics, such as for motor control,...
Autonomous mobile robots must accomplish tasks in unknown and noisy environments. In this context, learning robot behaviors in an imitation based approach would be desirable in the perspective of service robotics as well as of learning robots. In this work, we use reservoir computing (RC) for learning robot behaviors by demonstration. In RC, a randomly generated recurrent neural network, the reservoir,...
Recently, human-friendly support systems for product design have been developed as demands of individual user to products become diversified. In the previous works, interactive evolutionary computation has been applied to support product designs. An advantage of interactive evolutionary computation is that it can perform the optimization based on human preference and feeling in addition to the evaluation...
Cerebellar Model Articulation Controller (CMAC) NN is a computational model of cerebellum introduced as an alternative to backpropagated multilayer networks to control robot arms. From then it has seen many improvements and has been applied in many other areas as a general NN. These improvements have been in the context of generalization, learning techniques, differentiability, memory size, fuzzification...
This article explores the possibility of developing robot control software capable of discerning when and if a robot should deceive. Exploration of this problem is critical for developing robots with deception capabilities and may lend valuable insight into the phenomena of deception itself. In this paper we explore deception from an interdependence/game theoretic perspective. Further, we develop...
In this paper, we describe a new small world optimization algorithm for obtaining satisfactory solution for high-dimensional function. Based on the small world phenomenon which is revealed in Milgram's sociological experiment, some operators with decimal-coding strategy are proposed, and then an ??imitated society?? decimal-coding small world optimization algorithm (DSWOA) is designed to solve high-dimensional...
One of the most innovative applications of robotics is creating artificial social relationships between humans and robots in order to promote healthier and more active lifestyles as a means of long-term, sustainable healthcare solutions. This paper describes a theoretical framework to strategically and effectively implement a sociable robot in a healthcare or elderly care facility. Based on the innovation...
As robots step into the human's daily lives, interaction and communication between human and robot is becoming essential. For this social interaction with humans, we propose an emotion generation model considering simplicity, believability and uncertainty. First, OCC model is simplified and then stochastic approach on emotion decision algorithm for believability and uncertainty is applied. The proposed...
In this paper, we present our preliminary report in applying formal verification to the design process of robotic systems under dynamic environments; the goal is to complement existing testing or simulation techniques by experimenting an adaptable framework, where verification models with tamable complexity are generated from the simulation model. Our targets are robotic systems with shape-adjustable...
Line matching is useful in many computer vision tasks such as object recognition, image registration, and 3D reconstruction. The literature on line matching has advanced in recent years, nevertheless, compared to other features (such as point and region matching approaches) it has made little progress. Especially, very few algorithms address the problem of image scaling. In this paper, we present...
Unmanned aerial vehicles (UAVs) are seeing more widespread use in military, scientific, and civilian sectors in recent years. This study presents algorithms for the visual-servo control of an UAV. The helicopter has been stabilized with visual information through the control loop. Unlike previous study that use pose estimation approach which is time consuming and subject to various errors, the visual-servo...
To meet the necessity of handling environmental uncertainties of mobile robots, we proposed an efficient exploration strategy to gather information, called entropy sweeper. To do so, we utilized the entropy distribution and the utility function to determine which positions have more uncertainties. Proposed strategy is divided into two phases: the learning phase and the action phase. In general, uncertainties...
In this study, a novel dynamic agglomerative hierarchical clustering algorithm which combines Boltzmann theory of thermodynamics and a graph-theoretic representation of data objects is put forward for data with non-sphere shape clusters. The new algorithm employs neighbors searching operator and vertices spanning operator to construct the linkage paths between vertices. Additionally, in order to obtain...
The conventional Q-learning algorithm is described by a finite number of discretized states and discretized actions. When the system is represented in continuous domain, this may cause an abrupt transition of action as the state rapidly changes. To avoid this abrupt transition of action, the learning system requires fine-tuned states. However, the learning time significantly increases and the system...
Laser beam welding is the method of choice for the high-quality joining of materials. However, for industrial production these systems have to be set up and calibrated manually with much effort. Our objective is to apply intelligent data processing that results in a cognitive technical system that can learn how to weld, speed up the configuring process, and reduce costs. While monitoring laser welding...
Now, there are some techniques called machine learning, and reinforcement learning is one of the machine learning which often used for actual machine. In this study, we pay attention to the knowledge that does not depend on a reward in reinforcement learning, and we will improve learning efficiency by using it. Furthermore, we aim at letting agent coping with various tasks under environment where...
In this paper a novel model based on electromagnetism-like mechanism (EM) is proposed which is highly compatible with discrete space problems. The proposed method utilizes the EM operators to move particles towards an optimal or near optimal solutions. In fact, the proposed algorithm exploits the crossover operator to calculate forces on particles and move them according to these forces. To keep the...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.