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.
This paper addresses the problem of learning and efficiently representing discriminative probabilistic models of object-specific grasp affordances particularly when the number of labeled grasps is extremely limited. The proposed method does not require an explicit 3D model but rather learns an implicit manifold on which it defines a probability distribution over grasp affordances. We obtain hypothetical...
Our goal is to understand limitations of simplicity of knowledge structures and reasoning processes in Multiagent Systems. Therefore, we propose a framework that integrates external storage media and a capacity-constrained Multiagent System. Agents can store knowledge internally and on external storage media located in an environment. In some cases, agents either have to forget or to store knowledge...
This paper describes an novel approach towards linguistic processing for robots through integration of a motion language module and a natural language module. The motion language module represents association between symbolized motion patterns and words. The natural language module models sentences. The motion language module and the natural language module are graphically integrated. The integration...
Most of the central pattern generator (CPG) models are based on defining explicit dynamical systems and finding the appropriate parameters. In this paper, we propose a novel CPG model that is based on altering a nonlinear oscillator to obtain desired limit cycle behavior. This CPG model benefits from an explicit basin of attraction and also fast convergence behavior. The presented CPG model is used...
The present paper proposes a method to calculate a set of proposed initial values for the weight matrix and the bias vector of a neural network prior to training. The method described here applies for linear neural networks with one hidden layer, and a known proportional relationship between inputs and outputs. The algorithm and the calculations are intended to be simple, to facilitate automation...
A new ANN (artificial neural network) structure is proposed to learn dynamics model of robot. The characterizing feature is that some integral units are appended to a recurrent ANN structure, so it can image dynamic process commendably. Generalization capacity of the learning dynamics model is discussed, as well as its application in optimization, etc. The effectiveness of the method is confirmed...
Many interesting problems in reinforcement learning (RL) are continuous and/or high dimensional, and in this instance, RL techniques require the use of function approximators for learning value functions and policies. Often, local linear models have been preferred over distributed nonlinear models for function approximation in RL. We suggest that one reason for the difficulties encountered when using...
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.