Self-reflective segmentation of human bodily motions using recurrent neural networks

For realizing a naturalistic collaboration between the human and the robot, we have to establish the intention sharing from the series of motion data that are observed and exchanged between the human and the machine. In a word, this is a problem to detect "meanings" out of the digitized data stream. In this paper, we propose a novel approach based on semiosis, and present a method of interpreting bodily motions using recurrent neural networks called Elman networks. We made some experiments using the raw data acquired while a human performs a simple task of fetching objects by stretching and folding his/her arm, and demonstrate that the network can learn invariant features of the generalized motion concepts, classify the motion by referring to self-organized memory structure, and understand a task structure of the observed human bodily motion. These capabilities are essential for machine intelligence to establishing the human-robot shared autonomy, a new style of human-machine collaboration proposed in the area of robotics.     

A tree search method for the container loading problem with shipment priority

This paper addresses a special kind of container loading problem with shipment priority. We present a tree search method, which is based on a greedy heuristic. In the greedy heuristic, blocks made up of identical items with the same orientation are selected for packing into a container. Five evaluation functions are proposed for block selection, and the different blocks selected by each evaluation function constitute the branches of the search tree. A method of space splitting and merging is also embedded in the algorithm to facilitate efficient use of the container space. In addition, the proposed algorithm covers an important constraint called shipment priority to solve practical problems. The validity of the proposed algorithm is examined by comparing the present results with those of published algorithms using the same data.     

Identification of distributed systems and the theory of the regularization

The identification problems, i.e., the problems of finding unknown parameters in distributed systems from the observations are very important in modern control theory. The solutions of these identification problems can be obtained by solving the equations of the first kind. However, the solutions are often unstable. In other words, they are not continuously dependent on the data. The regularization or Tihonov's regularization is known as one of the stabilizing algorithms to solve these non well-posed problems. In this paper is studied the regularization method for identification of distributed systems. Several approximation theorems are proved to solve the equations of the first kind. Then, identification problems are reduced to the minimization of quadratic cost functionals by virtue of these theorems. On the other hand, it is known that the statistical methods for identification such as the maximum likelihood lead to the minimization problems of certain quadratic functionals. Comparing these quadratic cost functionals, the relations between the regularization and the statistical methods are discussed. Further, numerical examples are given to show the effectiveness of this method.     

Fusing multiple data and knowledge sources for signal understandingby genetic algorithm

This paper presents a new approach to partially automating a human expert's proficient interpretation skills for data and knowledge fusion in signal-understanding tasks. The authors start by recognizing the fact that signal interpretation is attributed much to a human expert's domain-specific, pattern-perceiving capability of grasping raw signals by structured representations having multiple levels of abstraction, rather than to some objectively defined knowledge. In other words, that is an emergent or self-organizing process, where information is regarded as perceptual as opposed to objectively defined. First, they attempt to organize such structured representations by usage of a hierarchical clustering method of data analysis. Then, based on these representations they model a human expert's interpretation skill as an activity of searching for an optimum combination of those perceptual units within that structured representation space being constrained by the data. In order to implement this activity, they introduce a genetic algorithm and apply it to the structured representation space assimilating a human analyst's creative interpreting task in flexibly shifting the focal view of attention from the coarse to the precise. They implement a working system for signal understanding of the remote sensing data of seismic prospecting and show the results output by the system     

Development of a 100keV electron beam nano lithography system

A wide range energy (25, 50, 100keV) electron beam lithography system with ZrO/W Schottky electron source and UHV chamber has been developed. The electron probe stability of 2.5%/hour is measured, and a beam diameter of 3nm is confirmed at 100keV beam energy. The ultimate pressure of bakeable work chamber is confirmed to reach 4×10⁻¹⁰Torr. With the UHV chamber and a gas jet nozzle, this system allows to perform in-situ electron beam nanolithography by combining with UHV multichamber systems.     

Duality theory in multiobjective programming

In this paper, a multiobjective programming problem is considered as that of finding the set of all nondominated solutions with respect to the given domination cone. Two point-to-set maps, the primal map and the dual map, and the vector-valued Lagrangian function are defined, corresponding to the case of a scalar optimization problem. The Lagrange multiplier theorem, the saddle-point theorem, and the duality theorem are derived by using the properties of these maps under adequate convexity assumptions and regularity conditions.     

A generalized Lagrangian function and multiplier method

As is well known, a saddle point for the Lagrangian function, if it exists, provides a solution to a convex programming problem; then, the values of the optimal primal and dual objective functions are equal. However, these results are not valid for nonconvex problems.In this paper, several results are presented on the theory of the generalized Lagrangian function, extended from the classical Lagrangian and the generalized duality program. Theoretical results for convex problems also hold for nonconvex problems by extension of the Lagrangian function. The concept of supporting hypersurfaces is useful to add a geometric interpretation to computational algorithms. This provides a basis to develop a new algorithm.     

Conjugate maps and duality in multiobjective optimization

This paper considers duality in convex vector optimization. A vector optimization problem requires one to find all the efficient points of the attainable value set for given multiple objective functions. Embedding the primal problem into a family of perturbed problems enables one to define a dual problem in terms of the conjugate map of the perturbed objective function. Every solution of the stable primal problem is associated with a certain solution of the dual problem, which is characterized as a subgradient of the perturbed efficient value map. This pair of solutions also provides a saddle point of the Lagrangian map.     

Stability of nondominated solutions in multicriteria decision-making

Decision-making problems with multiple noncommensurable objectives are specified by two factors, i.e., the set of all feasible solutions and the domination structure. The solutions are characterized as nondominated points. Hence, in these problems, there may exist two parameter vectors, according to which the above two factors change. The stability of the solution set for perturbations of these parameters is investigated in this paper. The analysis is guided by using the concept of continuity of the solution map defined on the two parameter spaces.