Recently, studies on machine learning have focused on methods that use symmetry implicit in a specific manifold as an inductive bias. Grassmann manifolds provide the ability to handle fundamental shapes represented as shape spaces, enabling stable shape analysis. In this paper, we present a novel approach in which we establish the theoretical foundations for learning distributions on the Grassmann manifold via continuous normalization flows, with the explicit goal of generating stable shapes. Our approach facilitates more robust generation by effectively eliminating the influence of extraneous transformations, such as rotations and inversions, through learning and generating within a Grassmann manifold designed to accommodate the essential shape information of the object. The experimental results indicated that the proposed method could generate high-quality samples by capturing the data structure. Furthermore, the proposed method significantly outperformed state-of-the-art methods in terms of the log-likelihood or evidence lower bound. The results obtained are expected to stimulate further research in this field, leading to advances for stable shape generation and analysis.

Coping with emergency situations requires effective and prompt decision-making under constantly changing situations. The deployment of various kinds of sensors makes it possible to acquire vast amounts of information. At present, however, most information processing is not automated; therefore, the quality of decision-making depends heavily on the capacities of the decision maker. To solve this problem, we propose a system for predicting future situations through parallel simulations based on observation data. To facilitate the development of such systems, we have been developing an optimistic simulation engine (hereafter referred to as O-SE) that supports parallel simulation of many possible situations and dynamic simulation modification based on observation data acquired by sensors. The design and evaluation results of the O-SE are illustrated in this paper.

We propose a data-driven approach to automatically generate a scene where tens to hundreds of characters densely interact with each other. During off-line processing, the close interactions between characters are precomputed by expanding a game tree, and these are stored as data structures called interaction patches. Then, during run-time, the system spatio-temporally concatenates the interaction patches to create scenes where a large number of characters closely interact with one another. Using our method, it is possible to automatically or interactively produce animations of crowds interacting with each other in a stylized way. The method can be used for a variety of applications including TV programs, advertisements and movies.

We have already proposed DTSS (event aware Dynamic Time Step Synchronization method) for speeding up moving objects (MOs) simulation, e.g. aircraft, ships, vehicles and so on, and evaluated it on the HLA (High Level Architecture, IEEE1516) computer cluster environment. However, speeding up the simulation for a number of MOs on a single processor is required as well, when the size of the problem is increased. In this paper, we propose DTSSRT (DTSS for Road Traffic simulation) that can speed up the simulation by reducing the simulation cost of each MO and the synchronization cost between MOs without degrading simulation accuracy. For evaluating DTSS-RT, we employed a road traffic sub-simulator of RoboCup rescue simulation. The results show that the performance of the simulation based on DTSS-RT is improved approximately 2 to 3 times over that of the conventional method except when the situation includes a heavy traffic jam.

A transactional agent is a mobile agent which manipulates objects in one or more than one computer so as to satisfy some constraint like ACID. An agent creates a surrogate agent on a computer on leaving the computer. A surrogate holds objects manipulated by the agent until the agent terminates. The surrogate can recreate a new incarnation of the agent if the agent is faulty. Transactional agents for multiple database servers are implemented in Aglets. We evaluate the performance in terms of total access time compared with traditional client-server model.