In a dialogue system, when there is a dialogue goal for the dialogue system that is independent of the user's dialogue goal, a dialogue that tries to reach a topic for that goal while coming to terms with the user (i.e., target-guided dialogue) has the potential to be useful for applications such as advertising and recommendation. However, in the case of multiple target-guided strategies, the complexity and multiplicity of designs for switching between target-guided strategies is a challenge. In this paper, we propose the hierarchical structure for dialogue management method, which alleviates the complexity and multiplicity of designing such target-guided strategy switching. It is found that the proposed method automatically complements the topic transitions of skipping, modifying, and sliding, and enhances naturalness of transitions and interest in guided topics.

In this study, we derive a translation vector of manipulating force polytope. The translation vector is derived a function of velocity and acceleration of extended task space. A dynamic manipulability ellipsoid that is performance index is known to translate by joint velocity [12]. We derived the extended task space constructed by task space and internal motion space, and discovered the dynamic manipulability polytope translate by velocity on the extended task space [13]. However, the effect to the manipulating force polytope by velocity on the extended task space is unclear, because external force by contact doesn't consider. In this paper, we discover that the translation vector of the manipulating force polytope becomes a function of acceleration and tensor production of velocity on the extended task space. The manipulating force polytope spanned on an extended force space constructed by a hand force and a force that cause internal motion. Furthermore, we establish that the manipulating force polytope and the manipulating force ellipsoid indicate to same characteristics by showing the manipulating force polytope is circumscribed to the manipulating force ellipsoid. By the results of this paper, we expect to improve force control performance and to improve collision detection performance on a cooperating robot.

This paper addresses a high speed collision check system for path planning. In order to shorten the calculation time of collision check, we apply pipeline processing with FPGA to broad phase collision check. In particular, proposed system is intended for use in bulk picking tasks. Therefore, we approximate robots and obstacles as cylinders and point clouds in broad phase collision check to avoid excessive collision detection at the neighbor of grasp pose. We demonstrate examples of collision check and verify the validity of the proposed system by comparing the calculation time between FPGA and CPU.

Humans can divide perceived continuous speech signals into phonemes and words, which have a double articulation structure, without explicit boundary points and labels, and learn the language. Learning such a double articulation structure of speech signals is important for realizing a robot that can acquire vocabulary and have a conversation. In this paper, we propose a novel statistical model GP-HSMM-DAA (Gaussian Process Hidden Semi Markov Model-based Double Articulation Analyzer) that can learn double articulation structures of time-series data by connecting statistical models hierarchically. In the proposed model, the parameters of each statistical model are mutually updated and learned complementarily. We present that GP-HSMM-DAA can segment continuous speech into phonemes and words with higher accuracy than the baseline methods.

The microinjection technique is widely applied in fields such as biology, medicine, and intracytoplasmic sperm injection (ICSI). Microinjection process requires special skill and, thus, generally ICSI is conducted by embryologists. However, the shortage of embryologists has become a problem in clinics, and there is a need for an easy injection system that does not rely on embryologists. In this study, we propose a micromanipulation interface that assists to perceive cell extension for easy injection system. The proposed interface provides 2-dimensional force/tactile feedback through a fabric actuator with air pressure based on real-time visual sensing of cell deformation. The effectiveness of the proposed interface is verified through puncturing experiments on perceiving cell extension perfumed by inexperienced subjects.