In this paper, we investigate effects of two kinds of the adaptive Δ-causality control, which adjusts the output timing of the position information among multiple terminals, on cooperative work between two remote robot control systems with force feedback by experiment. One is the local control under which the adaptive Δ-causality control is partially applied to the systems, and the other is the global control under which the adaptive Δ-causality control is globally done. In each system, a user remotely operates a robot having a force sensor by using a haptic interface device while watching video. We conduct cooperative work of carrying an object grasped by two robot arms and compare the two kinds of control in our experiment. Experimental results illustrate that the global control is more effective than the local control for the cooperative work.

In this study, we propose a new deep reinforcement learning-based music recommendation method with knowledge graphs. With the rapid development of Web services, music-related content posted on platforms, such as YouTube, is increasing dramatically. Conventional recommendation methods based on knowledge graphs have struggled with the cold-start problem caused by a lack of user preference information. The proposed method can solve this problem by introducing acoustic feature edges in the constructed knowledge graph. Furthermore, we realize efficient search using a deep reinforcement learning algorithm on a dense knowledge graph introducing acoustic feature-based edges. The proposed method can make appropriate recommendations even with a small amount of user preference information by learning the optimal action of the agent. We confirm the effectiveness of the proposed method by comparing our method with several conventional and state-of-the-art recommendation methods.

This paper investigates the influence of local lag on human perception of softness in a networked virtual environment with haptic sense by Quality of Experience (QoE) assessment. The local lag control can keep the consistency in the game state among multiple terminals by setting the local lag to the network delay. In the assessment, we employ only one terminal in a networked haptic balloon bursting game where there are two balloons in a virtual space; one balloon has a standard value of softness (expressed in force here) and the local lag is set to 0 ms, and the other has a different value of softness and the local lag is set to a certain value. Each subject bursts the two balloons by using a haptic interface device and answers which balloon is harder or not. As a result, we clarify how largely the local lag makes the softness harder.