Yuki Okafuji

Koji Inoue, Yuki Okafuji, Jun Baba et al.

Turn-taking is a crucial aspect of human-robot interaction, directly influencing conversational fluidity and user engagement. While previous research has explored turn-taking models in controlled environments, their robustness in real-world settings remains underexplored. In this study, we propose a noise-robust voice activity projection (VAP) model, based on a Transformer architecture, to enhance real-time turn-taking in dialogue robots. To evaluate the effectiveness of the proposed system, we conducted a field experiment in a shopping mall, comparing the VAP system with a conventional cloud-based speech recognition system. Our analysis covered both subjective user evaluations and objective behavioral analysis. The results showed that the proposed system significantly reduced response latency, leading to a more natural conversation where both the robot and users responded faster. The subjective evaluations suggested that faster responses contribute to a better interaction experience.

Ryo Miyoshi, Yuki Okafuji, Takuya Iwamoto et al.

In recent years, the demand for social robots has grown, requiring them to adapt their behaviors based on users' states. Accurately assessing user experience (UX) in human-robot interaction (HRI) is crucial for achieving this adaptability. UX is a multi-faceted measure encompassing aspects such as sentiment and engagement, yet existing methods often focus on these individually. This study proposes a UX estimation method for HRI by leveraging multimodal social signals. We construct a UX dataset and develop a Transformer-based model that utilizes facial expressions and voice for estimation. Unlike conventional models that rely on momentary observations, our approach captures both short- and long-term interaction patterns using a multi-instance learning framework. This enables the model to capture temporal dynamics in UX, providing a more holistic representation. Experimental results demonstrate that our method outperforms third-party human evaluators in UX estimation.

He Zhu, Ryo Miyoshi, Yuki Okafuji

Prior human-robot interaction (HRI) research has primarily focused on single-user interactions, where robots do not need to consider the timing or recipient of their responses. However, in multi-party interactions, such as at malls and hospitals, social robots must understand the context and decide both when and to whom they should respond. In this paper, we propose a Transformer-based multi-task learning framework to improve the decision-making process of social robots, particularly in multi-user environments. Considering the characteristics of HRI, we propose two novel loss functions: one that enforces constraints on active speakers to improve scene modeling, and another that guides response selection towards utterances specifically directed at the robot. Additionally, we construct a novel multi-party HRI dataset that captures real-world complexities, such as gaze misalignment. Experimental results demonstrate that our model achieves state-of-the-art performance in respond decisions, outperforming existing heuristic-based and single-task approaches. Our findings contribute to the development of socially intelligent social robots capable of engaging in natural and context-aware multi-party interactions.

Yuki Okafuji, Yasunori Ozaki, Jun Baba et al.

Research currently being conducted on the use of robots as human labor support technology. In particular, the service industry needs to allocate more manpower, and it will be important for robots to support people. This study focuses on using a humanoid robot as a social service robot to convey information in a shopping mall, and the robot's behavioral concepts were analyzed. In order to convey the information, two processes must occur. Pedestrians must stop in front of the robot, and the robot must continue the engagement with them. For the purpose of this study, three types of autonomous behavioral concepts of the robot for the general use were analyzed and compared in these processes in the experiment: active, passive-negative, and passive-positive concepts. After interactions were attempted with 65,000+ pedestrians, this study revealed that the passive-negative concept can make pedestrians stop more and stay longer. In order to evaluate the effectiveness of the robot in a real environment, the comparative results between three behaviors and human advertisers revealed that (1) the results of the active and passive-positive concepts of the robot are comparable to those of the humans, and (2) the performance of the passive-negative concept is higher than that of all participants. These findings demonstrate that the performance of robots is comparable to that of humans in providing information tasks in a limited environment; therefore, it is expected that service robots as a labor support technology will be able to perform well in the real world.

Yuki Tamaru, Yasunori Ozaki, Yuki Okafuji et al.

For a humanoid robot to make eye contact and initiate communication with a person, it is necessary to estimate the person's head position. However, eye contact becomes difficult due to the mechanical delay of the robot when the person is moving. Owing to these issues, it is important to conduct a head-position prediction to mitigate the effect of the delay in the robot motion. Based on the fact that humans turn their heads before changing direction while walking, we hypothesized that the accuracy of three-dimensional (3D) head-position prediction from a first-person view can be improved by considering the head pose. We compared our method with a conventional Kalman filter-based approach, and found our method to be more accurate. The experiment results show that considering the head pose helps improve the accuracy of 3D head-position prediction.