인간-로봇 팀에서의 공동 움직임과 신뢰 발전
인간-로봇 팀에서 공동 움직임(proxemics와 kinesics)은 신뢰 발전과 관련이 있으며, 이는 신뢰 손상의 조기 경보 신호로 사용될 수 있다.
Efficient Personalization of Robot Behaviors through Preference-based Action Representation Learning
Personalization in human-robot interaction can be achieved efficiently by learning a latent action space that maximizes the mutual information between the pre-trained robot policy and the user preference-aligned domain, without significantly compromising the original task performance.
ロボットに対する共感と心的状態の帰属の関係を調査する
ロボットの共感能力が高いほど、利用者はそのロボットに対して心的状態を帰属する傾向がある。
People Perceive Phantom Costs When Robots Make Overly Generous Offers
People imagine hidden "phantom costs" when robots make overly generous offers, leading them to be less likely to accept the offers.
Ultra-Range Gesture Recognition Using a Simple Web Camera for Effective Human-Robot Interaction
A novel deep learning framework, URGR, enables robust recognition of human gestures from distances up to 25 meters using only a simple RGB camera. The framework combines a super-resolution model, HQ-Net, and a hybrid classifier, GViT, to overcome the challenges of low-resolution and blurry images at long distances.
Online Temporal Action Segmentation with Surround Sampling and Temporally Aware Label Cleaning
Introducing two methods, surround dense sampling and Online Temporally Aware Label Cleaning (O-TALC), to improve the performance of online temporal action segmentation by addressing the issues of inaccurate segment boundaries and oversegmentation.
Auditory Detectability of Wheeled and Quadruped Mobile Robots in Varying Noise Levels and Cognitive Engagement
The auditory detectability of a wheeled robot and a quadruped robot varies significantly, with the quadruped robot being detected at much larger distances, even in high background noise. This has important implications for the design of human-centered robot navigation algorithms.
Modeling Social Interaction Dynamics Using Temporal Graph Networks for Improved Human-Robot Collaboration
The core message of this article is to propose an adapted Temporal Graph Networks (TGN) model that can comprehensively represent social interaction dynamics by incorporating temporal multi-modal behavioral data, including gaze interaction, voice activity, and environmental context. This representation enables practical implementation and outperforms baseline models for tasks like next gaze prediction and next speaker prediction, which are crucial for effective human-robot collaboration.
Generating Socially Compliant Robot Behaviors through Human Motion Forecasting in Shared Representation Space
Our framework ECHO learns a shared representation space between humans and robots to generate socially compliant robot behaviors by forecasting human motions in interactive social scenarios.
Seamless Human-Drone Collaboration through Immersive Mixed Reality Spatial Awareness and Virtual-Physical Interaction
A novel tele-immersive framework that promotes cognitive and physical collaboration between humans and drones through Mixed Reality, incorporating bi-directional spatial awareness and multi-modal virtual-physical interaction approaches.
