PepperPose: Full-Body Pose Estimation with a Companion Robot

要旨

Accurate full-body pose estimation across diverse actions in a user-friendly and location-agnostic manner paves the way for interactive applications in realms like sports, fitness, and healthcare. This task becomes challenging in real-world scenarios due to factors like the user's dynamic positioning, the diversity of actions, and the varying acceptability of the pose-capturing system. In this context, we present PepperPose, a novel companion robot system tailored for optimized pose estimation. Unlike traditional methods, PepperPose actively tracks the user and refines its viewpoint, facilitating enhanced pose accuracy across different locations and actions. This allows users to enjoy a seamless action-sensing experience. Our evaluation, involving 30 participants undertaking daily functioning and exercise actions in a home-like space, underscores the robot's promising capabilities. Moreover, we demonstrate the opportunities that PepperPose presents for human-robot interaction, its current limitations, and future developments.

著者
Chongyang Wang
Tsinghua University, Beijing, China
Siqi Zheng
Tsinghua University, Beijing, China
Lingxiao Zhong
Tsinghua University, Beijing, China
Chun Yu
Tsinghua University, Beijing, China
Chen Liang
Tsinghua University, Beijing, Beijing, China
Yuntao Wang
Tsinghua University, Beijing, China
Yuan Gao
Chinese University of Hong Kong, Shenzhen, Shenzhen, China
Tin Lun Lam
The Chinese University of Hong Kong, Shenzhen, Shenzhen, China
Yuanchun Shi
Tsinghua University, Beijing, China
論文URL

https://doi.org/10.1145/3613904.3642231

動画

会議: CHI 2024

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2024.acm.org/)

セッション: Human-Robot Interaction A

318B
4 件の発表
2024-05-14 23:00:00
2024-05-15 00:20:00