人机交互过程中，安全性是第一位的。传统的人机安全多关注物理安全，少关注人的心理安全。本课题组基于视觉信息，估计人的表情、头部姿态和视角，分析人的情绪变化和注意力变化，从而预测人的运动，调整机器人运动控制策略，达到保护人机物理安全和心理安全的目的。预印本地址：

\\
arXiv:2010.11671
From: Guoliang Liu Prof. Dr. <liuguoliang@sdu.edu.cn>
Date: Tue, 29 Sep 2020 04:19:53 GMT   (21850kb,D)

Title: Motion Planning Combines Psychological Safety and Motion Prediction for
  a Sense Motive Robot
Authors: Hejing Ling, Guoliang Liu, Guohui Tian
Categories: cs.HC cs.CV cs.RO
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
\\
  Human safety is the most important demand for human robot interaction and
collaboration (HRIC), which not only refers to physical safety, but also
includes psychological safety. Although many robots with different
configurations have entered our living and working environments, the human
safety problem is still an ongoing research problem in human-robot coexistence
scenarios. This paper addresses the human safety issue by covering both the
physical safety and psychological safety aspects. First, we introduce an
adaptive robot velocity control and step size adjustment method according to
human facial expressions, such that the robot can adjust its movement to keep
safety when the human emotion is unusual. Second, we predict the human motion
by detecting the suddenly changes of human head pose and gaze direction, such
that the robot can infer whether the human attention is distracted, predict the
next move of human and rebuild a repulsive force to avoid potential collision.
Finally, we demonstrate our idea on a 7 DOF TIAGo robot in the 3D Gazebo
environment, which shows that the robot becomes sense motive, and responds to
human action and emotion changes quickly and efficiently.
\\

本成果获得了国家自然科学基金共融机器人重大研究计划支持。