Development of a Socially Interactive System with Whole-Body Movements for BHR-4

Gan Ma, Junyao Gao*, Zhangguo Yu, Xuechao Chen, Qiang Huang, Yunhui Liu

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

6 Citations (Scopus)

Abstract

For a long time, humans have been communicating with others through voice, facial expressions, and body movements. If a humanoid robot has a human-habitual, natural, and human-like interactive form, it tends to be accepted by humans. To date, the majority of the existing humanoid robots have had difficulty in interacting with humans in a human-like way. This study focuses on this issue and develops a socially interactive system for enhancing the natural communication ability of a humanoid robot. The system, which is implemented in an android robot, BHR-4, features hearing, voice conversation, and facial and body emotional expression capabilities. Then, a full-body social motion planner for a humanoid robot is presented. The objective of this planner is to control the whole-body motion of the robot in a way similar to that of humans. Finally, experiments are conducted on the robot regarding its interactions with humans in a pure indoor environment. It is expected that the socially interactive system can enhance the natural communication ability of an android robot. The results of the experiments show that the combination of verbal behavior with facial expressions and body movements is better than verbal behavior alone, verbal behavior combined with facial expressions, or verbal behavior combined with body movements.

Original languageEnglish
Pages (from-to)183-192
Number of pages10
JournalInternational Journal of Social Robotics
Volume8
Issue number2
DOIs
Publication statusPublished - 1 Apr 2016

Keywords

  • Humanoid robot
  • Human–robot interaction
  • Social robot
  • Whole-body movement

Fingerprint

Dive into the research topics of 'Development of a Socially Interactive System with Whole-Body Movements for BHR-4'. Together they form a unique fingerprint.

Cite this