Automating Behavior Selection for Affective Telepresence Robot

Vasylkiv, Yurii; Ma, Zhen; Li, Guangliang; Sandry, Eleanor; Brock, Heike; Nakamura, Keisuke; Irani, Pourang; Gómez, Randy

doi:10.1109/icra48506.2021.9560755

Cited by 6 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…-Body pose: skeleton detection [16] is used to obtain the poses of the different persons' parts (limbs, body, head) in the field of view. -Gestures: Roughly 50 bodily movements can be recognized such as waving, pointing, teasing, scratching one's head, asking Haru to be quiet, jumping, laughing, face covering, bowing, clapping, walking, standing, sitting down, standing up, among others [21]. -Face features: Face in the database can be identified.…”

Section: Perceptionmentioning

confidence: 99%

Developing a Robot’s Empathetic Reactive Response Inspired by a Bottom-Up Attention Model

Gómez

Fang

Thill

et al. 2021

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

This paper describes the development of a reactive behavioral response framework for the tabletop robot Haru. The framework enables the robot to react to external stimuli through a repertoire of expressive routines. The behavioral response framework is inspired by the simple reactive behaviors of organisms (e.g. reflexes) based on a bottom-up attention model. First, a participatory study for behavior elicitation was conducted. We explored the possible expressive behaviors of the robot and the possible stimuli trigger. These stimuli-response (S-R) pairs are designed befitting the robot's characteristics. Then, we developed a perception and a reactive behavior module that automatically translates any perceived stimulus into expressive behavioral responses. We evaluated the proposed S-R framework using Haru in an interaction setting and our results show an increase in human attention activity indicative of its positive impact to conveying the robot's sense of agency.

show abstract

Section: Perceptionmentioning

confidence: 99%