Stepped Warm-Up–The Progressive Interaction Approach for Human-Robot Interaction in Public

Zhao, Min; Li, Dan; Wu, Zhun; Li, Shiyan; Zhang, Xiaonan; Lu, Yujiao; Zhou, Guangfu; Guan, Daisong

doi:10.1007/978-3-030-23541-3_23

Cited by 5 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All papers in Table 1 use them, whether the robot approaches people, or whether they approach it. For instance, Zhao and colleagues [140] tested the concept of "progressive interaction" with a three-stage model. Each stage relies on the person's distance to the robot to control its expressions and utterances: (i) the far field (from 4.2 m to 2.7 m); (ii) the mid field (from 2.7 m to 1.2 m); and (iii) the near field (less than 1.2 m).…”

Section: Robots Engaging With Peoplementioning

confidence: 99%

Break the Ice: a Survey on Socially Aware Engagement for Human–Robot First Encounters

Avelino

Garcia‐Marques

Ventura

et al. 2021

Int J of Soc Robotics

View full text Add to dashboard Cite

Section: Robots Engaging With Peoplementioning

confidence: 99%

Break the Ice: a Survey on Socially Aware Engagement for Human–Robot First Encounters

Avelino

Garcia‐Marques

Ventura

et al. 2021

Int J of Soc Robotics

View full text Add to dashboard Cite

“…Heenan et al [11] derive action set from Kendon's theory of conducting interaction [14]. The classification is based on the user's distance and head orientation, and the robot action is derived from Hall's proxemics theory [15], which is also suggested by Zhao et al [10]. Further, Zhao et al [10] extend proactive HRI to progressive initiations including visual observation and eye contact.…”

Section: Related Workmentioning

confidence: 99%

“…The classification is based on the user's distance and head orientation, and the robot action is derived from Hall's proxemics theory [15], which is also suggested by Zhao et al [10]. Further, Zhao et al [10] extend proactive HRI to progressive initiations including visual observation and eye contact. Those approaches inevitably require the predefinition of scenarios.…”

Section: Related Workmentioning

confidence: 99%

“…For system performances, Liao et al [16] and Rashed [17] use the success rate of initiation of interaction; Shi et al [18] evaluate the recognition accuracy of participants state. For users' subjective evaluations, Zhao et al [10] and Ozaki et al [6] utilize questionnaire to study users' experiences. Liao et al [16] consider the feedbacks on satisfaction, likability, perceived interruption, perceived hedge, and social-agent orientation.…”

Section: Related Workmentioning

confidence: 99%

“…While prior researchers also propose to use an end-toend framework in generating proactive greetings [7], [8], [9], their works suffer from the following limitations: First, the robot behaviors are restricted to very few types, typically less than 10, most of which are general words such as "Hello" [10], [11], "Excuse me", "May I Help You" [4]. Although those words can "break the ice" to some extent, they provide little information and shows no understanding of the scenario.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Proactive Interaction Framework for Intelligent Social Receptionist Robots

Yang¹,

Wang²,

Tian³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Proactive human-robot interaction (HRI) allows the receptionist robots to actively greet people and offer services based on vision, which has been found to improve acceptability and customer satisfaction. Existing approaches are either based on multi-stage decision processes or based on end-to-end decision models. However, the rule-based approaches require sedulous expert efforts and only handle minimal pre-defined scenarios. On the other hand, existing works with end-to-end models are limited to very general greetings or few behavior patterns (typically less than 10). To address those challenges, we propose a new end-to-end framework, the TransFormer with Visual Tokens for Human-Robot Interaction (TFVT-HRI) 1 . The proposed framework extracts visual tokens of relative objects from an RGB camera first. To ensure the correct interpretation of the scenario, a transformer decision model is then employed to process the visual tokens, which is augmented with the temporal and spatial information. It predicts the appropriate action to take in each scenario and identifies the right target. Our data is collected from an in-service receptionist robot in an office building, which is then annotated by experts for appropriate proactive behavior. The action set includes 1000+ diverse patterns by combining language, emoji expression, and body motions. We compare our model with other SOTA end-to-end models on both offline test sets and online user experiments in realistic office building environments to validate this framework. It is demonstrated that the decision model achieves SOTA performance in action triggering and selection, resulting in more humanness and intelligence when compared with the previous reactive reception policies.

show abstract