Sean-Vr

Zhang, Qiping; Tsoi, Nathan; Vázquez, Marynel

doi:10.1145/3568294.3580039

Cited by 1 publication

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Robotics simulators model aspects of the real world in a virtual environment and render virtual representations of the real world, often using game engines such as Unity [10], [52], [53]. In this work, we take advantage of the SEAN 2.0 simulator [10], which integrates with the Robot Operating System, and supports VR [11]. Virtual Reality interfaces have gained popularity in HRI [54]- [59].…”

Section: Related Workmentioning

confidence: 99%

“…We organized observations of human-robot interactions, as recorded in SEAN-VR [11], into the features described below.…”

Section: Observationsmentioning

confidence: 99%

“…Due to the complexity of reliably capturing observations of implicit feedback during navigation tasks, we performed a data collection effort using the Social Environment for Autonomous Navigation (SEAN) 2.0 [10] with Virtual Reality (VR) [11]. 3 Humans took part in the simulations through an avatar, which was controlled using a VR headset, as in Fig.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Recent Advances in Mobile Robot Localization in Complex Scenarios

Zhang

Liu

et al. 2023

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Human impressions of robot performance are often measured through surveys. As a more scalable and cost-effective alternative, we study the possibility of predicting people's impressions of robot behavior using non-verbal behavioral cues and machine learning techniques. To this end, we first contribute the SEAN TOGETHER Dataset consisting of observations of an interaction between a person and a mobile robot in a Virtual Reality simulation, together with impressions of robot performance provided by users on a 5-point scale. Second, we contribute analyses of how well humans and supervised learning techniques can predict perceived robot performance based on different combinations of observation types (e.g., facial, spatial, and map features). Our results show that facial expressions alone provide useful information about human impressions of robot performance; but in the navigation scenarios we tested, spatial features are the most critical piece of information for this inference task. Also, when evaluating results as binary classification (rather than multiclass classification), the F1-Score of human predictions and machine learning models more than doubles, showing that both are better at telling the directionality of robot performance than predicting exact performance ratings. Based on our findings, we provide guidelines for implementing these predictions models in real-world navigation scenarios.

show abstract