A study on the social acceptance of a robot in a multi-human interaction using an F-formation based motion model

Yang, Shih-An; Gamborino, Edwinn; Yang, Chun-Tang; Fu, Li-Chen

doi:10.1109/iros.2017.8206105

Cited by 8 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An REML analysis on the Not Free metric indicated that there were significant differences by Method ( F [9, 3114] = 64.72, p < 0.0001). The post hoc test showed that the baseline method by Yang et al (2017) resulted in significantly more poses generated in occupied cells of the environment map than all other methods. This was expected because the baseline did not consider the environment map in its calculations.…”

Section: Evaluation On the Cocktail Party Datasetmentioning

confidence: 98%

“…Another important related work is that of Yang et al (2017 ), which proposed an approach for a robot to position itself relative to humans during a group conversation. Because this approach builds on geometric properties of F-Formations, we consider it as a baseline for the proposed methods in our evaluation.…”

Section: Related Workmentioning

confidence: 99%

“…Baseline method: We implemented the pose generation method by Yang et al (2017) . As with our model-based approach, this method seeks a circular spatial pattern but without explicitly accounting for environment characteristics.…”

Section: Evaluation On the Cocktail Party Datasetmentioning

confidence: 99%

“…Fit metric indicated a significant effect of method ( F [9, 3114] = 5.50, p < 0.0001). A Tukey honestly significant difference (HSD) post hoc test showed that the baseline method by Yang et al (2017) led to significantly higher Circ. Fit values than the other methods.…”

Section: Evaluation On the Cocktail Party Datasetmentioning

confidence: 99%

See 3 more Smart Citations

Pose Generation for Social Robots in Conversational Group Formations

et al. 2022

View full text Add to dashboard Cite

We study two approaches for predicting an appropriate pose for a robot to take part in group formations typical of social human conversations subject to the physical layout of the surrounding environment. One method is model-based and explicitly encodes key geometric aspects of conversational formations. The other method is data-driven. It implicitly models key properties of spatial arrangements using graph neural networks and an adversarial training regimen. We evaluate the proposed approaches through quantitative metrics designed for this problem domain and via a human experiment. Our results suggest that the proposed methods are effective at reasoning about the environment layout and conversational group formations. They can also be used repeatedly to simulate conversational spatial arrangements despite being designed to output a single pose at a time. However, the methods showed different strengths. For example, the geometric approach was more successful at avoiding poses generated in nonfree areas of the environment, but the data-driven method was better at capturing the variability of conversational spatial formations. We discuss ways to address open challenges for the pose generation problem and other interesting avenues for future work.

show abstract

Section: Evaluation On the Cocktail Party Datasetmentioning

confidence: 98%

Section: Related Workmentioning

confidence: 99%

Section: Evaluation On the Cocktail Party Datasetmentioning

confidence: 99%

Section: Evaluation On the Cocktail Party Datasetmentioning

confidence: 99%

See 2 more Smart Citations

Pose Generation for Social Robots in Conversational Group Formations

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The goal of F-Formation detection is to estimate the o-space of the group, which is the space in front of group members or in the center of the group [69]. Some work explored rotating the robot's orientation and using motion models to determine how they impact F-Formations [69,73,139]. Vazquez et al [135] designed an F-Formation detection system that uses position and head orientation to track the direction of people's lower body, which generates soft group assignments to track body orientation.…”

Section: Group Spatial Behaviorsmentioning

confidence: 99%

Robot-Centric Perception of Human Groups

Taylor

Chan

Riek

2020

J. Hum.-Robot Interact.

View full text Add to dashboard Cite

The robotics community continually strives to create robots that are deployable in real-world environments. Often, robots are expected to interact with human groups. To achieve this goal, we introduce a new method, the Robot-Centric Group Estimation Model (RoboGEM), which enables robots to detect groups of people. Much of the work reported in the literature focuses on dyadic interactions, leaving a gap in our understanding of how to build robots that can effectively team with larger groups of people. Moreover, many current methods rely on exocentric vision, where cameras and sensors are placed externally in the environment, rather than onboard the robot. Consequently, these methods are impractical for robots in unstructured, human-centric environments, which are novel and unpredictable. Furthermore, the majority of work on group perception is supervised, which can inhibit performance in real-world settings. RoboGEM addresses these gaps by being able to predict social groups solely from an egocentric perspective using color and depth (RGB-D) data. To achieve group predictions, RoboGEM leverages joint motion and proximity estimations. We evaluated RoboGEM against a challenging, egocentric, real-world dataset where both pedestrians and the robot are in motion simultaneously, and show RoboGEM outperformed two state-of-the-art supervised methods in detection accuracy by up to 30%, with a lower miss rate. Our work will be helpful to the robotics community, and serve as a milestone to building unsupervised systems that will enable robots to work with human groups in real-world environments.

show abstract

Generating Social-Aware Locations for a Robot in a Human Group by Image Generation Using Adversarial Learning

Poluan,

Chen

2024

IEEE Access

View full text Add to dashboard Cite

A study on the social acceptance of a robot in a multi-human interaction using an F-formation based motion model

Cited by 8 publications

References 16 publications

Pose Generation for Social Robots in Conversational Group Formations

Pose Generation for Social Robots in Conversational Group Formations

Robot-Centric Perception of Human Groups

Generating Social-Aware Locations for a Robot in a Human Group by Image Generation Using Adversarial Learning

Contact Info

Product

Resources

About