Improving Visual Perception of a Social Robot for Controlled and In-the-wild Human-robot Interaction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929265521459200 |
|---|---|
| author | Zhong, Wangjie Tian, Leimin Le, Duy Tho Rezatofighi, Hamid |
| author_facet | Zhong, Wangjie Tian, Leimin Le, Duy Tho Rezatofighi, Hamid |
| contents | Social robots often rely on visual perception to understand their users and the environment. Recent advancements in data-driven approaches for computer vision have demonstrated great potentials for applying deep-learning models to enhance a social robot's visual perception. However, the high computational demands of deep-learning methods, as opposed to the more resource-efficient shallow-learning models, bring up important questions regarding their effects on real-world interaction and user experience. It is unclear how will the objective interaction performance and subjective user experience be influenced when a social robot adopts a deep-learning based visual perception model. We employed state-of-the-art human perception and tracking models to improve the visual perception function of the Pepper robot and conducted a controlled lab study and an in-the-wild human-robot interaction study to evaluate this novel perception function for following a specific user with other people present in the scene. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_01766 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving Visual Perception of a Social Robot for Controlled and In-the-wild Human-robot Interaction Zhong, Wangjie Tian, Leimin Le, Duy Tho Rezatofighi, Hamid Robotics Computer Vision and Pattern Recognition Social robots often rely on visual perception to understand their users and the environment. Recent advancements in data-driven approaches for computer vision have demonstrated great potentials for applying deep-learning models to enhance a social robot's visual perception. However, the high computational demands of deep-learning methods, as opposed to the more resource-efficient shallow-learning models, bring up important questions regarding their effects on real-world interaction and user experience. It is unclear how will the objective interaction performance and subjective user experience be influenced when a social robot adopts a deep-learning based visual perception model. We employed state-of-the-art human perception and tracking models to improve the visual perception function of the Pepper robot and conducted a controlled lab study and an in-the-wild human-robot interaction study to evaluate this novel perception function for following a specific user with other people present in the scene. |
| title | Improving Visual Perception of a Social Robot for Controlled and In-the-wild Human-robot Interaction |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.01766 |