Explore and Explain: Self-supervised Navigation and Recounting
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2020
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929313952038912 |
|---|---|
| author | Bigazzi, Roberto Landi, Federico Cornia, Marcella Cascianelli, Silvia Baraldi, Lorenzo Cucchiara, Rita |
| author_facet | Bigazzi, Roberto Landi, Federico Cornia, Marcella Cascianelli, Silvia Baraldi, Lorenzo Cucchiara, Rita |
| contents | Embodied AI has been recently gaining attention as it aims to foster the development of autonomous and intelligent agents. In this paper, we devise a novel embodied setting in which an agent needs to explore a previously unknown environment while recounting what it sees during the path. In this context, the agent needs to navigate the environment driven by an exploration goal, select proper moments for description, and output natural language descriptions of relevant objects and scenes. Our model integrates a novel self-supervised exploration module with penalty, and a fully-attentive captioning model for explanation. Also, we investigate different policies for selecting proper moments for explanation, driven by information coming from both the environment and the navigation. Experiments are conducted on photorealistic environments from the Matterport3D dataset and investigate the navigation and explanation capabilities of the agent as well as the role of their interactions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2007_07268 |
| institution | arXiv |
| publishDate | 2020 |
| record_format | arxiv |
| spellingShingle | Explore and Explain: Self-supervised Navigation and Recounting Bigazzi, Roberto Landi, Federico Cornia, Marcella Cascianelli, Silvia Baraldi, Lorenzo Cucchiara, Rita Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Robotics Embodied AI has been recently gaining attention as it aims to foster the development of autonomous and intelligent agents. In this paper, we devise a novel embodied setting in which an agent needs to explore a previously unknown environment while recounting what it sees during the path. In this context, the agent needs to navigate the environment driven by an exploration goal, select proper moments for description, and output natural language descriptions of relevant objects and scenes. Our model integrates a novel self-supervised exploration module with penalty, and a fully-attentive captioning model for explanation. Also, we investigate different policies for selecting proper moments for explanation, driven by information coming from both the environment and the navigation. Experiments are conducted on photorealistic environments from the Matterport3D dataset and investigate the navigation and explanation capabilities of the agent as well as the role of their interactions. |
| title | Explore and Explain: Self-supervised Navigation and Recounting |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Robotics |
| url | https://arxiv.org/abs/2007.07268 |