Vision-and-Dialog Navigation
743
13
Microsoft Research321 тыс
Следующее
02.10.19 – 57346:31Популярные
190 дней – 5291:03:57
18.10.22 – 1 0922:32Опубликовано 2 октября 2019, 16:36
Dialog-enabled smart assistants, which communicate via natural language and occupy human homes, have seen widespread adoption in recent years. These systems can communicate information, but do not manipulate objects or move themselves. By contrast, manipulation-capable and mobile robots are still largely deployed in industrial settings, but do not interact with human users. Dialog-enabled robots can bridge this gap, with natural language interfaces helping robots and non-experts collaborate to achieve their goals. In particular, navigation in unseen or dynamic environments to high-level goals (e.g., "Go to the room with a plant") can be facilitated by enabling navigation agents to ask questions in language, and to react to human clarifications on-the-fly. To study this challenge, we introduce Cooperative Vision-and-Dialog Navigation, an English language dataset situated in the Matterport Room-2-Room simulation environment.
See more at microsoft.com/en-us/research/v...
See more at microsoft.com/en-us/research/v...
Свежие видео
9 дней – 9670:45
9 дней – 58 65818:18
15 дней – 6450:12
16 дней – 3974:16
17 дней – 24 70521:45
18 дней – 3310:26Случайные видео
97 дней – 3 2844:47
116 дней – 16 2504:16
252 дня – 2260:24
04.04.22 – 4 2118:00
03.10.14 – 473 2019:07
3 часа – 8620:13
2 дня – 27 58517:08
2 дня – 26920:14
2 дня – 1 57535:30
4 дня – 2 3322:59
5 дней – 17 65031:52
8 дней – 74410:07:43
