Browse > Robots > Vision-based navigation with language-based assistance

Vision-based navigation with language-based assistance

1 papers with code · Robots

A grounded vision-language task where an agent with visual perception is guided via language to find objects in photorealistic indoor environments. The task emulates a real-world scenario in that (a) the requester may not know how to navigate to the target objects and thus makes requests by only specifying high-level endgoals, and (b) the agent is capable of sensing when it is lost and querying an advisor, who is more qualified at the task, to obtain language subgoals to make progress.

State-of-the-art leaderboards

No evaluation results yet. Help compare methods by submit evaluation metrics.

Greatest papers with code

Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention

CVPR 2019 debadeepta/vnla

We present Vision-based Navigation with Language-based Assistance (VNLA), a grounded vision-language task where an agent with visual perception is guided via language to find objects in photorealistic indoor environments.

IMITATION LEARNING VISION-BASED NAVIGATION WITH LANGUAGE-BASED ASSISTANCE VNLA