Few-shot Object Grounding and Mapping for Natural Language Robot Instruction Following

11/14/2020 ∙ by Valts Blukis, et al. ∙ 1

We study the problem of learning a robot policy to follow natural language instructions that can be easily extended to reason about new objects. We introduce a few-shot language-conditioned object grounding method trained from augmented reality data that uses exemplars to identify objects and align them to their mentions in instructions. We present a learned map representation that encodes object locations and their instructed use, and construct it from our few-shot grounding output. We integrate this mapping approach into an instruction-following policy, thereby allowing it to reason about previously unseen objects at test-time by simply adding exemplars. We evaluate on the task of learning to map raw observations and instructions to continuous control of a physical quadcopter. Our approach significantly outperforms the prior state of the art in the presence of new objects, even when the prior approach observes all objects during training.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 12

page 14

page 20

page 21

page 22

page 23

page 24

page 25

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.