Paper Image

Language reasoning for robot navigation

Published on:

21 July 2023

Primary Category:


Paper Authors:

Dmitriy Rivkin,

Nikhil Kakodkar,

Francois Hogan,

Bobak H. Baghi,

Gregory Dudek


Key Details

Has robot explore environment and detect objects

Uses language model to interpret user's conversational instructions

Associates objects with locations using spatial indexing

Can handle complex queries better than traditional methods

Demonstrates feasibility on physical robot system

AI generated summary

Language reasoning for robot navigation

This paper explores using large language models to help robots navigate environments and follow complex instructions expressed in natural language. The approach has a robot first explore an environment and detect objects, then uses a language model to interpret free-form user instructions and associate objects with locations. This allows the robot to handle more conversational queries compared to traditional robotic systems.

Answers from this paper


No comments yet, be the first to start the conversation...

Sign up to comment on this paper

Sign Up