Resolving Positional Ambiguity in Dialogues by Vision-Language Models for Robot Navigation

TL;DR

This paper presents a novel approach using vision-language models to resolve positional ambiguity in natural language commands for indoor robot navigation, enabling more accurate and disambiguated navigation instructions.

Contribution

It introduces a two-level method that links language to visual object IDs and depth maps, addressing positional ambiguity in human-robot communication.

Findings

Effective disambiguation of commands with multiple similar objects

Successful mapping from language to visual object IDs and depth maps

First integration of foundation models for positional ambiguity resolution

Abstract

We consider an autonomous navigation robot that can accept human commands through natural language to provide services in an indoor environment. These natural language commands may include time, position, object, and action components. However, we observe that the positional components within such commands usually refer to objects in the environment that may contain different levels of positional ambiguity. For example, the command "Go to the chair!" may be ambiguous when there are multiple chairs of the same type in a room. In order to disambiguate these commands, we employ a large language model and a large vision-language model to conduct multiple turns of conversations with the user. We propose a two-level approach that utilizes a vision-language model to map the meanings in natural language to a unique object ID in images and then performs another mapping from the unique object ID to a 3D depth map, thereby allowing the robot to navigate from its current position to the target position. To the best of our knowledge, this is the first work linking foundation models to the positional ambiguity issue.