Navi2Gaze: Leveraging Foundation Models for Navigation and Target Gazing

TL;DR

Navi2Gaze employs vision-language models to enable robots to navigate and gaze at objects with correct orientation based on task descriptions, significantly improving task accuracy in simulation benchmarks.

Contribution

The paper introduces Navi2Gaze, a novel VLM-driven method that automatically selects optimal robot poses for navigation and object gazing based on task semantics.

Findings

68.8% reduction in Distance to Goal (DTG) in benchmarks

Outperforms existing navigation approaches

Effective in real-world demonstrations

Abstract

Task-aware navigation continues to be a challenging area of research, especially in scenarios involving open vocabulary. Previous studies primarily focus on finding suitable locations for task completion, often overlooking the importance of the robot's pose. However, the robot's orientation is crucial for successfully completing tasks because of how objects are arranged (e.g., to open a refrigerator door). Humans intuitively navigate to objects with the right orientation using semantics and common sense. For instance, when opening a refrigerator, we naturally stand in front of it rather than to the side. Recent advances suggest that Vision-Language Models (VLMs) can provide robots with similar common sense. Therefore, we develop a VLM-driven method called Navigation-to-Gaze (Navi2Gaze) for efficient navigation and object gazing based on task descriptions. This method uses the VLM to score and select the best pose from numerous candidates automatically. In evaluations on multiple photorealistic simulation benchmarks, Navi2Gaze significantly outperforms existing approaches by precisely determining the optimal orientation relative to target objects, resulting in a 68.8% reduction in Distance to Goal (DTG). Real-world video demonstrations can be found on the supplementary website