Balancing Performance and Efficiency in Zero-shot Robotic Navigation

Abstract

We present an optimization study of the Vision-Language Frontier Maps (VLFM) applied to the Object Goal Navigation task in robotics. Our work evaluates the efficiency and performance of various vision-language models, object detectors, segmentation models, and multi-modal comprehension and Visual Question Answering modules. Using the $\text{val-mini}$ and $\text{val}$ splits of Habitat-Matterport 3D dataset, we conduct experiments on a desktop with limited VRAM. We propose a solution that achieves a higher success rate (+1.55%) improving over the VLFM BLIP-2 baseline without substantial success-weighted path length loss while requiring $\text{2.3 times}$ less video memory. Our findings provide insights into balancing model performance and computational efficiency, suggesting effective deployment strategies for resource-limited environments.

Submitted to ICTERI 2024 Posters Track

References in corpus (6)

• Learning Transferable Visual Models From Natural Language Supervision
• LAION-5B: An open large-scale dataset for training next generation image-text models
• Can an Embodied Agent Find Your "Cat-shaped Mug"? LLM-Guided Exploration for Zero-Shot Object Navigation
• Frontier Semantic Exploration for Visual Target Navigation
• ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation
• VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangement