paper-with-me

Papers

LOC-ZSON: Language-driven Object-Centric Zero-Shot Object Retrieval and Navigation

2024-05-08 · Tianrui Guan, Yurou Yang, Harry Cheng, Muyuan Lin, Richard Kim, Rajasimman Madhivanan, Arnie Sen, Dinesh Manocha

In this paper, we present LOC-ZSON, a novel Language-driven Object-Centric image representation for object navigation task within complex scenes. We propose an object-centric image representation and corresponding losses for visual-language model (VLM) fine-tuning, which can handle complex object-level queries. In addition, we design a novel LLM-based augmentation and prompt templates for stability during training and zero-shot inference. We implement our method on Astro robot and deploy it in both simulated and real-world environments for zero-shot object navigation. We show that our proposed method can achieve an improvement of 1.38 - 13.38% in terms of text-to-image recall on different benchmark settings for the retrieval task. For object navigation, we show the benefit of our approach in simulation and real world, showing 5% and 16.67% improvement in terms of navigation success rate, respectively.

📄 PDF Abstract BibTeX arXiv:2405.05363

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingObjectRetrieval

Similar Papers 제목 키워드 기반

CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation

2022-03-20 · CVPR 2023 1 · Samir Yitzhak Gadre, Mitchell Wortsman, Gabriel Ilharco, Ludwig Schmidt 외

For robots to be generally useful, they must be able to find arbitrary objects described by people (i.e., be language-driven) even without expensive navigation training on in-domain data (i.e., perform zero-shot inferenc…

image-classificationImage ClassificationObject LocalizationPhilosophy

Zero-shot Object Navigation with Vision-Language Models Reasoning

2024-10-24 · Congcong Wen, Yisiyuan Huang, Hao Huang, Yanjia Huang 외

Object navigation is crucial for robots, but traditional methods require substantial training data and cannot be generalized to unknown environments. Zero-shot object navigation (ZSON) aims to address this challenge, all…

Decision MakingLanguage ModelingLanguage ModellingObject+1

PanoNav: Mapless Zero-Shot Object Navigation with Panoramic Scene Parsing and Dynamic Memory

2025-11-10 · Qunchao Jin, Yilin Wu, Changhao Chen arxiv

Zero-shot object navigation (ZSON) in unseen environments remains a challenging problem for household robots, requiring strong perceptual understanding and decision-making capabilities. While recent methods leverage metr…

Spatial ReasoningScene Parsing

Can an Embodied Agent Find Your "Cat-shaped Mug"? LLM-Guided Exploration for Zero-Shot Object Navigation

2023-03-06 · Vishnu Sashank Dorbala, James F. Mullen Jr., Dinesh Manocha

We present LGX (Language-guided Exploration), a novel algorithm for Language-Driven Zero-Shot Object Goal Navigation (L-ZSON), where an embodied agent navigates to a uniquely described target object in a previously unsee…

Motion PlanningObjectobject-detectionObject Detection+1

3DGSNav: Enhancing Vision-Language Model Reasoning for Object Navigation via Active 3D Gaussian Splatting

2026-02-12 · Wancai Zheng, Hao Chen, Xianlong Lu, Linlin Ou 외 arxiv

Object navigation is a core capability of embodied intelligence, enabling an agent to locate target objects in unknown environments. Recent advances in vision-language models (VLMs) have facilitated zero-shot object navi…

Spatial ReasoningDecision Making