.png){kind=icon}
返回
EIK-Nav: Boosting zero-shot object navigation with explicit and implicit knowledge
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2025.112945.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Zero-shot Object Navigation demands the agent to explore unfamiliar environments and navigate to certain objects. In this paper, we propose a new framework that combines Explicit and Implicit Knowledge Navigation (EIK-Nav) to facilitate the overall zero-shot object navigation from both the exploration and detection process. The implicit knowledge is derived from the pre-trained vision-language model (VLM) that measures the semantic distance between the textual target category and RGB images, and thus provides a baseline value for determining the exploration potential of a specific area. The explicit knowledge is provided by the large language model (LLM), consisting of the co-occurrence relation among the target, the room, and other objects. EIK-Nav uses explicit knowledge as an extra constraint over the implicit value to decide where the most valuable area to explore is. In the detection process, the explicit co-occurrence relation can further offer additional evidence for determining the confidence of the detected target, which can elevate the detection process from being independent to considering the surrounding context. The experimental results on photo-realistic environments, including Matterport 3D (MP3D), Habitat-Matterport 3D (HM3D), and Gibson demonstrate that our proposed method achieves state-ofthe-art results even compared with training-based methods.
Keyword:
Zero-shot object navigation
Object navigation
Embodied AI
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Investigating Synthetic-to-Real Transfer Robustness for Stereo Matching and Optical Flow Estimation研究合成到真实迁移鲁棒性在立体匹配和光流估计中的应用
PREAI
分享收藏Can an Embodied Agent Find Your “Cat-shaped Mug”? LLM-Based Zero-Shot Object Navigation 具体化的代理可以找到您的 “猫形杯子” 吗？ 基于LLM的零射击对象导航
OAAI
OAAI分享收藏LiDAR-based localization using universal encoding and memory-aware regression.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Enhancing multimodal-input object goal navigation by leveraging large language models for inferring room-object relationship knowledge通过利用大型语言模型推断房间-对象关系知识来增强多模态输入对象目标导航
PREAI
分享收藏Parameter-efficient action planning with large language models for vision-and-language navigation基于大型语言模型的参数高效动作规划，用于视觉与语言导航Pattern RecognitionOAAI
Pattern RecognitionIF7.6
OAAI分享收藏
查看更多内容