.png){kind=icon}
返回
MVSSC: Meta-reinforcement learning based visual indoor navigation using multi-view semantic spatial context
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patrec.2023.11.023.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In Visual Indoor Navigation (VIN), Deep Reinforcement Learning (DRL) is commonly used by agents to achieve end-to-end mapping from vision to action when navigating toward a target based on observation. However, current DRL-based work suffers from two challenges: partial observability resulting from using solely a single first-person view and poor generalization in the case of unknown scenes and unknown objects. In light of these issues, this paper introduces the integration of multi-view as an expansion of observability and meta -learning as a primary generalization technique into the DRL framework and presents the meta-reinforcement learning method that leverages Multi-View Semantic Spatial Context (MVSSC). Specifically, aiming to explore the informative multi-view context for better efficiency in searching for and navigating to the target, we model the objects' relationship from two aspects, multi-view semantic context (MVSEC) and multi-view spatial context (MVSPC). MVSEC enables agents to encode prior semantic relationships adaptively via a multi-view modulated graph. Meanwhile, MVSPC enhances the spatial representation of target-related objects' correlation through similarity grids of multi-view. After adaptively fusing the multi-view and context information under the meta -reinforcement learning framework, our method can encourage efficient target search and robust navigation with stronger generalization performance to unknown scenes and unknown objects. Extensive experimental results on the AI2-THOR simulator demonstrate that our method outperforms the current state-of-the-art approaches.
Keyword:
Visual indoor navigation
Meta-reinforcement learning
Semantic spatial context
期刊
IF:
3.3
论文数:
8.0K
被引数:
1.6W
机构
引用论文
A Survey on Visual Navigation for Artificial Agents With Deep Reinforcement Learning基于深度强化学习的人工智能体视觉导航研究综述.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations视觉基因组: 使用众包密集图像注释连接语言和视觉OAAI
OAAI分享收藏Multi goals and multi scenes visual mapless navigation in indoor using meta-learning and scene priorsNEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏 没有更多内容
没有更多内容