.png){kind=icon}
返回
Learning Heterogeneous Relation Graph and Value Regularization Policy for Visual Navigation
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2023.3300888.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The goal of visual navigation is steering an agent to find a given target object with current observation. It is crucial to learn an informative visual representation and robust navigation policy in this task. Aiming to promote these two parts, we propose three complementary techniques, heterogeneous relation graph (HRG), a value regularized navigation policy (VRP), and gradient-based meta learning (ML). HRG integrates object relationships, including object semantic closeness and spatial directions, e.g., a knife is usually co-occurrence with bowl semantically or located at the left of the fork spatially. It improves visual representation learning. Both VRP and gradient-based ML improve robust navigation policy, regulating this process of the agent to escape from the deadlock states such as being stuck or looping. Specifically, gradient-based ML is a type of supervision method used in policy network training, which eliminates the gap between the seen and unseen environment distributions. In this process, VRP maximizes the transformation of the mutual information between visual observation and navigation policy, thus improving more informed navigation decisions. Our framework shows superior performance over the current state-of-the-art (SOTA) in terms of success rate and success weighted by length (SPL). Our HRG outperforms the Visual Genome knowledge graph on cross-scene generalization with approximate to 56% and F139% improvement on Hits@5(& lowast;) (proportion of correct entities ranked in top 5) and MRR & lowast; (mean reciprocal rank), respectively. Our code and HRG datasets will be made publicly available in the scientific community.
Keyword:
Knowledge graph
meta learning (ML)
reinforcement learning (RL)
value regularization policy
visual navigation
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
.png){kind=icon}
Psychometrics of the Child PTSD Symptom Scale for DSM-5 for Trauma-Exposed Children and Adolescents
OAAI
OAAI分享收藏Optimal Graph Transformer Viterbi knowledge inference network for more successful visual navigation用于更成功的视觉导航的最佳图形变压器Viterbi知识推理网络
PREAI
分享收藏分享收藏
查看更多内容