论文总结 Maps for Navigation —— Map-Based Model for VLN、ON and VN

最新推荐文章于 2024-07-12 15:56:08 发布

酥三苹

最新推荐文章于 2024-07-12 15:56:08 发布

阅读量221

点赞数 1

文章标签：人工智能机器人

本文链接：https://blog.csdn.net/weixin_44110393/article/details/134613634

版权

这里总结了一下视觉语言导航、目标物体导航、视觉导航等领域中，与map memory有关的论文；现在VLN中相关的SOTA方法几乎都跟map有关系，或者是拓扑地图或者是栅格地图，这里进行总结方便以后阅读。

错误和补充欢迎评论。

Cognitive mapping and planning for visual navigation. CVPR 2017.
Neural Topological SLAM for Visual Navigation. CVPR 2020.
Visual Graph Memory with Unsupervised Representation for Visual Navigation. ICCV2021.
Topological Semantic Graph Memory for Image-Goal Navigation
EgoMap: Projective mapping and structured egocentric memory for Deep RL.

Learning to Explore using Active Neural SLAM. CVPR 2019 Habitat PointGoal Navigation Challenge.
Object Goal Navigation using Goal-Oriented Semantic Exploration. CVPR 2020 AI-Habitat Object Goal Navigation Challenge.
Seeing the un-scene: Learning amodal semantic maps for room navigation. ECCV 2020.
Semantic MapNet: Building Allocentric Semantic Maps and Representations from Egocentric Views. AAAI 2021.
Learning to Map for Active Semantic Goal Navigation. ICLR 2022.
How To Not Train Your Dragon: Training-free Embodied Object Goal Navigation with Semantic Frontiers. RSS 2023.
Object Goal Navigation with Recursive Implicit Maps. IROS 2023.
Interactive Semantic Map Representation for Skill-based Visual Object Navigation. Arxiv 2023.
MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation. NeurIPS 2020.

Topological Planning with Transformers for Vision-and-Language Navigation. CVPR 2021.
Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation. NeurIPS 2022.
Sasra: Semantically-aware spatio-temporal reasoning agent for vision-and-language navigation in continuous environments. ICPR 2022.
Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation. CVPR 2022.
Cross-modal Map Learning for Vision and Language Navigation. CVPR 2022.
Bevbert: Topo-metric map pre-training for language-guided navigation. ICCV 2023.
GridMM: Grid Memory Map for Vision-and-Language Navigation. ICCV 2023.

Visual language maps for robot navigation. ICRA 2023.
Instance-Level Semantic Maps for Vision Language Navigation. IEEE RO-MAN 2023.

关注