Visual Navigation With Spatial Attention
Bar Mayo, Tamir Hazan, Ayellet Tal
Abstract
Paths-Ours & [30]'s (b) Our agent's view (c) Our attention (d) [30]'s view Figure 1. Visual navigation. (a) The agent aims at finding a TV (red rectangle) in a living room (top view), starting from a given location (black circle). Our agent's path is marked in orange and [30]'s path is in magenta. At each step, the agent is given a specific view, depending on its position. In this example, our agent starts by turning around in its starting location to gather information-a strategy it has learned. (b) shows our agent's view before the first move forward, whereas (d) shows [30]'s view before its first move forward. (c) shows our attention model, which combines semantic and spatial information of (b)'s view; it directs our agent to move forward, towards the TV. Differently, the view in (d) is part of [30]'s lengthy exploration (magenta path in (a)) after the sought-after TV.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
16 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Trajectory Diffusion for ObjectGoal Navigation cites Object Goal Navigation using Goal-Oriented Semantic Exploration
- Trajectory Diffusion for ObjectGoal Navigation cites PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning
- Semantic MapNet: Building Allocentric Semantic Maps and Representations from Egocentric Views cites Object Goal Navigation using Goal-Oriented Semantic Exploration
- PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning cites Object Goal Navigation using Goal-Oriented Semantic Exploration
- PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning cites Semantic MapNet: Building Allocentric Semantic Maps and Representations from Egocentric Views
- Enhancing Multi-Robot Semantic Navigation Through Multimodal Chain-of-Thought Score Collaboration cites Object Goal Navigation using Goal-Oriented Semantic Exploration
- Enhancing Multi-Robot Semantic Navigation Through Multimodal Chain-of-Thought Score Collaboration cites PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning
- REGNav: Room Expert Guided Image-Goal Navigation cites Object Goal Navigation using Goal-Oriented Semantic Exploration
Cited by top-tier papers16
- PONI: Potential Functions for ObjectGoal Navigation with Interaction-free LearningSanthosh Kumar Ramakrishnan, Devendra Singh Chaplot, Ziad Al-Halah, Jitendra Malik et al.CVPR 2022 · 129 citations
- Trajectory Diffusion for ObjectGoal NavigationXinyao Yu, Sixian Zhang, Xinhang Song, Xiaorong Qin et al.NeurIPS 2024 · 32 citations
- One Step at a Time: Long-Horizon Vision-and-Language Navigation with MilestonesChan Hee Song, Jihyung Kil, Tai-Yu Pan, Brian M. Sadler et al.CVPR 2022 · 21 citations
- Enhancing Multi-Robot Semantic Navigation Through Multimodal Chain-of-Thought Score CollaborationZhixuan Shen, Haonan Luo, Kexun Chen, Fengmao Lv et al.AAAI 2025 · 21 citations
- REGNav: Room Expert Guided Image-Goal NavigationPengna Li, Kangyi Wu, Jingwen Fu, Sanping ZhouAAAI 2025 · 15 citations
Builds on4
- Object Goal Navigation using Goal-Oriented Semantic ExplorationDevendra Singh Chaplot, Dhiraj Gandhi, Abhinav Gupta, Ruslan SalakhutdinovNeurIPS 2020 · 857 citations
- Bayesian Relational Memory for Semantic Visual NavigationYi Wu, Yuxin Wu, Aviv Tamar, Stuart Russell et al.ICCV 2019 · 114 citations
- Semantic MapNet: Building Allocentric Semantic Maps and Representations from Egocentric ViewsVincent Cartillier, Zhile Ren, Neha Jain, Stefan Lee et al.AAAI 2021 · 89 citations
- Situational Fusion of Visual Representation for Visual NavigationWilliam B. Shen, Danfei Xu, Yuke Zhu, Li Fei-Fei et al.ICCV 2019 · 70 citations
Related papers
- Pathdreamer: A World Model for Indoor NavigationJing Yu Koh, Honglak Lee, Yinfei Yang, Jason Baldridge et al.ICCV 2021 · 128 citations
- Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language NavigationZihan Wang, Xiangyang Li, Jiahao Yang, Yeqi Liu et al.CVPR 2024 · 13 citations
- Cross-modal Map Learning for Vision and Language NavigationGeorgios Georgakis, Karl Schmeckpeper, Karan Wanchoo, Soham Dan et al.CVPR 2022 · 2 citations
- NavQ: Learning a Q-Model for Foresighted Vision-and-Language NavigationPeiran Xu, Xicheng Gong, Yadong MuICCV 2025 · 2 citations
- The Road to Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language NavigationYuankai Qi, Zizheng Pan, Yicong Hong, Ming-Hsuan Yang et al.ICCV 2021 · 87 citations
