点击下方卡片，关注“具身智能之心”公众号
编辑丨具身智能之心
本文只做学术分享，如有侵权，联系删文
更多干货，欢迎加入国内首个具身智能全栈学习社区：具身智能之心知识星球(戳我)，这里包含所有你想要的。
最近有同学向我们咨询了一些具身导航相关的工作，今天也为大家梳理一下这几年发展的路线和方法论，建议收藏。更多内容欢迎加入国内首个具身智能全栈学习社区：具身智能之心知识星球！
点目标导航工作汇总
Comparison of Model-Free and Model-Based Learning-Informed Planning for PointGoal Navigation
会议/年份：CoRL, 2022 论文链接：https://openreview.net/pdf?id=2s92OhjT4L 代码：https://github.com/yimengli46/bellman_point_goal 项目链接：https://yimengli46.github.io/Projects/CoRL2022LHPWorkshop/index.html
RobustNav: Towards Benchmarking Robustness in Embodied Navigation
会议/年份：ICCV, 2021 论文链接：https://arxiv.org/pdf/2104.04112.pdf 代码：https://github.com/allenai/robustnav 项目链接：https://prior.allenai.org/projects/robustnav
The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation
会议/年份：ICCV, 2021 论文链接：https://arxiv.org/pdf/2106.04531.pdf 代码：https://github.com/joel99/objectnav 项目链接：https://xiaoming-zhao.github.io/projects/pointnav-vo
Differentiable SLAM-Net: Learning Particle SLAM for Visual Navigation
会议/年份：CVPR, 2021 论文链接：https://arxiv.org/pdf/2105.07593.pdf
Embodied Visual Navigation with Automatic Curriculum Learning in Real Environments
会议/年份：ICRA, 2021 论文链接：https://arxiv.org/pdf/2009.05429.pdf
Occupancy Anticipation for Efficient Exploration and Navigation
会议/年份：ECCV, 2020 论文链接：http://vision.cs.utexas.edu/projects/occupancy_anticipation/main.pdf 代码：https://github.com/facebookresearch/OccupancyAnticipation 项目链接：http://vision.cs.utexas.edu/projects/occupancy_anticipation/
Auxiliary Tasks Speed Up Learning PointGoal Navigation
会议/年份：CoRL, 2020 论文链接：https://arxiv.org/abs/2007.04561 代码：https://github.com/joel99/habitat-pointnav-aux
Learning to Explore using Active Neural SLAM
会议/年份：ICLR, 2020 论文链接：https://openreview.net/pdf?id=HklXn1BKDH 代码：https://github.com/devendrachaplot/Neural-SLAM 项目链接：https://devendrachaplot.github.io/projects/Neural-SLAM
DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames
会议/年份：ICLR, 2020 论文链接：https://arxiv.org/abs/1911.00357 代码：https://github.com/facebookresearch/habitat-api/tree/master/habitat_baselines/rl/ddppo 项目链接：https://wijmans.xyz/publication/ddppo-2019/
A Behavioral Approach to Visual Navigation with Graph Localization Networks
会议/年份：RSS, 2019. 论文链接：https://arxiv.org/pdf/1903.00445.pdf 代码：https://github.com/kchen92/graphnav 项目链接：https://graphnav.stanford.edu/
SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual Navigation
会议/年份：ICCV, 2019 论文链接：https://arxiv.org/pdf/1905.07512.pdf 代码：https://github.com/facebookresearch/splitnet
Habitat: A Platform for Embodied AI Research
会议/年份：ICCV, 2019 论文链接：https://arxiv.org/abs/1904.01201 代码：https://github.com/facebookresearch/habitat-api 项目链接：https://aihabitat.org/
Cognitive Mapping and Planning for Visual Navigation
会议/年份：CVPR, 2017 论文链接：https://arxiv.org/abs/1702.03920
视听导航工作汇总
Learning Semantic-Agnostic and Spatial-Aware Representation for Generalizable Visual-Audio Navigation
会议/年份： IEEE RA-L 2023 论文链接： https://arxiv.org/pdf/2304.10773.pdf
Pay Self-Attention to Audio-Visual Navigation
会议/年份： BMVC 2022 论文链接： https://arxiv.org/pdf/2210.01353.pdf 主页链接： https://yyf17.github.io/FSAAVN/index.html
SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning
会议/年份： arXiv 2022 论文链接： https://arxiv.org/pdf/2206.08312.pdf 代码： https://github.com/facebookresearch/sound-spaces 主页链接： https://vision.cs.utexas.edu/projects/soundspaces2
Sound Adversarial Audio-Visual Navigation
会议/年份： ICLR 2022 论文链接： https://openreview.net/pdf?id=NkZq4OEYN- 代码： https://github.com/yyf17/SAAVN/tree/main 主页链接： https://yyf17.github.io/SAAVN
Active Audio-Visual Separation of Dynamic Sound Sources
会议/年份： ECCV 2022 论文链接： https://arxiv.org/abs/2202.00850 主页链接： http://vision.cs.utexas.edu/projects/active-av-dynamic-separation/
Move2Hear: Active Audio-Visual Source Separation
会议/年份： ICCV 2021 论文链接： https://arxiv.org/abs/2105.07142 主页链接： http://vision.cs.utexas.edu/projects/move2hear/
Semantic Audio-Visual Navigation
会议/年份： CVPR 2021 论文链接： https://arxiv.org/pdf/2012.11583.pdf 代码： https://github.com/facebookresearch/sound-spaces/tree/main/ss_baselines/savi 主页链接： http://vision.cs.utexas.edu/projects/semantic_audio_visual_navigation/
Learning to Set Waypoints for Audio-Visual Navigation
会议/年份： ICLR 2021 论文链接： https://arxiv.org/pdf/2008.09622.pdf 主页链接： http://vision.cs.utexas.edu/projects/audio_visual_waypoints/
Look, Listen, and Act: Towards Audio-Visual Embodied Navigation
会议/年份： ICRA 2020 论文链接： https://arxiv.org/pdf/2012.11583.pdf 主页链接： http://vision.cs.utexas.edu/projects/semantic_audio_visual_navigation
Audio-Visual Embodied Navigation
会议/年份： ECCV 2020 论文链接： https://arxiv.org/pdf/1912.11474.pdf 主页链接： http://vision.cs.utexas.edu/projects/audio_visual_navigation/
ObjectGoal导航工作汇总
DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects
会议/年份：arXiv 2024 论文链接：https://arxiv.org/abs/2410.02730 主页链接：https://zhaowei-wang-nlp.github.io/divscene-project-page/
MOPA: Modular Object Navigation with PointGoal Agents
会议/年份：WACV 2024 论文链接：https://openaccess.thecvf.com/content/WACV2024/html/Raychaudhuri_MOPA_Modular_Object_Navigation_With_PointGoal_Agents_WACV_2024_paper.html 主页链接：https://youtu.be/Jcspov0UpsA
Self-Supervised Object Goal Navigation with In-Situ Finetuning
会议/年份：IROS 2023 论文链接：https://arxiv.org/abs/2212.05923 主页链接：https://www.youtube.com/watch?v=LXsZst5ZUpU
Good Time to Ask: A Learning Framework for Asking for Help in Embodied Visual Navigation
会议/年份：arXiv 2022 论文链接：https://arxiv.org/abs/2206.10606 代码：https://github.com/jennyzzt/good_time_to_ask
ProcTHOR: Large-Scale Embodied AI Using Procedural Generation
会议/年份：arXiv 2022 论文链接：https://arxiv.org/pdf/2206.06994.pdf 主页链接：https://procthor.allenai.org/
THDA: Treasure Hunt Data Augmentation for Semantic Navigation
会议/年份：ICCV, 2021 论文链接：https://openaccess.thecvf.com/content/ICCV2021/papers/Maksymets_THDA_Treasure_Hunt_Data_Augmentation_for_Semantic_Navigation_ICCV_2021_paper.pdf
Hierarchical Object-to-Zone Graph for Object Navigation
会议/年份：ICCV 2021 论文链接：https://arxiv.org/abs/2109.02066 代码：https://github.com/sx-zhang/HOZ.git 主页链接：https://drive.google.com/file/d/1UtTcFRhFZLkqgalKom6_9GpQmsJfXAZC/view
Auxiliary Tasks and Exploration Enable ObjectGoal Navigation
会议/年份：ICCV 2021 论文链接：https://arxiv.org/pdf/2108.11550.pdf 代码：https://github.com/Xiaoming-Zhao/PointNav-VO 主页链接：https://joel99.github.io/objectnav/
Visual Navigation With Spatial Attention
会议/年份：CVPR 2021 论文链接：https://arxiv.org/pdf/2104.09807.pdf
VTNet: Visual Transformer Network for Object Goal Navigation
会议/年份：ICLR 2021 论文链接：https://arxiv.org/pdf/2009.07783.pdf
Learning hierarchical relationships for object-goal navigation
会议/年份：CoRL, 2020 论文链接：https://arxiv.org/abs/2003.06749
MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation
会议/年份：NeurIPS 2020 论文链接：https://arxiv.org/abs/2012.03912 代码：https://github.com/saimwani/multiON 主页链接：https://shivanshpatel35.github.io/multi-ON/
ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects
会议/年份：arXiv, 2020 论文链接：https://arxiv.org/abs/2006.13171
Semantic Visual Navigation by Watching YouTube Videos
会议/年份：arXiv 2020 论文链接：https://arxiv.org/pdf/2006.10034.pdf 主页链接：https://matthewchang.github.io/value-learning-from-videos/
Learning Object Relation Graph and Tentative Policy for Visual Navigation
会议/年份：ECCV, 2020 论文链接：https://arxiv.org/abs/2007.11018
Object Goal Navigation using Goal-Oriented Semantic Exploration
会议/年份：NeurIPS 2020 论文链接：https://arxiv.org/pdf/2007.00643.pdf 主页链接：https://devendrachaplot.github.io/projects/semantic-exploration
Simultaneous Mapping and Target Driven Navigation
会议/年份：arXiv, 2019 论文链接：https://arxiv.org/abs/1911.07980
Situational Fusion of Visual Representation for Visual Navigation
会议/年份：ICCV, 2019 论文链接：https://arxiv.org/abs/1908.09073
Bayesian Relational Memory for Semantic Visual Navigation
会议/年份：ICCV 2019 论文链接：https://arxiv.org/abs/1909.04306 代码：https://github.com/jxwuyi/HouseNavAgent
Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning
会议/年份：CVPR 2019 论文链接：https://arxiv.org/abs/1812.00971 代码：https://github.com/allenai/savn 主页链接：https://prior.allenai.org/projects/savn
Visual Representations for Semantic Target Driven Navigation
会议/年份：ICRA 2019 论文链接：https://arxiv.org/pdf/1805.06066.pdf 代码：https://github.com/arsalan-mousavian/Navigation
Visual Semantic Navigation using Scene Priors
会议/年份：ICLR, 2019 论文链接：https://arxiv.org/abs/1810.06543
Cognitive Mapping and Planning for Visual Navigation
会议/年份：CVPR 2017 论文链接：https://arxiv.org/abs/1702.03920
ImageGoal导航工作汇总
Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigation
会议/年份：CVPR 2024 论文链接：https://xiaohanlei.github.io/projects/IEVE/IEVE.pdf 主页链接：https://xiaohanlei.github.io/projects/IEVE/
Renderable Neural Radiance Map for Visual Navigation
会议/年份：CVPR 2023 论文链接：https://openaccess.thecvf.com/content/CVPR2023/html/Kwon_Renderable_Neural_Radiance_Map_for_Visual_Navigation_CVPR_2023_paper.html 主页链接：https://rllab-snu.github.io/projects/RNR-Map/
Last-Mile Embodied Visual Navigation
会议/年份：CoRL 2022 论文链接：https://arxiv.org/abs/2211.11746 代码：https://github.com/Jbwasse2/SLING 主页链接：https://jbwasse2.github.io/portfolio/SLING/
Topological Semantic Graph Memory for Image-Goal Navigation
会议/年份：CoRL 2022 论文链接：https://openreview.net/pdf?id=xjTUxBfIzE 代码：https://github.com/rllab-snu/TopologicalSemanticGraphMemory 主页链接：https://github.com/bareblackfoot/Topological-Semantic-Graph-Memory
No RL, No Simulation: Learning to Navigate without Navigating
会议/年份：NeurIPS 2021 论文链接：https://arxiv.org/pdf/2110.09470.pdf
Visual Graph Memory with Unsupervised Representation for Visual Navigation
会议/年份：ICCV 2021 论文链接：https://openaccess.thecvf.com/content/ICCV2021/papers/Kwon_Visual_Graph_Memory_With_Unsupervised_Representation_for_Visual_Navigation_ICCV_2021_paper.pdf 代码：https://github.com/rllab-snu/Visual-Graph-Memory 主页链接：https://rllab-snu.github.io/projects/vgm/doc.html
Learning View and Target Invariant Visual Servoing for Navigation
会议/年份：ICRA 2020 论文链接：https://arxiv.org/pdf/2003.02327.pdf 代码：https://github.com/GMU-vision-robotics/View-Invariant-Visual-Servoing-for-Navigation 主页链接：https://yimengli46.github.io/Projects/ICRA2020/index.html
Neural Topological SLAM for Visual Navigation
会议/年份：CVPR 2020 论文链接：https://arxiv.org/pdf/2005.12256.pdf 主页链接：https://devendrachaplot.github.io/projects/Neural-Topological-SLAM
Semi-Parametric Topological Memory for Navigation
会议/年份：ICLR 2018 论文链接：https://arxiv.org/pdf/1803.00653.pdf 代码：https://github.com/nsavinov/SPTM 主页链接：https://sites.google.com/view/SPTM
Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning
会议/年份：ICRA 2017 论文链接：https://arxiv.org/abs/1609.05143 主页链接：https://prior.allenai.org/projects/target-driven-visual-navigation
视觉语言导航工作汇总
SASRA: Semantically-aware Spatio-temporal Reasoning Agent for Vision-and-Language Navigation in Continuous Environments
会议/年份： ICPR, 2022 论文链接： https://arxiv.org/abs/2108.11945 主页链接： https://zubair-irshad.github.io/projects/SASRA.html Video: https://www.youtube.com/watch?v=DsziGtgaJC0
Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments
会议/年份： EMNLP, 2021 论文链接： https://aclanthology.org/2021.emnlp-main.328 代码： https://github.com/3dlg-hcvc/LAW-VLNCE 主页链接： https://3dlg-hcvc.github.io/LAW-VLNCE Video: https://www.youtube.com/watch?v=7dRymdCIAvo
History Aware Multimodal Transformer for Vision-and-Language Navigation
会议/年份： NeurIPS, 2021 论文链接： https://arxiv.org/pdf/2110.13309.pdf 代码： https://github.com/cshizhe/VLN-HAMT 主页链接： https://cshizhe.github.io/projects/vln_hamt.html
SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation
会议/年份：NeurIPS, 2021 论文链接： https://arxiv.org/pdf/2110.14143.pdf
Curriculum Learning for Vision-and-Language Navigation
会议/年份： NeurIPS, 2021 论文链接： https://arxiv.org/pdf/2111.07228.pdf 代码： https://github.com/IMNearth/Curriculum-Learning-For-VLN
Airbert: In-domain Pretraining for Vision-and-Language Navigation
会议/年份： ICCV, 2021 论文链接： https://arxiv.org/pdf/2108.09105.pdf 代码： https://github.com/airbert-vln/airbert 主页链接： https://airbert-vln.github.io/
Waypoint Models for Instruction-guided Navigation in Continuous Environments
会议/年份： ICCV, 2021 论文链接： https://arxiv.org/pdf/2106.07876.pdf 代码： https://github.com/jacobkrantz/VLN-CE 主页链接： https://jacobkrantz.github.io/waypoint-vlnce/
Vision-Language Navigation with Random Environmental Mixup
会议/年份： ICCV, 2021 论文链接： https://arxiv.org/pdf/2106.07876.pdf 代码： https://github.com/LCFractal/VLNREM
Self-Motivated Communication Agent for Real-World Vision-Dialog Navigation
会议/年份： ICCV, 2021 论文链接： https://openaccess.thecvf.com/content/ICCV2021/papers/Zhu_Self-Motivated_Communication_Agent_for_Real-World_Vision-Dialog_Navigation_ICCV_2021_paper.pdf
Episodic Transformer for Vision-and-Language Navigation
会议/年份： ICCV, 2021 论文链接： https://arxiv.org/pdf/2105.06453.pdf 代码： https://github.com/alexpashevich/E.T. 主页链接： https://sites.google.com/view/episodictransformer
Pathdreamer: A World Model for Indoor Navigation
会议/年份： ICCV, 2021 论文链接： https://arxiv.org/pdf/2105.08756.pdf 代码： https://github.com/google-research/pathdreamer 主页链接： https://google-research.github.io/pathdreamer/
The Road To Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation
会议/年份： ICCV, 2021 论文链接： https://arxiv.org/pdf/2104.04167.pdf 代码： https://github.com/YuankaiQi/ORIST
Neighbor-view Enhanced Model for Vision and Language Navigation
会议/年份： ACM MM, 2021 论文链接： https://arxiv.org/pdf/2107.07201.pdf 代码： https://github.com/MarSaKi/NvEM
Scene-Intuitive Agent for Remote Embodied Visual Grounding
会议/年份： CVPR, 2021 论文链接： https://arxiv.org/pdf/2103.12944.pdf
Room-and-Object Aware Knowledge Reasoning for Remote Embodied Referring Expression
会议/年份： CVPR, 2021 论文链接： https://openaccess.thecvf.com/content/CVPR2021/papers/Gao_Room-and-Object_Aware_Knowledge_Reasoning_for_Remote_Embodied_Referring_Expression_CVPR_2021_paper.pdf
SOON: Scenario Oriented Object Navigation With Graph-Based Exploration
会议/年份： CVPR, 2021 论文链接： https://arxiv.org/pdf/2103.17138.pdf
Topological Planning With Transformers for Vision-and-Language Navigation
会议/年份： CVPR, 2021 论文链接： https://arxiv.org/pdf/2012.05292.pdf
Structured Scene Memory for Vision-Language Navigation
会议/年份： CVPR, 2021 论文链接： https://arxiv.org/pdf/2103.03454.pdf 代码： https://github.com/HanqingWangAI/SSM-VLN
VLN BERT: A Recurrent Vision-and-Language BERT for Navigation
会议/年份： CVPR, 2021 论文链接： https://arxiv.org/abs/2011.13922 代码： https://github.com/YicongHong/Recurrent-VLN-BERT
Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation
会议/年份： ICRA, 2021 论文链接： https://arxiv.org/abs/2104.10674 代码： https://github.com/GT-RIPL/robo-vln 主页链接： https://zubair-irshad.github.io/projects/robo-vln.html Video: https://www.youtube.com/watch?v=y16x9n_zP_4
Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' Rule
会议/年份： ICLR, 2021 论文链接： https://arxiv.org/pdf/2009.07783.pdf
Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning
会议/年份： TCSVT, 2020 论文链接： https://arxiv.org/pdf/2011.10972.pdf
Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation
会议/年份： NeurIPS, 2020 论文链接： https://proceedings.neurips.cc/paper/2020/file/eddb904a6db773755d2857aacadb1cb0-Paper.pdf
Counterfactual Vision-and-Language Navigation: Unravelling the Unseen
会议/年份： NeurIPS, 2020
论文链接： https://proceedings.neurips.cc/paper/2020/file/39016cfe079db1bfb359ca72fcba3fd8-Paper.pdf
论文标题： Language and Visual Entity Relationship Graph for Agent Navigation
会议/年份： NeurIPS, 2020
论文链接： https://arxiv.org/abs/2010.09304
代码： https://github.com/YicongHong/Entity-Graph-VLN
Environment-agnostic Multitask Learning for Natural Language Grounded Navigation
会议/年份： ECCV, 2020 论文链接： https://arxiv.org/abs/2003.00443
Active Visual Information Gathering for Vision-Language Navigation
会议/年份： ECCV, 2020 论文链接： https://arxiv.org/abs/2007.08037 代码： https://github.com/HanqingWangAI/Active_VLN
Soft Expert Reward Learning for Vision-and-Language Navigation
会议/年份： ECCV, 2020 论文链接： https://arxiv.org/abs/2007.10835
Improving Vision-and-Language Navigation with Image-Text Pairs from the Web
会议/年份： ECCV, 2020 论文链接： https://arxiv.org/abs/2004.14973
Counterfactual Vision-and-Language Navigation via Adversarial Path Sampling
会议/年份： ECCV, 2020 论文链接： https://arxiv.org/abs/1911.07308 代码： https://github.com/jacobkrantz/VLN-CE 主页链接： https://jacobkrantz.github.io/vlnce
Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments
会议/年份： ECCV, 2020 论文链接： https://arxiv.org/abs/2004.02857 代码： https://github.com/jacobkrantz/VLN-CE 主页链接： https://jacobkrantz.github.io/vlnce
Sub-Instruction Aware Vision-and-Language Navigation
会议/年份： arXiv, 2020 论文链接： https://arxiv.org/abs/2004.02707
Take the Scenic Route: Improving Generalization in Vision-and-Language Navigation
会议/年份： - arXiv, 2020 论文链接： https://arxiv.org/abs/2003.14269
Vision-Dialog Navigation by Exploring Cross-modal Memory
会议/年份： CVPR, 2020 论文链接： https://arxiv.org/abs/2003.06745 代码： https://github.com/yeezhu/CMN.pytorch
Multi-View Learning for Vision-and-Language Navigation
会议/年份： arXiv, 2020 论文链接： https://arxiv.org/abs/2003.00857
Counterfactual Vision-and-Language Navigation via Adversarial Path Sampling
会议/年份： ECCV, 2020 论文链接： https://arxiv.org/abs/1911.07308
Environment-agnostic Multitask Learning for Natural Language Grounded Navigation
会议/年份： ECCV, 2020 论文链接： https://arxiv.org/abs/2003.00443
Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training
会议/年份： CVPR, 2020 论文链接： https://arxiv.org/abs/2002.10638 代码： https://github.com/weituo12321/PREVALENT
Just Ask: An Interactive Learning Framework for Vision and Language Navigation
会议/年份： AAAI, 2020 论文链接： https://arxiv.org/abs/1912.00915
Perceive, Transform, and Act: Multi-Modal Attention Networks for Vision-and-Language Navigation
会议/年份： arXiv, 2019 论文链接： https://arxiv.org/abs/1911.12377 代码： https://github.com/aimagelab/perceive-transform-and-act
Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks
会议/年份： CVPR, 2020 论文链接： https://arxiv.org/abs/1911.07883
Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation
会议/年份： CVPR, 2020 论文链接： https://arxiv.org/abs/1911.07450
Transferable Representation Learning in Vision-and-Language Navigation
会议/年份： ICCV, 2019 论文链接： https://arxiv.org/abs/1908.03409
Embodied Vision-and-Language Navigation with Dynamic Convolutional Filters
会议/年份： BMVC, 2019 论文链接： https://arxiv.org/abs/1907.02985 代码： https://github.com/aimagelab/DynamicConv-agent
Chasing Ghosts: Instruction Following as Bayesian State Tracking
会议/年份： NeurIPS, 2019 论文链接： https://arxiv.org/abs/1907.02022 代码： https://github.com/batra-mlp-lab/vln-chasing-ghosts Video: https://www.youtube.com/watch?v=eoGbescCNP0
Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning
会议/年份： EMNLP, 2019 论文链接： https://arxiv.org/abs/1812.04155 代码： https://github.com/debadeepta/vnla Video: https://youtu.be/Vp6C29qTKQ0
Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention
会议/年份： CVPR, 2019 论文链接： https://arxiv.org/abs/1909.01871 代码： https://github.com/khanhptnk/hanna Video: https://youtu.be/18P94aaaLKg
Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation
会议/年份： CVPR, 2019 论文链接： http://arxiv.org/abs/1903.02547 代码： https://github.com/Kelym/FAST Video: https://www.youtube.com/watch?v=AD9TNohXoPA
TOUCHDOWN: Natural Language Navigation and Spatial Reasoning in Visual Street Environments
会议/年份： CVPR, 2019 论文链接： https://arxiv.org/pdf/1811.12354.pdf 代码： https://github.com/lil-lab/touchdown
The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation
会议/年份： CVPR, 2019 论文链接： https://arxiv.org/abs/1903.01602 代码： https://github.com/chihyaoma/regretful-agent 主页链接： https://chihyaoma.github.io/project/2019/02/25/regretful.html
Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
会议/年份： ICLR, 2019 论文链接： https://arxiv.org/abs/1901.03035 代码： https://github.com/chihyaoma/selfmonitoring-agent 主页链接： https://chihyaoma.github.io/project/2018/09/27/selfmonitoring.html
Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
会议/年份： CVPR, 2019 论文链接： https://arxiv.org/abs/1811.10092
Speaker-Follower Models for Vision-and-Language Navigation
会议/年份： NeurIPS, 2018 论文链接： https://arxiv.org/abs/1806.02724 代码： https://github.com/ronghanghu/speaker_follower 主页链接： http://ronghanghu.com/speaker_follower/
Mapping Instructions to Actions in 3D Environmentswith Visual Goal Prediction
会议/年份： EMNLP, 2018 论文链接： https://arxiv.org/abs/1809.00786
Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation
会议/年份： ECCV, 2018 论文链接： https://arxiv.org/abs/1803.07729
Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments
会议/年份： CVPR, 2018 论文链接： https://arxiv.org/abs/1711.07280 代码： https://github.com/peteanderson80/Matterport3DSimulator 主页链接： https://bringmeaspoon.org/
更多内容欢迎加入国内首个具身智能全栈学习社区：具身智能之心知识星球！
