Visual Navigation

Visual Navigation is the problem of navigating an agent, e.g. a mobile robot, in an environment using camera input only. The agent is given a target image (an image it will see from the target position), and its goal is to move from its current position to the target by applying a sequence of actions, based on the camera observations only.

Source: Vision-based Navigation Using Deep Reinforcement Learning

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 201–225 of 316 papers

Title	Date	Tasks	Status	Hype
Simultaneous Navigation and Construction Benchmarking Environments	Mar 31, 2021	BenchmarkingDeep Reinforcement Learning	CodeCode Available	1
MaAST: Map Attention with Semantic Transformersfor Efficient Visual Navigation	Mar 21, 2021	Deep Reinforcement LearningSemantic Segmentation	—Unverified	0
A Survey of Embodied AI: From Simulators to Research Tasks	Mar 8, 2021	Embodied Question AnsweringQuestion Answering	—Unverified	0
Learning a State Representation and Navigation in Cluttered and Dynamic Environments	Mar 7, 2021	Representation LearningVisual Navigation	—Unverified	0
A Pose-only Solution to Visual Reconstruction and Navigation	Mar 2, 2021	3D Scene ReconstructionComputational Efficiency	CodeCode Available	1
Sequential Place Learning: Heuristic-Free High-Performance Long-Term Place Recognition	Mar 2, 2021	Autonomous DrivingAutonomous Navigation	CodeCode Available	1
Hierarchical and Partially Observable Goal-driven Policy Learning with Goals Relational Graph	Mar 1, 2021	Hierarchical Reinforcement LearningReinforcement Learning (RL)	CodeCode Available	1
Learning for Visual Navigation by Imagining the Success	Feb 28, 2021	NavigateReinforcement Learning (RL)	—Unverified	0
Scene Retrieval for Contextual Visual Mapping	Feb 25, 2021	General ClassificationImage Retrieval	—Unverified	0
Imitation Learning with Human Eye Gaze via Multi-Objective Prediction	Feb 25, 2021	Continuous ControlImitation Learning	CodeCode Available	0
End-to-End Egospheric Spatial Memory	Feb 15, 2021	General Reinforcement LearningImitation Learning	CodeCode Available	1
Learned Camera Gain and Exposure Control for Improved Visual Feature Detection and Matching	Feb 8, 2021	Simultaneous Localization and MappingVisual Navigation	—Unverified	0
A Pipeline for Vision-Based On-Orbit Proximity Operations Using Deep Learning and Synthetic Imagery	Jan 14, 2021	Deep LearningImage Generation	—Unverified	0
Visual Graph Memory With Unsupervised Representation for Visual Navigation	Jan 1, 2021	NavigateVisual Navigation	CodeCode Available	1
Pose Invariant Topological Memory for Visual Navigation	Jan 1, 2021	Contrastive LearningData Augmentation	—Unverified	0
Semantic Audio-Visual Navigation	Dec 21, 2020	PositionVisual Navigation	—Unverified	0
A Recurrent Vision-and-Language BERT for Navigation	Nov 26, 2020	Decision MakingDecoder	CodeCode Available	1
DeepSeqSLAM: A Trainable CNN+RNN for Joint Global Description and Sequence-based Place Recognition	Nov 17, 2020	Autonomous DrivingAutonomous Navigation	CodeCode Available	1
A Few Shot Adaptation of Visual Navigation Skills to New Observations using Meta-Learning	Nov 6, 2020	Deep Reinforcement LearningMeta-Learning	—Unverified	0
Unsupervised Domain Adaptation for Visual Navigation	Oct 27, 2020	Domain AdaptationTranslation	—Unverified	0
On Embodied Visual Navigation in Real Environments Through Habitat	Oct 26, 2020	Domain AdaptationUnsupervised Domain Adaptation	CodeCode Available	0
Visual Navigation in Real-World Indoor Environments Using End-to-End Deep Reinforcement Learning	Oct 21, 2020	Deep Reinforcement LearningGPU	CodeCode Available	1
SHREC 2020 track: 6D Object Pose Estimation	Oct 19, 2020	6D Pose Estimation6D Pose Estimation using RGB	—Unverified	0
Embodied Visual Navigation with Automatic Curriculum Learning in Real Environments	Sep 11, 2020	Deep Reinforcement LearningNavigate	—Unverified	0
Multimodal Aggregation Approach for Memory Vision-Voice Indoor Navigation with Meta-Learning	Sep 1, 2020	Meta-LearningVisual Navigation	—Unverified	0

Show:10 25 50

← PrevPage 9 of 13Next →

All datasets Cooperative Vision-and-Dialogue Navigation R2R SOON Test AI2-THOR Dmlab-30 Help, Anna! (HANNA)

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	NaviLLM	dist_to_end_reduction	7.9	—	Unverified
2	VLN-PETL	dist_to_end_reduction	6.13	—	Unverified
3	early to bed	dist_to_end_reduction	6.03	—	Unverified
4	HAMT	dist_to_end_reduction	5.58	—	Unverified
5	s-agent (NDH-Full)	dist_to_end_reduction	5.27	—	Unverified
6	BabyWalk (r2r-pretrain)	dist_to_end_reduction	4.46	—	Unverified
7	Environment-agnostic Multitask Learning	dist_to_end_reduction	3.91	—	Unverified
8	BabyWalk	dist_to_end_reduction	3.65	—	Unverified
9	Test2-NDH	dist_to_end_reduction	3.44	—	Unverified
10	SCoA	dist_to_end_reduction	3.37	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SUSA	spl	0.64	—	Unverified
2	Meta-Explore	spl	0.61	—	Unverified
3	NaviLLM	spl	0.6	—	Unverified
4	BEV-BERT	spl	0.6	—	Unverified
5	HOP	spl	0.59	—	Unverified
6	DUET	spl	0.58	—	Unverified
7	VLN-PETL	spl	0.58	—	Unverified
8	VLN-BERT	spl	0.57	—	Unverified
9	Prevalent	spl	0.51	—	Unverified
10	RCM+SIL(no early exploration)	spl	0.38	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	AutoVLN	Nav-SPL	27.83	—	Unverified
2	NaviLLM	Nav-SPL	26.26	—	Unverified
3	Meta-Explore	Nav-SPL	25.8	—	Unverified
4	SUSA	Nav-SPL	25.47	—	Unverified
5	DUET	Nav-SPL	21.42	—	Unverified
6	GBE	Nav-SPL	13.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MVV-IN	SPL (All)	17.27	—	Unverified
2	SAVN	SPL (All)	16.15	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PopArt-IMPALA	Medium Human-Normalized Score	72.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Prevalent	spl	28.72	—	Unverified