SOTAVerified

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

Showing 51100 of 316 papers

TitleStatusHype
HOP: History-and-Order Aware Pre-training for Vision-and-Language NavigationCode1
Sound Adversarial Audio-Visual NavigationCode1
Catch Me If You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments with Moving SoundsCode1
Goal-Aware Cross-Entropy for Multi-Target Reinforcement LearningCode1
SGoLAM: Simultaneous Goal Localization and Mapping for Multi-Object Goal NavigationCode1
Waypoint Models for Instruction-guided Navigation in Continuous EnvironmentsCode1
Towards Autonomous Crop-Agnostic Visual Navigation in Arable FieldsCode1
Towards real-world navigation with deep differentiable plannersCode1
Teaching Agents how to Map: Spatial Reasoning for Multi-Object NavigationCode1
Collaborative Visual NavigationCode1
RobustNav: Towards Benchmarking Robustness in Embodied NavigationCode1
Out of the Box: Embodied Navigation in the Real WorldCode1
Pushing it out of the Way: Interactive Visual NavigationCode1
Visual Navigation with Spatial AttentionCode1
SOON: Scenario Oriented Object Navigation with Graph-based ExplorationCode1
Simultaneous Navigation and Construction Benchmarking EnvironmentsCode1
A Pose-only Solution to Visual Reconstruction and NavigationCode1
Sequential Place Learning: Heuristic-Free High-Performance Long-Term Place RecognitionCode1
Hierarchical and Partially Observable Goal-driven Policy Learning with Goals Relational GraphCode1
End-to-End Egospheric Spatial MemoryCode1
Visual Graph Memory With Unsupervised Representation for Visual NavigationCode1
A Recurrent Vision-and-Language BERT for NavigationCode1
DeepSeqSLAM: A Trainable CNN+RNN for Joint Global Description and Sequence-based Place RecognitionCode1
Visual Navigation in Real-World Indoor Environments Using End-to-End Deep Reinforcement LearningCode1
Learning to Set Waypoints for Audio-Visual NavigationCode1
Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without SacrificesCode1
Learning Object Relation Graph and Tentative Policy for Visual NavigationCode1
Semantic Visual Navigation by Watching YouTube VideosCode1
One-Shot Informed Robotic Visual Search in the WildCode1
Visual Navigation Among Humans with Optimal Control as a SupervisorCode1
Learning hierarchical relationships for object-goal navigationCode1
Sparse Graphical Memory for Robust PlanningCode1
Extending Maps with Semantic and Contextual Object Information for Robot Navigation: a Learning-Based Framework using Visual and Depth CuesCode1
MVP: Unified Motion and Visual Self-Supervised Learning for Large-Scale Robotic NavigationCode1
Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-trainingCode1
Discriminative Particle Filter Reinforcement Learning for Complex Partial ObservationsCode1
Think Locally, Act Globally: Federated Learning with Local and Global RepresentationsCode1
Side-Tuning: A Baseline for Network Adaptation via Additive Side NetworksCode1
SoundSpaces: Audio-Visual Navigation in 3D EnvironmentsCode1
Sim2Real Predictivity: Does Evaluation in Simulation Predict Real-World Performance?Code1
CityLearn: Diverse Real-World Environments for Sample-Efficient Navigation Policy LearningCode1
VUSFA:Variational Universal Successor Features Approximator to Improve Transfer DRL for Target Driven Visual NavigationCode1
Vision-and-Dialog NavigationCode1
An Open Source and Open Hardware Deep Learning-powered Visual Navigation Engine for Autonomous Nano-UAVsCode1
Learning Exploration Policies for NavigationCode1
Self-Monitoring Navigation Agent via Auxiliary Progress EstimationCode1
Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-LearningCode1
A 64mW DNN-based Visual Navigation Engine for Autonomous Nano-DronesCode1
Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentsCode1
Cognitive Mapping and Planning for Visual NavigationCode1
Show:102550
← PrevPage 2 of 7Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1NaviLLMdist_to_end_reduction7.9Unverified
2VLN-PETLdist_to_end_reduction6.13Unverified
3early to beddist_to_end_reduction6.03Unverified
4HAMTdist_to_end_reduction5.58Unverified
5s-agent (NDH-Full)dist_to_end_reduction5.27Unverified
6BabyWalk (r2r-pretrain)dist_to_end_reduction4.46Unverified
7Environment-agnostic Multitask Learningdist_to_end_reduction3.91Unverified
8BabyWalkdist_to_end_reduction3.65Unverified
9Test2-NDHdist_to_end_reduction3.44Unverified
10SCoAdist_to_end_reduction3.37Unverified
#ModelMetricClaimedVerifiedStatus
1SUSAspl0.64Unverified
2Meta-Explorespl0.61Unverified
3NaviLLMspl0.6Unverified
4BEV-BERTspl0.6Unverified
5HOPspl0.59Unverified
6DUETspl0.58Unverified
7VLN-PETLspl0.58Unverified
8VLN-BERTspl0.57Unverified
9Prevalentspl0.51Unverified
10RCM+SIL(no early exploration)spl0.38Unverified
#ModelMetricClaimedVerifiedStatus
1AutoVLNNav-SPL27.83Unverified
2NaviLLMNav-SPL26.26Unverified
3Meta-ExploreNav-SPL25.8Unverified
4SUSANav-SPL25.47Unverified
5DUETNav-SPL21.42Unverified
6GBENav-SPL13.3Unverified
#ModelMetricClaimedVerifiedStatus
1MVV-INSPL (All)17.27Unverified
2SAVNSPL (All)16.15Unverified
#ModelMetricClaimedVerifiedStatus
1PopArt-IMPALAMedium Human-Normalized Score72.8Unverified
#ModelMetricClaimedVerifiedStatus
1Prevalentspl28.72Unverified