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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 316 papers

TitleStatusHype
XFeat: Accelerated Features for Lightweight Image MatchingCode5
Navigation World ModelsCode4
Visual Planning: Let's Think Only with ImagesCode3
ViNT: A Foundation Model for Visual NavigationCode3
CityWalker: Learning Embodied Urban Navigation from Web-Scale VideosCode3
LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual PreferencesCode2
NaviDiffusor: Cost-Guided Diffusion Model for Visual NavigationCode2
GaussNav: Gaussian Splatting for Visual NavigationCode2
Scaling Data Generation in Vision-and-Language NavigationCode2
SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic LearningCode2
BEVBert: Multimodal Map Pre-training for Language-guided NavigationCode2
Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge ModelsCode2
Towards Learning a Generalist Model for Embodied NavigationCode2
POPGym: Benchmarking Partially Observable Reinforcement LearningCode2
NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language ModelsCode2
Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language NavigationCode2
Vision-and-Language Navigation via Causal LearningCode2
GOAT-Bench: A Benchmark for Multi-Modal Lifelong NavigationCode2
Sim2Real Predictivity: Does Evaluation in Simulation Predict Real-World Performance?Code1
Last-Mile Embodied Visual NavigationCode1
Learning Exploration Policies for NavigationCode1
HOP: History-and-Order Aware Pre-training for Vision-and-Language NavigationCode1
HabiCrowd: A High Performance Simulator for Crowd-Aware Visual NavigationCode1
An Open Source and Open Hardware Deep Learning-powered Visual Navigation Engine for Autonomous Nano-UAVsCode1
Hierarchical and Partially Observable Goal-driven Policy Learning with Goals Relational GraphCode1
A Pose-only Solution to Visual Reconstruction and NavigationCode1
Language-enhanced RNR-Map: Querying Renderable Neural Radiance Field maps with natural languageCode1
A Recurrent Vision-and-Language BERT for NavigationCode1
Learning from Unlabeled 3D Environments for Vision-and-Language NavigationCode1
Benchmarking Visual Localization for Autonomous NavigationCode1
Offline Reinforcement Learning for 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
Multi3DRefer: Grounding Text Description to Multiple 3D ObjectsCode1
CityLearn: Diverse Real-World Environments for Sample-Efficient Navigation Policy LearningCode1
End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent PhenomenonCode1
MVP: Unified Motion and Visual Self-Supervised Learning for Large-Scale Robotic NavigationCode1
EndoMamba: An Efficient Foundation Model for Endoscopic Videos via Hierarchical Pre-trainingCode1
Agent Journey Beyond RGB: Unveiling Hybrid Semantic-Spatial Environmental Representations for Vision-and-Language NavigationCode1
Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-LearningCode1
Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without SacrificesCode1
Extending Maps with Semantic and Contextual Object Information for Robot Navigation: a Learning-Based Framework using Visual and Depth CuesCode1
CaMP: Causal Multi-policy Planning for Interactive Navigation in Multi-room ScenesCode1
CaMP: Causal Multi-policy Planning for Interactive Navigation in Multi-room ScenesCode1
A Visual Navigation Perspective for Category-Level Object Pose EstimationCode1
An Interactive Navigation Method with Effect-oriented AffordanceCode1
A 64mW DNN-based Visual Navigation Engine for Autonomous Nano-DronesCode1
Cognitive Mapping and Planning for Visual NavigationCode1
Collaborative Visual NavigationCode1
Discriminative Particle Filter Reinforcement Learning for Complex Partial ObservationsCode1
Show:102550
← PrevPage 1 of 7Next →
All datasetsCooperative Vision-and-Dialogue NavigationR2RSOON TestAI2-THORDmlab-30Help, Anna! (HANNA)

Benchmark Results

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