SOTAVerified

Autonomous Driving

Autonomous driving is the task of driving a vehicle without human conduction.

Many of the state-of-the-art results can be found at more general task pages such as 3D Object Detection and Semantic Segmentation.

(Image credit: Exploring the Limitations of Behavior Cloning for Autonomous Driving)

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 6092 papers

TitleStatusHype
RoadBEV: Road Surface Reconstruction in Bird's Eye ViewCode3
DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving ScenesCode3
Detect Anything 3D in the WildCode3
Producing and Leveraging Online Map Uncertainty in Trajectory PredictionCode3
Panacea+: Panoramic and Controllable Video Generation for Autonomous DrivingCode3
DeFlow: Decoder of Scene Flow Network in Autonomous DrivingCode3
Does End-to-End Autonomous Driving Really Need Perception Tasks?Code3
LLM4Drive: A Survey of Large Language Models for Autonomous DrivingCode3
PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian SplattingCode3
DeepInteraction++: Multi-Modality Interaction for Autonomous DrivingCode3
TorchSparse: Efficient Point Cloud Inference EngineCode3
NeuroNCAP: Photorealistic Closed-loop Safety Testing for Autonomous DrivingCode3
Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous DrivingCode3
OASim: an Open and Adaptive Simulator based on Neural Rendering for Autonomous DrivingCode3
MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous DrivingCode3
MapTRv2: An End-to-End Framework for Online Vectorized HD Map ConstructionCode3
AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and ReasoningCode3
MaskGWM: A Generalizable Driving World Model with Video Mask ReconstructionCode3
LiDAR4D: Dynamic Neural Fields for Novel Space-time View LiDAR SynthesisCode3
IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object DetectionCode3
MAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAMCode3
HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous DrivingCode3
AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge BasesCode3
HOPE: A Reinforcement Learning-based Hybrid Policy Path Planner for Diverse Parking ScenariosCode3
iDisc: Internal Discretization for Monocular Depth EstimationCode3
MapTR: Structured Modeling and Learning for Online Vectorized HD Map ConstructionCode3
Geometric-aware Pretraining for Vision-centric 3D Object DetectionCode3
GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous DrivingCode3
Generalizing Motion Planners with Mixture of Experts for Autonomous DrivingCode3
CarLLaVA: Vision language models for camera-only closed-loop drivingCode3
HPNet: Dynamic Trajectory Forecasting with Historical Prediction AttentionCode3
CarDreamer: Open-Source Learning Platform for World Model based Autonomous DrivingCode3
Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action ModelsCode3
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based AgentsCode3
Generative AI for Autonomous Driving: Frontiers and OpportunitiesCode3
Leveraging Enhanced Queries of Point Sets for Vectorized Map ConstructionCode3
GenAD: Generative End-to-End Autonomous DrivingCode3
Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and OpportunitiesCode3
GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial UnderstandingCode3
Mind the map! Accounting for existing map information when estimating online HDMaps from sensorCode3
Generalized Trajectory Scoring for End-to-end Multimodal PlanningCode3
GS-SDF: LiDAR-Augmented Gaussian Splatting and Neural SDF for Geometrically Consistent Rendering and ReconstructionCode3
End-to-End Driving with Online Trajectory Evaluation via BEV World ModelCode3
CRITERIA: a New Benchmarking Paradigm for Evaluating Trajectory Prediction Models for Autonomous DrivingCode3
Behavior Generation with Latent ActionsCode3
Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous DrivingCode3
Enhancing End-to-End Autonomous Driving with Latent World ModelCode3
AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-TuningCode3
Embodied Understanding of Driving ScenariosCode3
DrivingWorld: Constructing World Model for Autonomous Driving via Video GPTCode3
Show:102550
← PrevPage 2 of 122Next →
All datasetsCARLA LeaderboardTown05 LongTown05 Short

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ReasonNetDriving Score79.95—Unverified
2InterFuserDriving Score76.18—Unverified
3TCPDriving Score75.14—Unverified
4TF++ WPDriving Score66.32—Unverified
5Learning From All Vehicles (LAV)Driving Score61.85—Unverified
6TransFuserDriving Score61.18—Unverified
7TransFuser (Reproduced)Driving Score55.04—Unverified
8TCP (Reproduced)Driving Score47.91—Unverified
9Latent TransFuserDriving Score45.2—Unverified
10GRIADDriving Score36.79—Unverified
#ModelMetricClaimedVerifiedStatus
1Geometric FusionRC69.17—Unverified
2TransFuserRC56.36—Unverified
#ModelMetricClaimedVerifiedStatus
1Geometric FusionRC86.91—Unverified
2TransFuserRC78.41—Unverified