SOTAVerified

Bench2Drive

Bench2Drive is an autonomous driving benchmark based on the CARLA leaderboard 2.0. It consists of 220 short routes featuring safety critical scenarios. The evaluation is performed closed-loop in the CARLA simulator. The performance of an entire driving stack is being evaluated.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–35 of 35 papers

TitleStatusHype
GEMINUS: Dual-aware Global and Scene-Adaptive Mixture-of-Experts for End-to-End Autonomous DrivingCode0
FocalAD: Local Motion Planning for End-to-End Autonomous Driving—0
From Failures to Fixes: LLM-Driven Scenario Repair for Self-Evolving Autonomous Driving—0
GaussianFusion: Gaussian-Based Multi-Sensor Fusion for End-to-End Autonomous DrivingCode0
CogAD: Cognitive-Hierarchy Guided End-to-End Autonomous Driving—0
ReasonPlan: Unified Scene Prediction and Decision Reasoning for Closed-loop Autonomous DrivingCode1
Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)—0
DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving—0
iPad: Iterative Proposal-centric End-to-End Autonomous DrivingCode2
Safety2Drive: Safety-Critical Scenario Benchmark for the Evaluation of Autonomous Driving—0
X-Driver: Explainable Autonomous Driving with Vision-Language Models—0
Two Tasks, One Goal: Uniting Motion and Planning for Excellent End To End Autonomous Driving Performance—0
End-to-End Driving with Online Trajectory Evaluation via BEV World ModelCode3
ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation—0
Hydra-NeXt: Robust Closed-Loop Driving with Open-Loop TrainingCode1
DiffAD: A Unified Diffusion Modeling Approach for Autonomous Driving—0
SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action AlignmentCode3
HiP-AD: Hierarchical and Multi-Granularity Planning with Deformable Attention for Autonomous Driving in a Single DecoderCode2
DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous DrivingCode2
CAPS: Context-Aware Priority Sampling for Enhanced Imitation Learning in Autonomous Driving—0
Sce2DriveX: A Generalized MLLM Framework for Scene-to-Drive Learning—0
Hidden Biases of End-to-End Driving DatasetsCode4
Bench2Drive-R: Turning Real World Data into Reactive Closed-Loop Autonomous Driving Benchmark by Generative Model—0
DiFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient End-to-End Self-DrivingCode1
CarLLaVA: Vision language models for camera-only closed-loop drivingCode3
Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous DrivingCode4
Validity Learning on Failures: Mitigating the Distribution Shift in Autonomous Vehicle Planning—0
SparseDrive: End-to-End Autonomous Driving via Sparse Scene RepresentationCode4
GenAD: Generative End-to-End Autonomous DrivingCode3
DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous DrivingCode2
Hidden Biases of End-to-End Driving ModelsCode2
Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous DrivingCode2
VAD: Vectorized Scene Representation for Efficient Autonomous DrivingCode3
Planning-oriented Autonomous DrivingCode4
Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong BaselineCode1
Show:102550

No leaderboard results yet.