Buchumschlag

SafeAlign-VLA: A Negative-Enhanced Safe Alignment Framework for Risk-Aware Autonomous Driving

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Tian, Kefei, Lian, Yuansheng, Yang, Kai, Chen, Xiangdong, Li, Shen
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Robotics Computer Vision and Pattern Recognition
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

C-CoT: Counterfactual Chain-of-Thought with Vision-Language Models for Safe Autonomous Driving
von: Tian, Kefei, et al.
Veröffentlicht: (2026)

Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives
von: Wang, Junli, et al.
Veröffentlicht: (2026)

UncAD: Towards Safe End-to-end Autonomous Driving via Online Map Uncertainty
von: Yang, Pengxuan, et al.
Veröffentlicht: (2025)

Safe2Drive: Evaluating Safe Driving Behaviors of E2E Autonomous Driving Models
von: Sahu, Nishad, et al.
Veröffentlicht: (2026)

Towards Safe and Reliable Autonomous Driving: Dynamic Occupancy Set Prediction
von: Shao, Wenbo, et al.
Veröffentlicht: (2024)

A Computer Vision Approach for Autonomous Cars to Drive Safe at Construction Zone
von: Ahammed, Abu Shad, et al.
Veröffentlicht: (2024)

UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving
von: Li, Yongkang, et al.
Veröffentlicht: (2026)

VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving
von: Huang, Zilin, et al.
Veröffentlicht: (2024)

MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving
von: Huang, Yuzhou, et al.
Veröffentlicht: (2026)

Visual Environment Assessment for Safe Autonomous Quadrotor Landing
von: Secchiero, Mattia, et al.
Veröffentlicht: (2023)

Reasoning-VLA: A Fast and General Vision-Language-Action Reasoning Model for Autonomous Driving
von: Zhang, Dapeng, et al.
Veröffentlicht: (2025)

AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving
von: Wu, Yanhao, et al.
Veröffentlicht: (2026)

DriveCritic: Towards Context-Aware, Human-Aligned Evaluation for Autonomous Driving with Vision-Language Models
von: Song, Jingyu, et al.
Veröffentlicht: (2025)

DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Driving
von: jia, Feiyang, et al.
Veröffentlicht: (2026)

DriveVLM-RL: Neuroscience-Inspired Reinforcement Learning with Vision-Language Models for Safe and Deployable Autonomous Driving
von: Huang, Zilin, et al.
Veröffentlicht: (2026)

AutoDrive-R$^2$: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving
von: Yuan, Zhenlong, et al.
Veröffentlicht: (2025)

Enhancing End-to-End Autonomous Driving with Risk Semantic Distillaion from VLM
von: Qin, Jack, et al.
Veröffentlicht: (2025)

Uni-World VLA: Interleaved World Modeling and Planning for Autonomous Driving
von: Liu, Qiqi, et al.
Veröffentlicht: (2026)

DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving
von: Shang, Shuyao, et al.
Veröffentlicht: (2026)

CoReVLA: A Dual-Stage End-to-End Autonomous Driving Framework for Long-Tail Scenarios via Collect-and-Refine
von: Fang, Shiyu, et al.
Veröffentlicht: (2025)

SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation
von: Li, Wei, et al.
Veröffentlicht: (2025)

Towards Latency-Aware 3D Streaming Perception for Autonomous Driving
von: Peng, Jiaqi, et al.
Veröffentlicht: (2025)

DiffVLA++: Bridging Cognitive Reasoning and End-to-End Driving through Metric-Guided Alignment
von: Gao, Yu, et al.
Veröffentlicht: (2025)

CurricuVLM: Towards Safe Autonomous Driving via Personalized Safety-Critical Curriculum Learning with Vision-Language Models
von: Sheng, Zihao, et al.
Veröffentlicht: (2025)

From Static to Dynamic: a Survey of Topology-Aware Perception in Autonomous Driving
von: Chen, Yixiao, et al.
Veröffentlicht: (2025)

Devil is in Narrow Policy: Unleashing Exploration in Driving VLA Models
von: Chen, Canyu, et al.
Veröffentlicht: (2026)

DiffVLA: Vision-Language Guided Diffusion Planning for Autonomous Driving
von: Jiang, Anqing, et al.
Veröffentlicht: (2025)

Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving
von: Han, Jianhua, et al.
Veröffentlicht: (2025)

SEPT: Standard-Definition Map Enhanced Scene Perception and Topology Reasoning for Autonomous Driving
von: Pei, Muleilan, et al.
Veröffentlicht: (2025)

WAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous Driving
von: Xu, Mingwang, et al.
Veröffentlicht: (2025)

SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignment
von: Renz, Katrin, et al.
Veröffentlicht: (2025)

SEAL: Vision-Language Model-Based Safe End-to-End Cooperative Autonomous Driving with Adaptive Long-Tail Modeling
von: You, Junwei, et al.
Veröffentlicht: (2025)

Is VLA Reasoning Faithful? Probing Safety of Chain-of-Causation in Autonomous Driving Models
von: Mayumu, Nicanor, et al.
Veröffentlicht: (2026)

ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
von: Li, Yongkang, et al.
Veröffentlicht: (2025)

VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models
von: Zhang, Borong, et al.
Veröffentlicht: (2025)

Asynchronous Large Language Model Enhanced Planner for Autonomous Driving
von: Chen, Yuan, et al.
Veröffentlicht: (2024)

TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformers
von: Yu, Bin, et al.
Veröffentlicht: (2026)

Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review
von: Kuznietsov, Anton, et al.
Veröffentlicht: (2024)

Enhancing Autonomous Driving Safety with Collision Scenario Integration
von: Wang, Zi, et al.
Veröffentlicht: (2025)

Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)
von: Yang, Zhenjie, et al.
Veröffentlicht: (2025)