Autonomous Vehicle Technology and Safety

Neueste Paper

• TerrainForge: Physics-Grounded road geometry Editing for Counterfactual Autonomous Driving

  Yang Chen, Yicheng Zhu, zhenning Li, Tao Li, Zilin Bian · 5. Oktober 2026

  Road geometry (e.g., crests, sags, and speed humps) and surface conditions (e.g., wet or icy pavement) affect how vehicles move, what drivers and onboard cameras observe, and how much clearance remains between vehicles. Editing these properties in a driving scene therefore requires corresponding cha…

• Evaluating Physical Consistency and Plausibility in Generative Scenario Models for Autonomous Driving

  Manasa Mariam Mammen, Zafer Kayatas, Stefan Wagner · 2. Oktober 2026

  Generative AI models are increasingly used for scenario generation in autonomous driving. While they can generate realistic-looking scenarios, they often provide limited transparency into learned representations and consistency with real-world vehicle dynamics. This lack of formal assurance limits t…

• Comparative study of adapting pre-trained models for driving behavior video captioning

  Sayak Mallick, Philipp Geiger, Augustin Kelava · 1. Oktober 2026

  This report examines and compares some of the many fine tuning and prompting methods existing, applying them within the domain of autonomous driving. The idea is to compare these methods by adapting a Large Language Model (LLM) on a video dataset. LLM's have become extremely good at achieving a good…

• Vision-Language-Action Autonomous Driving Agent with Language-based Memory

  Kai Yan, Xiangyu Chen, Yulong Cao, Alex Naumann, Peter Karkus, Yan Wang, Jef Packer, Alex Schwing, Yuxiong Wang, Boris Ivanovic, Wenjie Luo, Marco Pavone · 1. Oktober 2026

  Vision-Language-Action (VLA) foundation models have recently emerged as one of the prevailing solutions for autonomous driving, as they can utilize knowledge acquired during vision-language pretraining for accurate and interpretable driving. However, VLAs can take only a limited number of frames as …

• VehicleArena: A Realistic Urban Environment for Multi-Agent Driving

  Jie Yang, Jiajun Chen, Jiazheng Zhou, Mianqiu Huang, Yining Zheng, Yuxin Wang, Xipeng Qiu · 1. Oktober 2026

  Real-world embodied agents often pursue independent objectives within a shared physical environment, where their actions can alter the conditions faced by others. Existing benchmarks, however, typically assume shared goals or explicitly prescribed interaction protocols, leaving such emergent physica…

• TACTIC: Temporal and Context-Aware LLM Tactical Planning for Roadside LiDAR Attacks

  Yiming Gao, Shaocheng Luo · 1. Oktober 2026

  Physical LiDAR attacks are often evaluated using fixed primitives and manually selected parameters, despite their strong dependence on surrounding traffic. We present TACTIC, a scene-aware framework that uses a multimodal large language model (MLLM) to coordinate state-adaptive roadside LiDAR attack…

• DrivingBench: Can Vision-Language Models Drive a Toyota Corolla?

  Aditya Ramabadran, Simon Mahns, Tobias Gessler · 1. Oktober 2026

  Frontier models excel at many digital benchmarks, yet their ability to drive a real car, an everyday human skill, remains largely untested. We present DrivingBench, to our knowledge the first benchmark where general-purpose vision-language models must drive a real car. Through three tools, the model…

• Efficient Multi-Modal Planning with Reward-Guided Preference Optimization for Autonomous Driving

  Chenglin Chen, Lujia Wang, Xinhu Zheng, Jun Ma, Haoang Li · 1. Oktober 2026

  Safe and efficient trajectory planning is essential in autonomous driving. However, existing end-to-end approaches often fall short in both computational efficiency and safety guarantees. Methods based on imitation learning suffer from causal confusion, while rule-based scoring approaches often incu…

• CoVLM-Bench: A Real-World Benchmark for Cooperative Driving Question Answering and Planning

  Kang Yang, Shuai Liu, Hang Li, Yance Fang, Deying Li, Yongcai Wang · 30. September 2026

  Vision-language models (VLMs) have made substantial progress in autonomous driving, but their success has primarily been studied in ego-centric scenes. Infrastructure-side observations provide views beyond the ego vehicle's field of view, yet conventional cooperative-driving systems typically transf…

• doPlan: A Variable-Horizon Dataset for Multi-Stage Language-Conditioned Planning in Autonomous Driving

  Parthib Roy, Yash Tandon, Marcus Blennemann, Giovanni Tapia Lopez, Angel Martinez-Sanchez, Mohan M. Trivedi, Ross Greer · 30. September 2026

  Autonomous vehicles interacting with passengers through natural language must reason beyond immediate commands. Passenger intent may span multiple stages of behavior, depend on future events, refer to surrounding agents or landmarks, and remain relevant as driving conditions evolve. Existing languag…

• ExceptionDrive: A Planning-Oriented Counterfactual Corner-Case Benchmark for Autonomous Driving

  Ziyi Luo, Zhe Sun, Yehao Lu, Lei Zhou, Lisheng Wu, Xuewei Li, Zequn Qin, Xi Li · 30. September 2026

  Average performance on routine driving benchmarks does not establish planner reliability under rare, safety-critical hazards. We proposed ExceptionDrive, a counterfactual planning benchmark that uses VLM-assisted screening, localized multi-view editing, and quality auditing to insert hazards into re…

• Brain-SAD: A Brain-Inspired Safe Autonomous Driving Control Framework with Dynamic Fear-Oriented Constraint on Dual-Policy

  Huan Rong, Chao Yin, Anouar Imel, Yijie Xia, Tinghuai Ma · 30. September 2026

  Constrained Reinforcement Learning has recently gained increasing attention in the field of Safe Autonomous Driving, where the general mechanism is to maximize the expected reward while keeping the overall action risk bounded. In this way, the safety issues arising in AD can be mitigated through con…

• Learning from Shared-Control Overrides: Context-Driven Acceleration Profile Prediction for Personalized Overtaking

  Ruizheng Xu (Heudiasyc), Lounis Adouane (Heudiasyc), Javier Iba\~nez-Guzm\'an, Cl\'ement Zinoune · 30. September 2026

  Adaptive Cruise Control (ACC) systems are typically calibrated for an average driver, often resulting in a mismatch between vehicle behavior and individual expectations during time-critical maneuvers such as highway overtaking. When the ACC is perceived as too conservative and inconsistent, drivers …

• AD-E2E-JEPA: A Joint-Embedding Predictive Architecture For End-to-End Autonomous Driving

  Haoran Zhu, Wancong Zhang, Yann LeCun, Anna Choromanska · 29. September 2026

  Autonomous driving requires \textit{world models} that can understand the physical world, reason and plan, and operate safely. In this paper, we first systematically evaluate existing action-conditioned joint-embedding predictive architecture (JEPA) world models, including LeWM, DINO-WM, and JEPA-WM…

• VehDyn: A Driving World Model Benchmark for Vehicle Dynamics

  Tianyi Wang, Wangsheng Du, Jiazhou Chen, Tianyi Zeng, Xiangyu Li, Jiseop Byeon, Yujin Wang, Yiming Xu, Yangyang Wang, Bingzhao Gao, Sikai Chen, Zhaomiao Guo, Junfeng Jiao, Christian Claudel, Alexandre Bayen · 29. September 2026

  Video world models are emerging as data engines, action planners, and generative simulators for autonomous driving, but existing benchmarks primarily assess visual fidelity and coarse physical plausibility, providing limited evidence on whether generated driving futures obey realistic vehicle kinema…

• TriO: Tri-Modal Unsupervised Occupancy World Model for Anything Perception

  Quinlan Sykora, Sourav Biswas, Christopher Diehl, Andrew Cunningham, Thomas Gilles, Raquel Urtasun · 29. September 2026

  We present TriO, a multi-modal unsupervised world model that predicts 4D occupancy, obstacle segmentation, flow and LiDAR. In contrast to prior work, TriO utilizes three distinct sensor modalities (camera, LiDAR, and RADAR) as both inputs and sources of self-supervision, eliminating the need for add…

• DriveHierarchy: A Benchmark for Diagnosing VLM Driving Capabilities from Open-Loop Understanding to Closed-Loop Execution

  Chengkai Xu, Jiaqi Liu, Yicheng Guo, Peng Hang, Jian Sun · 29. September 2026

  Evaluating VLM-based autonomous driving remains difficult because driving competence is composite, where a capable system must ground traffic participants and hazards, integrate context across views and time, reason about future evolution, and act appropriately under closed-loop interaction. Existin…

• STRIDE: Automated Evaluation of Text-to-Trajectory Alignment across Diverse Contexts

  Wanchun Ni, Tao Qi, Leonel Aguilar, Jiugeng Sun, Marlene Wagner, Verena Zimmermann, Mennatallah El-Assady · 29. September 2026

  Language-conditioned trajectory generation is here, but its evaluation has not kept pace. Existing pedestrian trajectory metrics compare trajectories with real-world human data. This does not scale to text-to-trajectory generation across diverse contexts, as collecting human trajectories for every s…

• RECAST: From Log Replay to Closed-Loop Driving Simulation with View-Complete Actors

  Zijun Zhao, Liewen Liao, Kang Shen, Songan Zhang, Ming Yang · 28. September 2026

  Closed-loop driving simulation requires rendered observations to remain reliable as the ego vehicle and surrounding actors move beyond their recorded trajectories, exposing views absent from the source log. Existing data-driven simulators reconstruct dynamic actors from sparse observations, which ca…

• WALT: Learning World-Model-Aligned Latent Trajectories for Autonomous Driving

  Mingkai Jia, Jiaxin Guo, Zhijian Shu, Jiawei Xu, Mingxiao Li, Jintao Cheng, Ping Tan, Wei Yin · 28. September 2026

  Driving world models learn rich predictive representations of the surrounding environment from visual observations, yet accurate visual prediction does not necessarily translate into effective trajectory planning. We argue that a key bottleneck lies in the mismatch between visual world states and ra…

• Guiding End-to-End Driving Models with Endpoint-Constrained Trajectory Optimization

  Brayden Zhang, Mahsa Golchoubian, Igor Gilitschenski, Boris Ivanovic, Kashyap Chitta · 28. September 2026

  End-to-end driving policies are commonly trained through open-loop behavior cloning, yet they must ultimately operate in closed-loop when deployed on a vehicle, creating a fundamental mismatch between training and execution. Beyond the commonly studied effects of covariate shift and causal confusion…

• Evaluation Is All You Need for Multi-Modal Autonomous Driving

  Zeyu He, Shiqi Liu, Ke Chen, Yun Yan, Jinzi Wu, Dianqiao Lei, Sirui Wang, ShuRui Peng, Tao Chen, Zhuo Huang, Yu Wu, Yadong Shao, Zhichao Li, Ke Sun, Yang Guan, Keqiang Li, Shengbo Eben Li · 28. September 2026

  Multi-modal planning is promising for autonomous driving by representing multiple plausible behaviors in ambiguous and long-tail scenarios. Existing methods mainly focus on improving trajectory multi-modality, enhancing trajectory representations, or reshaping the candidate distribution. Nevertheles…

• TrafficImag: A Benchmark for Counterfactual Roadside Traffic Video Generation

  Xiangyu Li, Tianyi Wang, Zhihao Dou, Christian Claudel, Zhaomiao Guo · 28. September 2026

  Existing roadside traffic datasets support perception, forecasting, and visual question answering, but they do not evaluate counterfactual video generation, in which a selected actor is modified and the generated future should remain consistent with road topology and unrelated traffic. We introduce …

• Auditing Latent-Space Monitors for Autonomous Driving

  Nikhil Kamalkumar Advani, Vishwajeet Shivaji Hogale, Saurav Kumar · 28. September 2026

  Runtime failure monitors can use a model's internal representations to anticipate failures. We audit this monitoring strategy across two autonomous-driving tasks: online vectorized map generation with LaneSegNet and end-to-end planning with VAD. We find that frame-level errors are predictable at inf…

• Safety-oriented pedestrian trajectory prediction at urban intersections using time-to-collision and crossing-zone context

  Erel Avineri, Yftach Gil, Yehudit Aperstein · 25. September 2026

  Accurate pedestrian trajectory prediction is important for proactive road-safety applications, particularly at urban intersections where pedestrian motion is shaped by both vehicle interactions and crossing context. This study presents a safety-oriented trajectory-prediction framework that combines …