面向安全驾驶感知的溯因自我视角事故视频理解

BADAS：利用真实世界行车记录仪数据的上下文感知碰撞预测

BADAS: Context Aware Collision Prediction Using Real-World Dashcam Data

BADAS利用真实行车记录仪数据，通过自车中心评估和V-JEPA2骨干网络，在多个基准上实现最先进的碰撞预测性能，并发布模型与数据以推动研究。

COOPERNAUT: End-to-End Driving with Cooperative Perception for Networked Vehicles

Optical sensors and learning algorithms for autonomous vehicles have dramatically advanced in the past few years. Nonetheless, the reliability of today's autonomous vehicles is hindered by the limited line-of-sight sensing capability and the brittleness of data-driven methods in handling extreme situations. With recent developments of telecommunication technologies, cooperative perception with vehicle-to-vehicle communications has become a promising paradigm to enhance autonomous driving in dangerous or emergency situations. We introduce COOPERNAUT, an end-to-end learning model that uses cross…

不存在的证据：当视觉失效时维持世界模型的跨模态溯因风险感知

Evidence of Absence: Cross-Modal Abductive Risk Perception to Sustain World Models When Vision Fails

该研究提出跨模态溯因风险感知方法，在视觉失效时通过声学线索维持世界模型，可提前1.7秒预警，虚警减少42%，校准良好，能在视觉退化下保持高危险感知度。

预训练视觉模型作为自动驾驶安全滤波器的感知骨干网络

Pre-Trained Vision Models as Perception Backbones for Safety Filters in Autonomous Driving

针对高维视觉自动驾驶场景下安全滤波器设计难度大的问题，本研究将冻结的预训练视觉模型作为感知骨干网络，结合三种黑箱动力学训练方法在DeepAccident数据集上实验，所得滤波器性能与使用真实状态的滤波器相当。

Early Lane Change Prediction for Automated Driving Systems Using Multi-Task Attention-based Convolutional Neural Networks

Lane change (LC) is one of the safety-critical manoeuvres in highway driving according to various road accident records. Thus, reliably predicting such manoeuvre in advance is critical for the safe and comfortable operation of automated driving systems. The majority of previous studies rely on detecting a manoeuvre that has been already started, rather than predicting the manoeuvre in advance. Furthermore, most of the previous works do not estimate the key timings of the manoeuvre (e.g., crossing time), which can actually yield more useful information for the decision making in the ego vehicle…

通过结合深度霍夫变换的语义线检测与分类提升监控摄像机视场质量

Enhancing Surveillance Camera FOV Quality via Semantic Line Detection and Classification with Deep Hough Transform

针对摄像机视场质量缺乏自动评估的问题，提出结合深度Hough变换的语义线检测与分类方法，在EgoCart上取得F1 0.729和83.8%分类准确率。

AI-Based Framework for Understanding Car Following Behaviors of Drivers in A Naturalistic Driving Environment

The most common type of accident on the road is a rear-end crash. These crashes have a significant negative impact on traffic flow and are frequently fatal. To gain a more practical understanding of these scenarios, it is necessary to accurately model car following behaviors that result in rear-end crashes. Numerous studies have been carried out to model drivers' car-following behaviors; however, the majority of these studies have relied on simulated data, which may not accurately represent real-world incidents. Furthermore, most studies are restricted to modeling the ego vehicle's acceleratio…

危险意识交通场景图生成

Hazard-Aware Traffic Scene Graph Generation

本文提出交通场景图生成任务，通过结合交通事故数据和深度线索，提升自动驾驶车辆对危险因素的感知与推理能力。

基于法律多智能体推理的可解释交通责任分析

Interpretable Traffic Responsibility from Dashcam Video via Legal Multi Agent Reasoning

本文提出C-TRAIL多模态数据集，结合视频与文本描述，通过两阶段框架实现交通责任判定，优于现有方法并提供透明法律推理过程。

DROID: Driver-centric Risk Object Identification

Identification of high-risk driving situations is generally approached through collision risk estimation or accident pattern recognition. In this work, we approach the problem from the perspective of subjective risk. We operationalize subjective risk assessment by predicting driver behavior changes and identifying the cause of changes. To this end, we introduce a new task called driver-centric risk object identification (DROID), which uses egocentric video to identify object(s) influencing a driver's behavior, given only the driver's response as the supervision signal. We formulate the task as…