Related papers: AccidentGPT: Accident Analysis and Prevention from…
We present DriveGPT, a scalable behavior model for autonomous driving. We model driving as a sequential decision-making task, and learn a transformer model to predict future agent states as tokens in an autoregressive fashion. We scale up…
With the emergence of large language models (LLMs) and vision foundation models, how to combine the intelligence and capacity of these open-sourced or API-available models to achieve open-world visual perception remains an open question. In…
Autonomous vehicles (AVs) are poised to redefine transportation by enhancing road safety, minimizing human error, and optimizing traffic efficiency. The success of AVs depends on their ability to interpret complex, dynamic environments…
Predicting vehicle trajectories is crucial for ensuring automated vehicle operation efficiency and safety, particularly on congested multi-lane highways. In such dynamic environments, a vehicle's motion is determined by its historical…
Road accidents significantly threaten public safety and require in-depth analysis for effective prevention and mitigation strategies. This paper focuses on predicting accidents through the examination of a comprehensive traffic dataset…
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in Traffic Accident Detection (TAD) and Traffic Accident Understanding (TAU). However, existing studies mainly focus on describing and interpreting accident videos,…
The integration of Autonomous Vehicles (AVs) into existing human-driven traffic systems poses considerable challenges, especially within environments where human and machine interactions are frequent and complex, such as at unsignalized…
This paper presents a novel dataset for traffic accidents analysis. Our goal is to resolve the lack of public data for research about automatic spatio-temporal annotations for traffic safety in the roads. Through the analysis of the…
To maximize safety and driving comfort, autonomous driving systems can benefit from implementing foresighted action choices that take different potential scenario developments into account. While artificial scene prediction methods are…
Synthesis of diverse driving scenes serves as a crucial data augmentation technique for validating the robustness and generalizability of autonomous driving systems. Current methods aggregate high-definition (HD) maps and 3D bounding boxes…
Predicting the future trajectories of multiple interacting agents in a scene has become an increasingly important problem for many different applications ranging from control of autonomous vehicles and social robots to security and…
Heterogeneous graph learning aims to capture complex relationships and diverse relational semantics among entities in a heterogeneous graph to obtain meaningful representations for nodes and edges. Recent advancements in heterogeneous graph…
We present a novel framework for modeling traffic congestion events over road networks. Using multi-modal data by combining count data from traffic sensors with police reports that report traffic incidents, we aim to capture two types of…
Accurate prediction of road accidents remains challenging due to intertwined spatial, temporal, and contextual factors in urban traffic. We propose MSGAT-GRU, a multi-scale graph attention and recurrent model that jointly captures localized…
Accident prediction and timely preventive actions improve road safety by reducing the risk of injury to road users and minimizing property damage. Hence, they are critical components of advanced driver assistance systems (ADAS) and…
In a given scenario, simultaneously and accurately predicting every possible interaction of traffic participants is an important capability for autonomous vehicles. The majority of current researches focused on the prediction of an single…
The pursuit of autonomous driving technology hinges on the sophisticated integration of perception, decision-making, and control systems. Traditional approaches, both data-driven and rule-based, have been hindered by their inability to…
Vehicle-to-Everything (V2X) cooperation is reshaping traffic safety from an ego-centric sensing problem into one of collective intelligence. This survey structures recent progress within a unified Sensor-Perception-Decision (SPD) framework…
Due to the current developments towards autonomous driving and vehicle active safety, there is an increasing necessity for algorithms that are able to perform complex criticality predictions in real-time. Being able to process multi-object…
In high-conflict mixed-traffic scenarios involving human-driven and autonomous vehicles, most existing autonomous driving systems default to overly conservative behaviors, lack proactive interaction, and consequently suffer from limited…