Related papers: Vega: Learning to Drive with Natural Language Inst…
Visual Language Models (VLMs), with powerful multimodal reasoning capabilities, are gradually integrated into autonomous driving by several automobile manufacturers to enhance planning capability in challenging environments. However, the…
Scene understanding is essential for enhancing driver safety, generating human-centric explanations for Automated Vehicle (AV) decisions, and leveraging Artificial Intelligence (AI) for retrospective driving video analysis. This study…
The emergence of multi-modal foundation models has markedly transformed the technology for autonomous driving, shifting away from conventional and mostly hand-crafted design choices towards unified, foundation-model-based approaches,…
Current Vision-Language-Action (VLA) paradigms in end-to-end autonomous driving rely on offline training from static datasets, leaving them vulnerable to distribution shift. Recent post-training methods use takeover data to mitigate this by…
End-to-end autonomous driving models based on Vision-Language-Action (VLA) architectures have shown promising results by learning driving policies through behavior cloning on expert demonstrations. However, imitation learning inherently…
Exploring open-world situations in an end-to-end manner is a promising yet challenging task due to the need for strong generalization capabilities. In particular, end-to-end autonomous driving in unstructured outdoor environments often…
Humans learn language by listening, speaking, writing, reading, and also, via interaction with the multimodal real world. Existing language pre-training frameworks show the effectiveness of text-only self-supervision while we explore the…
Recent reasoning-augmented Vision-Language-Action (VLA) models have improved the interpretability of end-to-end autonomous driving by generating intermediate reasoning traces. Yet these models primarily describe what they perceive and…
This work highlights that video world modeling, alongside vision-language pre-training, establishes a fresh and independent foundation for robot learning. Intuitively, video world models provide the ability to imagine the near future by…
Vision-and-Language Navigation (VLN) tasks agents with locating specific objects in unseen environments using natural language instructions and visual cues. Many existing VLN approaches typically follow an 'observe-and-reason' schema, that…
Large vision-language models (VLMs) have garnered increasing interest in autonomous driving areas, due to their advanced capabilities in complex reasoning tasks essential for highly autonomous vehicle behavior. Despite their potential,…
Prediction, decision-making, and motion planning are essential for autonomous driving. In most contemporary works, they are considered as individual modules or combined into a multi-task learning paradigm with a shared backbone but separate…
Human-level driving is an ultimate goal of autonomous driving. Conventional approaches formulate autonomous driving as a perception-prediction-planning framework, yet their systems do not capitalize on the inherent reasoning ability and…
The effective communication of procedural knowledge remains a significant challenge in natural language processing (NLP), as purely textual instructions often fail to convey complex physical actions and spatial relationships. We address…
Autonomous driving necessitates the ability to reason about future interactions between traffic agents and to make informed evaluations for planning. This paper introduces the \textit{Gen-Drive} framework, which shifts from the traditional…
In modern urban environments, camera networks generate massive amounts of operational footage -- reaching petabytes each day -- making scalable video analytics essential for efficient processing. Many existing approaches adopt an SQL-based…
Trajectory planning is a fundamental yet challenging component of autonomous driving. End-to-end planners frequently falter under adverse weather, unpredictable human behavior, or complex road layouts, primarily because they lack strong…
Visual navigation in unknown environments based solely on natural language descriptions is a key capability for intelligent robots. In this work, we propose a navigation framework built upon off-the-shelf Visual Language Models (VLMs),…
While many visualization specification languages are user-friendly, they tend to have one critical drawback: they are designed for small data on the client-side and, as a result, perform poorly at scale. We propose a system that takes…
Learning to navigate in a visual environment following natural-language instructions is a challenging task, because the multimodal inputs to the agent are highly variable, and the training data on a new task is often limited. In this paper,…