相关论文: Poutine: Vision-Language-Trajectory Pre-Training a…

Policy steering is an emerging way to adapt robot behaviors at deployment-time: a learned verifier analyzes low-level action samples proposed by a pre-trained policy (e.g., diffusion policy) and selects only those aligned with the task.…

Motivated by the emergent reasoning capabilities of Vision Language Models (VLMs) and their potential to improve the comprehensibility of autonomous driving systems, this paper introduces a closed-loop autonomous driving controller called…

This paper introduces an innovative application of foundation models, enabling Unmanned Ground Vehicles (UGVs) equipped with an RGB-D camera to navigate to designated destinations based on human language instructions. Unlike learning-based…

Vision-Language-Action (VLA) driving augments end-to-end (E2E) planning with language-enabled backbones, yet it remains unclear what changes beyond the usual accuracy--cost trade-off. We revisit this question with 3--RQ analysis in…

Ensuring safety remains a key challenge for autonomous vehicles (AVs), especially in rare and complex scenarios. One critical but understudied aspect is the \textbf{potential risk} situations, where the risk is \textbf{not yet observable}…

Strategic planning is critical for multi-step reasoning, yet compact Large Language Models (LLMs) often lack the capacity to formulate global strategies, leading to error propagation in long-horizon tasks. Our analysis reveals that LLMs…

Unmanned Aerial Vehicle (UAV) Vision-and-Language Navigation (VLN) is vital for applications such as disaster response, logistics delivery, and urban inspection. However, existing methods often struggle with insufficient multimodal fusion,…

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…

Recently, the remarkable advance of the Large Language Model (LLM) has inspired researchers to transfer its extraordinary reasoning capability to both vision and language data. However, the prevailing approaches primarily regard the visual…

Current autonomous driving vehicles rely mainly on their individual sensors to understand surrounding scenes and plan for future trajectories, which can be unreliable when the sensors are malfunctioning or occluded. To address this problem,…

The field of vision-language models (VLMs), which take images and texts as inputs and output texts, is rapidly evolving and has yet to reach consensus on several key aspects of the development pipeline, including data, architecture, and…

Solving complex long-horizon robotic manipulation problems requires sophisticated high-level planning capabilities, the ability to reason about the physical world, and reactively choose appropriate motor skills. Vision-language models…

Improving embodied reasoning in multimodal-large-language models (MLLMs) is essential for building vision-language-action models (VLAs) on top of them to readily translate multimodal understanding into low-level actions. Accordingly, recent…

Outdoor Vision-and-Language Navigation (VLN) requires an agent to navigate through realistic 3D outdoor environments based on natural language instructions. The performance of existing VLN methods is limited by insufficient diversity in…

This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought (CoT) prompting and reinforcement learning. We begin by evaluating the impact of different prompting strategies and find…

Multimodal large language models (MLLMs) have emerged as a prominent area of interest within the research community, given their proficiency in handling and reasoning with non-textual data, including images and videos. This study seeks to…

In this paper, we propose a novel approach for solving the Visual Question Answering (VQA) task in autonomous driving by integrating Vision-Language Models (VLMs) with continual learning. In autonomous driving, VQA plays a vital role in…

Vision-and-Language Navigation (VLN) requires agents to navigate photo-realistic environments following natural language instructions. Current methods predominantly rely on imitation learning, which suffers from limited generalization and…

Autonomous cars need geometric accuracy and semantic understanding to navigate complex environments, yet most stacks handle them separately. We present XYZ-Drive, a single vision-language model that reads a front-camera frame, a 25m…

Large Language Models (LLMs) and strong vision models have enabled rapid research and development in the field of Vision-Language-Action models that enable robotic control. The main objective of these methods is to develop a generalist…