Vega: Learning to Drive with Natural Language Instructions

• URL: http://arxiv.org/abs/2603.25741v2
• Date: Mon, 30 Mar 2026 09:45:53 GMT
• Title: Vega: Learning to Drive with Natural Language Instructions
• Abstract summary: We propose a unified Vision-Language-World-Action model, Vega, for instruction-based generation and planning.<n>We employ the autoregressive paradigm to process visual inputs (vision) and language instructions (language) and the diffusion paradigm to generate future predictions.<n>Our method achieves superior planning performance and exhibits strong instruction-following abilities.
• Score: 93.49357278917223
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-language-action models have reshaped autonomous driving to incorporate languages into the decision-making process. However, most existing pipelines only utilize the language modality for scene descriptions or reasoning and lack the flexibility to follow diverse user instructions for personalized driving. To address this, we first construct a large-scale driving dataset (InstructScene) containing around 100,000 scenes annotated with diverse driving instructions with the corresponding trajectories. We then propose a unified Vision-Language-World-Action model, Vega, for instruction-based generation and planning. We employ the autoregressive paradigm to process visual inputs (vision) and language instructions (language) and the diffusion paradigm to generate future predictions (world modeling) and trajectories (action). We perform joint attention to enable interactions between the modalities and use individual projection layers for different modalities for more capabilities. Extensive experiments demonstrate that our method not only achieves superior planning performance but also exhibits strong instruction-following abilities, paving the way for more intelligent and personalized driving systems.

Related papers

• Language-Instructed Vision Embeddings for Controllable and Generalizable Perception [21.164230220588873]
  Language-Instructed Vision Embeddings (LIVE) uses language as high-level guidance to produce task-centric embeddings.<n>LIVE reduces visual hallucinations, surpasses vision-language models with orders of magnitude more parameters on visual question answering.
  arXiv  Detail & Related papers  (2026-06-17T20:39:04Z)
• AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation [78.80536515102305]
  Vision-and-Language Navigation (VLN) requires an agent to ground language instructions to its own movement within a visual environment.<n>We propose AwareVLN, a novel framework that equips the navigation model with a self-aware reasoning mechanism.<n>Our approach features two key innovations: (1) a structural reasoning module that fosters spatial and task-oriented self-awareness, and (2) an automatic data engine with progress division for effective training.
  arXiv  Detail & Related papers  (2026-05-21T17:58:26Z)
• Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future [125.92052530850425]
  Vision-Language-Action (VLA) frameworks integrate perception with language-grounded decision making.<n>VLA frameworks offer a pathway toward more interpretable, generalizable, and human-aligned driving policies.<n>This work aims to establish a coherent foundation for advancing human-compatible autonomous driving systems.
  arXiv  Detail & Related papers  (2025-12-18T16:57:44Z)
• doScenes: An Autonomous Driving Dataset with Natural Language Instruction for Human Interaction and Vision-Language Navigation [0.0]
  doScenes is a novel dataset designed to facilitate research on human-vehicle instruction interactions.<n>DoScenes bridges the gap between instruction and driving response, enabling context-aware and adaptive planning.
  arXiv  Detail & Related papers  (2024-12-08T11:16:47Z)
• OccLLaMA: An Occupancy-Language-Action Generative World Model for Autonomous Driving [12.004183122121042]
  OccLLaMA is an occupancy-language-action generative world model. We build a unified multi-modal vocabulary for vision, language and action. OccLLaMA achieves competitive performance across multiple tasks.
  arXiv  Detail & Related papers  (2024-09-05T06:30:01Z)
• LangNav: Language as a Perceptual Representation for Navigation [63.90602960822604]
  We explore the use of language as a perceptual representation for vision-and-language navigation (VLN) Our approach uses off-the-shelf vision systems for image captioning and object detection to convert an agent's egocentric panoramic view at each time step into natural language descriptions.
  arXiv  Detail & Related papers  (2023-10-11T20:52:30Z)
• Learning to Model the World with Language [100.76069091703505]
  To interact with humans and act in the world, agents need to understand the range of language that people use and relate it to the visual world. Our key idea is that agents should interpret such diverse language as a signal that helps them predict the future. We instantiate this in Dynalang, an agent that learns a multimodal world model to predict future text and image representations.
  arXiv  Detail & Related papers  (2023-07-31T17:57:49Z)
• EC^2: Emergent Communication for Embodied Control [72.99894347257268]
  Embodied control requires agents to leverage multi-modal pre-training to quickly learn how to act in new environments. We propose Emergent Communication for Embodied Control (EC2), a novel scheme to pre-train video-language representations for few-shot embodied control. EC2 is shown to consistently outperform previous contrastive learning methods for both videos and texts as task inputs.
  arXiv  Detail & Related papers  (2023-04-19T06:36:02Z)
• Instruction-Following Agents with Multimodal Transformer [95.70039658112873]
  We propose a simple yet effective model for robots to solve instruction-following tasks in vision-based environments. Our method consists of a multimodal transformer that encodes visual observations and language instructions. We show that this unified transformer model outperforms all state-of-the-art pre-trained or trained-from-scratch methods in both single-task and multi-task settings.
  arXiv  Detail & Related papers  (2022-10-24T17:46:47Z)
• Language Model-Based Paired Variational Autoencoders for Robotic Language Learning [18.851256771007748]
  Similar to human infants, artificial agents can learn language while interacting with their environment. We present a neural model that bidirectionally binds robot actions and their language descriptions in a simple object manipulation scenario. Next, we introduce PVAE-BERT, which equips the model with a pretrained large-scale language model.
  arXiv  Detail & Related papers  (2022-01-17T10:05:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.