BEVWorld: A Multimodal World Model for Autonomous Driving via Unified BEV Latent Space

• URL: http://arxiv.org/abs/2407.05679v2
• Date: Thu, 18 Jul 2024 08:33:43 GMT
• Title: BEVWorld: A Multimodal World Model for Autonomous Driving via Unified BEV Latent Space
• Authors: Yumeng Zhang, Shi Gong, Kaixin Xiong, Xiaoqing Ye, Xiao Tan, Fan Wang, Jizhou Huang, Hua Wu, Haifeng Wang,
• Abstract summary: We present BEVWorld, a novel approach that tokenizes multimodal sensor inputs into a unified and compact Bird's Eye View latent space for environment modeling. Experiments demonstrate the effectiveness of BEVWorld in autonomous driving tasks, showcasing its capability in generating future scenes and benefiting downstream tasks such as perception and motion prediction.
• Score: 57.68134574076005
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: World models are receiving increasing attention in autonomous driving for their ability to predict potential future scenarios. In this paper, we present BEVWorld, a novel approach that tokenizes multimodal sensor inputs into a unified and compact Bird's Eye View (BEV) latent space for environment modeling. The world model consists of two parts: the multi-modal tokenizer and the latent BEV sequence diffusion model. The multi-modal tokenizer first encodes multi-modality information and the decoder is able to reconstruct the latent BEV tokens into LiDAR and image observations by ray-casting rendering in a self-supervised manner. Then the latent BEV sequence diffusion model predicts future scenarios given action tokens as conditions. Experiments demonstrate the effectiveness of BEVWorld in autonomous driving tasks, showcasing its capability in generating future scenes and benefiting downstream tasks such as perception and motion prediction. Code will be available at https://github.com/zympsyche/BevWorld.

Related papers

• SimBEV: A Synthetic Multi-Task Multi-Sensor Driving Data Generation Tool and Dataset [101.51012770913627]
  Bird's-eye view (BEV) perception for autonomous driving has garnered significant attention in recent years. We introduce SimBEV, a synthetic data generation tool that incorporates information from multiple sources to capture accurate BEV ground truth data. We use SimBEV to create the SimBEV dataset, a large collection of annotated perception data from diverse driving scenarios.
  arXiv  Detail & Related papers  (2025-02-04T00:00:06Z)
• EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation [55.26713167507132]
  We introduce a generative robotics foundation model that constructs and interprets embodied spaces. EnerVerse employs an autoregressive video diffusion framework to predict future embodied spaces from instructions, enhanced by a sparse context memory for long-term reasoning. We present EnerVerse-D, a data engine pipeline combining the generative model with 4D Gaussian Splatting, forming a self-reinforcing data loop to reduce the sim-to-real gap.
  arXiv  Detail & Related papers  (2025-01-03T17:00:33Z)
• DrivingGPT: Unifying Driving World Modeling and Planning with Multi-modal Autoregressive Transformers [61.92571851411509]
  We introduce a multimodal driving language based on interleaved image and action tokens, and develop DrivingGPT to learn joint world modeling and planning. Our DrivingGPT demonstrates strong performance in both action-conditioned video generation and end-to-end planning, outperforming strong baselines on large-scale nuPlan and NAVSIM benchmarks.
  arXiv  Detail & Related papers  (2024-12-24T18:59:37Z)
• Multimodal Latent Language Modeling with Next-Token Diffusion [111.93906046452125]
  Multimodal generative models require a unified approach to handle both discrete data (e.g., text and code) and continuous data (e.g., image, audio, video) We propose Latent Language Modeling (LatentLM), which seamlessly integrates continuous and discrete data using causal Transformers.
  arXiv  Detail & Related papers  (2024-12-11T18:57:32Z)
• CASPFormer: Trajectory Prediction from BEV Images with Deformable Attention [4.9349065371630045]
  We propose Context Aware Scene Prediction Transformer (CASPFormer), which can perform multi-modal motion prediction from spatialized Bird-Eye-View (BEV) images. Our system can be integrated with any upstream perception module that is capable of generating BEV images. We evaluate our model on the nuScenes dataset and show that it reaches state-of-the-art across multiple metrics.
  arXiv  Detail & Related papers  (2024-09-26T12:37:22Z)
• Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving [15.100104512786107]
  Drive-OccWorld adapts a visioncentric- 4D forecasting world model to end-to-end planning for autonomous driving. We propose injecting flexible action conditions, such as velocity, steering angle, trajectory, and commands, into the world model to enable controllable generation. Our method can generate plausible and controllable 4D occupancy, paving the way for advancements in driving world generation and end-to-end planning.
  arXiv  Detail & Related papers  (2024-08-26T11:53:09Z)
• PowerBEV: A Powerful Yet Lightweight Framework for Instance Prediction in Bird's-Eye View [14.113805629254191]
  Bird's-eye view (BEV) representations are commonplace in perception for autonomous driving. Existing approaches for BEV instance prediction rely on a multi-task auto-regressive coupled with post-processing to predict future instances. We propose an efficient novel end-to-end framework named POWERBEV, which differs in several design choices aimed at reducing the inherent redundancy in previous methods.
  arXiv  Detail & Related papers  (2023-06-19T08:11:05Z)
• DiffBEV: Conditional Diffusion Model for Bird's Eye View Perception [14.968177102647783]
  We propose an end-to-end framework, named DiffBEV, to exploit the potential of diffusion model to generate a more comprehensive BEV representation. In practice, we design three types of conditions to guide the training of the diffusion model which denoises the coarse samples and refines the semantic feature. We show that DiffBEV achieves a 25.9% mIoU on the nuScenes dataset, which is 6.2% higher than the best-performing existing approach.
  arXiv  Detail & Related papers  (2023-03-15T02:42:48Z)
• BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving [92.05963633802979]
  We present BEVerse, a unified framework for 3D perception and prediction based on multi-camera systems. We show that the multi-task BEVerse outperforms single-task methods on 3D object detection, semantic map construction, and motion prediction.
  arXiv  Detail & Related papers  (2022-05-19T17:55:35Z)

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.