D2-V2X: Depth-Driven Cooperative V2X Reasoning for Autonomous Driving

• URL: http://arxiv.org/abs/2605.24098v1
• Date: Fri, 22 May 2026 18:05:10 GMT
• Title: D2-V2X: Depth-Driven Cooperative V2X Reasoning for Autonomous Driving
• Abstract summary: We introduce D2-V2X, a spatially-aware Question-Rationale-Answer (QRA) benchmark featuring 8,500 triplets.<n>By enforcing natural language recall rationales prior to structured outputs, our model is forced to explicitly articulate spatial relations.<n>While the model achieves a functional decision-making F1-score of 53.5, we identify 3D-to-2D projection as a fundamental bottleneck in current VLM architectures.
• Score: 10.860896159477264
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Single-vehicle Vision-Language Models (VLMs) are fundamentally constrained by sensor occlusions. While Vehicle-to-Everything (V2X) systems mitigate this, current benchmarks lack the cooperative reasoning required for resolving ambiguities in complex environments. We introduce D2-V2X, a spatially-aware Question-Rationale-Answer (QRA) benchmark featuring 8,500 triplets derived from multimodal vehicle and infrastructure sensors. We additionally establish a baseline that aligns 3D LiDAR features with the VLM's latent space. By enforcing natural language Chain-of-Thought rationales prior to structured JSON outputs, our model is forced to explicitly articulate spatial relations. Our experiments demonstrate that grounding VLMs in cooperative LiDAR achieves 24.4% recall in identifying occluded hazards compared to near-zero in zero-shot models and reduces spatial estimation error for visible objects by 77% compared to the zero-shot baseline. While the model achieves a functional decision-making F1-score of 53.5, we identify 3D-to-2D projection as a fundamental bottleneck in current VLM architectures, establishing a new baseline for future innovation. Data, code, and trained models available at https://github.com/KevinRichard1/D2-V2X

Related papers

• RADAR: Benchmarking Vision-Language-Action Generalization via Real-World Dynamics, Spatial-Physical Intelligence, and Autonomous Evaluation [76.22852262683746]
  We introduce RADAR, a benchmark designed to systematically evaluate VLA generalization under realistic conditions.<n>We apply RADAR to audit multiple state-of-the-art VLA models and uncover severe fragility beneath their apparent competence.
  arXiv  Detail & Related papers  (2026-02-11T16:08:30Z)
• DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning [94.62097655403683]
  We propose DrivePI, a novel spatial-aware 4D MLLM that serves as a unified Vision-Language-Action framework.<n>Our method jointly performs spatial understanding, 3D perception, prediction (i.e., occupancy flow), and planning (i.e., action outputs) in parallel.<n>With only a 0.5B Qwen2.5 model as MLLM backbone, DrivePI as a single unified model matches or exceeds both existing VLA models and specialized VA models.
  arXiv  Detail & Related papers  (2025-12-14T18:45:54Z)
• Beyond Flatlands: Unlocking Spatial Intelligence by Decoupling 3D Reasoning from Numerical Regression [12.590536117486257]
  Existing Vision Language Models (VLMs) struggle to comprehend real-world 3D spatial intelligence.<n> GEODE augments main VLM with two specialized, plug-and-play modules.<n>The synergy of these modules allows our 1.5B parameter model to function as a high-level semantic dispatcher.
  arXiv  Detail & Related papers  (2025-11-14T12:42:07Z)
• SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities [59.39858959066982]
  understanding and reasoning about spatial relationships is a fundamental capability for Visual Question Answering (VQA) and robotics. We develop an automatic 3D spatial VQA data generation framework that scales up to 2 billion VQA examples on 10 million real-world images. By training a VLM on such data, we significantly enhance its ability on both qualitative and quantitative spatial VQA.
  arXiv  Detail & Related papers  (2024-01-22T18:01:01Z)
• V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perception [49.7212681947463]
  Vehicle-to-Vehicle (V2V) cooperative perception system has great potential to revolutionize the autonomous driving industry. We present V2V4Real, the first large-scale real-world multi-modal dataset for V2V perception. Our dataset covers a driving area of 410 km, comprising 20K LiDAR frames, 40K RGB frames, 240K annotated 3D bounding boxes for 5 classes, and HDMaps.
  arXiv  Detail & Related papers  (2023-03-14T02:49:20Z)
• LiDAR-based 4D Panoptic Segmentation via Dynamic Shifting Network [56.71765153629892]
  We propose the Dynamic Shifting Network (DS-Net), which serves as an effective panoptic segmentation framework in the point cloud realm. Our proposed DS-Net achieves superior accuracies over current state-of-the-art methods in both tasks. We extend DS-Net to 4D panoptic LiDAR segmentation by the temporally unified instance clustering on aligned LiDAR frames.
  arXiv  Detail & Related papers  (2022-03-14T15:25:42Z)
• PillarGrid: Deep Learning-based Cooperative Perception for 3D Object Detection from Onboard-Roadside LiDAR [15.195933965761645]
  We propose textitPillarGrid, a novel cooperative perception method fusing information from multiple 3D LiDARs. PillarGrid consists of four main phases: 1) cooperative preprocessing of point clouds, 2) pillar-wise voxelization and feature extraction, 3) grid-wise deep fusion of features from multiple sensors, and 4) convolutional neural network (CNN)-based augmented 3D object detection. Extensive experimentation shows that PillarGrid outperforms the SOTA single-LiDAR-based 3D object detection methods with respect to both accuracy and range by a large margin.
  arXiv  Detail & Related papers  (2022-03-12T02:28:41Z)
• LiDAR-based Panoptic Segmentation via Dynamic Shifting Network [56.71765153629892]
  LiDAR-based panoptic segmentation aims to parse both objects and scenes in a unified manner. We propose the Dynamic Shifting Network (DS-Net), which serves as an effective panoptic segmentation framework in the point cloud realm. Our proposed DS-Net achieves superior accuracies over current state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-11-24T08:44:46Z)

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.