[
    {
        "id": "osp-17769",
        "type": "article-journal",
        "title": "Explicit Geometric Chain-of-Thought for Vision-Language-Action in Autonomous Driving",
        "author": [
            {
                "family": "Gui",
                "given": "Xingtai"
            },
            {
                "family": "Zhou",
                "given": "Yucheng"
            },
            {
                "family": "Guo",
                "given": "Dongqian"
            },
            {
                "family": "Gong",
                "given": "Jiahao"
            },
            {
                "family": "Tan",
                "given": "Feiyang"
            },
            {
                "family": "Shen",
                "given": "Jianbing"
            }
        ],
        "URL": "https://omanscience.com/en/articles/explicit-geometric-chain-of-thought-for-vision-language-action-in-autonomous-driving",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Vision-language-action~(VLA) models have emerged as a promising paradigm for autonomous driving. However, existing VLA models still suffer from a fundamental mismatch: driving actions require precise 3D geometric cues, while visual-language understanding and reasoning are largely conducted in a 2D semantic space. In this paper, we propose GeoCoTDrive, an explicit geometric chain-of-thought framework that grounds geometry in a planning-oriented manner. GeoCoTDrive follows a think with 2D first, drive with dedicated 3D priors paradigm. It first grounds 2D regions corresponding to decision-critical cues, and then retrieves localized 3D priors by sampling features from a geometric foundation model within the grounded regions. These localized geometric features are interleaved into the autoregressive context to support the trajectory generation. To supervise this process, we introduce planning-relevant grounding, a new region-level grounding task that focuses on local spatial cues directly affecting ego planning decisions, and construct the PlanningGrounding dataset to endow VLAs with planning-oriented grounding capability. Experiments across multiple end-to-end autonomous driving benchmarks show that GeoCoTDrive consistently improves safety-critical planning performance, demonstrating the effectiveness of the explicit geometric chain-of-thought process for VLA-based planning."
    }
]