{
  "annotation_id": "6145f5bd-b525-4255-b15e-d42b43a98c2e",
  "date_created": "2026-02-17T05:53:15.633000Z",
  "date_modified": "2026-02-17T05:53:15.633000Z",
  "file_hash": "8a6775a34e9ea0ef1a410c74468e0445da36917428c8193a1d2610a281c801fd",
  "private": false,
  "record": {
    "abstract": "Constructing an accurate simulation model of real-world environments requires reliable estimation of physical parameters such as mass, geometry, friction, and contact surfaces. Traditional real-to-simulation (Real2Sim) pipelines rely on manual measurements or fixed, pre-programmed exploration routines, which limit their adaptability to varying tasks and user intents. This paper presents a Real2Sim framework that autonomously generates and executes Behavior Trees for task-specific physical interactions to acquire only the parameters required for a given simulation objective, without relying on pre-defined task templates or expert-designed exploration routines. Given a high-level user request, an incomplete simulation description, and an RGB observation of the scene, a vision-language model performs multi-modal reasoning to identify relevant objects, infer required physical parameters, and generate a structured Behavior Tree composed of elementary robotic actions. The resulting behavior is executed on a torque-controlled Franka Emika Panda, enabling compliant, contact-rich interactions for parameter estimation. The acquired measurements are used to automatically construct a physics-aware simulation. Experimental results on the real manipulator demonstrate estimation of object mass, surface height, and friction-related quantities across multiple scenarios, including occluded objects and incomplete prior models. The proposed approach enables interpretable, intent-driven, and autonomously Real2Sim pipelines, bridging high-level reasoning with physically-grounded robotic interaction.",
    "arxiv_id": "2601.08454",
    "authors": [
      "Alessandro Adami",
      "Sebastian Zudaire",
      "Ruggero Carli",
      "Pietro Falco"
    ],
    "categories": [
      "cs.RO"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "Real2Sim based on Active Perception with automatically VLM-generated Behavior Trees",
    "url": "https://arxiv.org/abs/2601.08454",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "69a9a0b6-bd15-4615-9eb3-8d7135fd5ce0",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}