arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.05557cs.CVcs.RO
收藏

PIRATR:基于变换器的参数化物体推理用于机器人应用的3D点云

PIRATR: Parametric Object Inference for Robotic Applications with Transformers in 3D Point Clouds

AIT Austrian Institute of Technology Center for Vision, Automation & Control(奥地利技术研究院视觉、自动化与控制中心)

Michael Schwingshackl, Fabio F. Oberweger, Mario Niedermeyer, Huemer Johannes, Markus Murschitz

AI总结:

PIRATR通过端到端3D点云检测框架,结合变换器实现参数化物体的6自由度姿态和属性估计,适用于机器人应用。

摘要:

我们提出了PIRATR,一种用于点云中机器人使用案例的端到端3D物体检测框架。在扩展PI3DETR的基础上,我们的方法通过从受遮挡的点云数据中联合估计多类6自由度姿态和类特定参数属性,简化了参数化3D物体检测。这种 formulation 不仅实现了几何定位,还能够估计任务相关的参数属性,如机械手的开合,其中3D模型根据简单的预定义规则进行调整。该架构采用模块化、类特定的头部,使其易于扩展到新的物体类型而无需重新设计流程。我们在自动叉车平台上验证了PIRATR,重点关注三个结构和功能上多样的类别:起重机夹具、装载平台和托盘。完全在合成环境中训练,PIRATR能够有效泛化到真实的户外激光雷达扫描,无需额外微调即可达到0.919的检测mAP。PIRATR建立了一种姿态感知、参数化的感知新范式。这填补了低级几何推理与可操作世界模型之间的差距,为可扩展、基于模拟训练的感知系统铺平了道路,这些系统可以部署在动态机器人环境中。代码可在https://github.com/swingaxe/piratr上获取。

英文摘要:

We present PIRATR, an end-to-end 3D object detection framework for robotic use cases in point clouds. Extending PI3DETR, our method streamlines parametric 3D object detection by jointly estimating multi-class 6-DoF poses and class-specific parametric attributes directly from occlusion-affected point cloud data. This formulation enables not only geometric localization but also the estimation of task-relevant properties for parametric objects, such as a gripper's opening, where the 3D model is adjusted according to simple, predefined rules. The architecture employs modular, class-specific heads, making it straightforward to extend to novel object types without re-designing the pipeline. We validate PIRATR on an automated forklift platform, focusing on three structurally and functionally diverse categories: crane grippers, loading platforms, and pallets. Trained entirely in a synthetic environment, PIRATR generalizes effectively to real outdoor LiDAR scans, achieving a detection mAP of 0.919 without additional fine-tuning. PIRATR establishes a new paradigm of pose-aware, parameterized perception. This bridges the gap between low-level geometric reasoning and actionable world models, paving the way for scalable, simulation-trained perception systems that can be deployed in dynamic robotic environments. Code available at https://github.com/swingaxe/piratr.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑