用Transformer实现3D点云中物体的参数化检测，让机器人能理解物体可变属性。
PIRATR: Parametric Object Inference for Robotic Applications with Transformers in 3D Point Clouds
- 基于Transformer端到端检测，联合估计物体位姿与可变参数（如夹爪开合度）
- 在合成数据上训练，直接部署于真实户外激光雷达数据，检测mAP达0.919
- 模块化设计支持新物体类型快速扩展，适合工业机器人场景
我们提出PIRATR，一个面向机器人应用的端到端3D物体检测框架，用于点云数据。在PI3DETR基础上，该方法通过联合估计多类别6-DoF位姿和类别特定的参数化属性，简化了参数化3D物体检测流程，直接从受遮挡影响的点云中获取结果。该设定不仅实现几何定位，还能估计任务相关的物体属性（如夹爪开合度），其3D模型根据预设规则动态调整。架构采用模块化、类别特异性头设计，使新增物体类型无需重设计流水线。我们在自动化叉车平台上验证了PIRATR，针对三种结构与功能各异的类别：吊钩夹具、装载平台和托盘。模型完全在合成环境中训练，无需微调即可有效泛化至真实户外LiDAR扫描，检测mAP达到0.919。PIRATR建立了一种感知新范式——姿态感知的参数化感知，弥合了低层几何推理与可操作世界模型之间的差距，为可扩展、仿真训练的感知系统在动态机器人环境中的部署铺平道路。代码已开源：https://github.com/swingaxe/piratr。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。