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

2026-02-05 · Michael Schwingshackl, Fabio F. Oberweger, Mario Niedermeyer, Huemer Johannes, Markus Murschitz arxiv

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.

📄 PDF Abstract BibTeX arXiv:2602.05557

Code (0)

등록된 구현이 없습니다.

Tasks

3D Object Detection Point Clouds

Local-HDP: Interactive Open-Ended 3D Object Categorization in Real-Time Robotic Scenarios

2020-09-02 · H. Ayoobi, H. Kasaei, M. Cao, R. Verbrugge 외

We introduce a non-parametric hierarchical Bayesian approach for open-ended 3D object categorization, named the Local Hierarchical Dirichlet Process (Local-HDP). This method allows an agent to learn independent topics fo…

Object Categorization Variational Inference

Efficient Global Point Cloud Alignment using Bayesian Nonparametric Mixtures

2016-03-15 · CVPR 2017 7 · Julian Straub, Trevor Campbell, Jonathan P. How, John W. Fisher III

Point cloud alignment is a common problem in computer vision and robotics, with applications ranging from 3D object recognition to reconstruction. We propose a novel approach to the alignment problem that utilizes Bayesi…

3D Object Recognition Object Recognition

Object proposal generation applying the distance dependent Chinese restaurant process

2017-04-12 · Mikko Lauri, Simone Frintrop

In application domains such as robotics, it is useful to represent the uncertainty related to the robot's belief about the state of its environment. Algorithms that only yield a single "best guess" as a result are not su…

Bayesian Inference Object Object Discovery Object Proposal Generation

Challenges for Monocular 6D Object Pose Estimation in Robotics

2023-07-22 · Stefan Thalhammer, Dominik Bauer, Peter Hönig, Jean-Baptiste Weibel 외

Object pose estimation is a core perception task that enables, for example, object grasping and scene understanding. The widely available, inexpensive and high-resolution RGB sensors and CNNs that allow for fast inferenc…

6D Pose Estimation using RGB Object Occlusion Handling Pose Estimation+1

Model-based Kernel Sum Rule: Kernel Bayesian Inference with Probabilistic Models

2014-09-18 · Yu Nishiyama, Motonobu Kanagawa, Arthur Gretton, Kenji Fukumizu

Kernel Bayesian inference is a principled approach to nonparametric inference in probabilistic graphical models, where probabilistic relationships between variables are learned from data in a nonparametric manner. Variou…

Bayesian Inference