PIRATR: 3D点群におけるトランスフォーマを用いたロボティクス向けパラメトリック物体推論
PIRATR: Parametric Object Inference for Robotic Applications with Transformers in 3D Point Clouds
遮蔽のある3D点群から6自由度姿勢とクラス固有のパラメータ(例: グリッパ開口幅)を同時推定するエンドツーエンド検出フレームワークを提案し、フォークリフトでの実LiDARスキャンに合成学習のみで汎化できることを示した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Michael Schwingshackl, Fabio F. Oberweger, Mario Niedermeyer, Huemer Johannes, Markus Murschitz
分類: cs.CV, cs.RO
原文アブストラクト
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.
