AdaAfford: 少数回のインタラクションで3D関節物体の操作アフォーダンスを適応学習
AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactions
3D関節物体の操作アフォーダンスを、テスト時に少数回のインタラクションを行うことでインスタンスごとに精度良く適応させるフレームワークAdaAffordを提案し、PartNet-Mobilityデータセットで有効性を示した。
著者: Yian Wang, Ruihai Wu, Kaichun Mo, Jiaqi Ke, Qingnan Fan, Leonidas Guibas, Hao Dong
分類: cs.CV, cs.RO
原文アブストラクト
Perceiving and interacting with 3D articulated objects, such as cabinets, doors, and faucets, pose particular challenges for future home-assistant robots performing daily tasks in human environments. Besides parsing the articulated parts and joint parameters, researchers recently advocate learning manipulation affordance over the input shape geometry which is more task-aware and geometrically fine-grained. However, taking only passive observations as inputs, these methods ignore many hidden but important kinematic constraints (e.g., joint location and limits) and dynamic factors (e.g., joint friction and restitution), therefore losing significant accuracy for test cases with such uncertainties. In this paper, we propose a novel framework, named AdaAfford, that learns to perform very few test-time interactions for quickly adapting the affordance priors to more accurate instance-specific posteriors. We conduct large-scale experiments using the PartNet-Mobility dataset and prove that our system performs better than baselines.
