AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactions. (arXiv:2112.00246v4 [cs.CV] UPDATED)

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 …

3d arxiv cv interactions learning objects