AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactions
This work addresses a key challenge for home-assistant robots in handling articulated objects, though it is incremental as it builds on prior affordance learning methods.
The paper tackles the problem of accurately perceiving manipulation affordance for 3D articulated objects by addressing hidden kinematic and dynamic uncertainties, achieving improved performance over baselines in large-scale experiments on the PartNet-Mobility dataset.
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.