Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery
This addresses the challenge of embodied agents manipulating objects to recover parts, which is incremental in combining action selection and motion segmentation for perceptual recovery.
The paper tackles the problem of discovering and segmenting articulated object parts through physical interaction, without semantic labels, by introducing Act the Part (AtP), which learns efficient strategies that generalize to unseen categories and transfer to real-world data without fine-tuning.
People often use physical intuition when manipulating articulated objects, irrespective of object semantics. Motivated by this observation, we identify an important embodied task where an agent must play with objects to recover their parts. To this end, we introduce Act the Part (AtP) to learn how to interact with articulated objects to discover and segment their pieces. By coupling action selection and motion segmentation, AtP is able to isolate structures to make perceptual part recovery possible without semantic labels. Our experiments show AtP learns efficient strategies for part discovery, can generalize to unseen categories, and is capable of conditional reasoning for the task. Although trained in simulation, we show convincing transfer to real world data with no fine-tuning.