Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery

05/03/2021
by   Samir Yitzhak Gadre, et al.
0

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.

READ FULL TEXT

page 3

page 6

page 8

page 12

page 13

page 14

page 15

page 16

research
07/19/2022

Structure from Action: Learning Interactions for Articulated Object 3D Structure Discovery

Articulated objects are abundant in daily life. Discovering their parts,...
research
06/16/2020

Learning About Objects by Learning to Interact with Them

Much of the remarkable progress in computer vision has been focused arou...
research
12/01/2020

Visual Identification of Articulated Object Parts

As autonomous robots interact and navigate around real-world environment...
research
10/07/2020

Hierarchical Relational Inference

Common-sense physical reasoning in the real world requires learning abou...
research
05/04/2023

Learning Generalizable Pivoting Skills

The skill of pivoting an object with a robotic system is challenging for...
research
05/26/2023

Towards Open-World Segmentation of Parts

Segmenting object parts such as cup handles and animal bodies is importa...
research
12/21/2021

Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects

Rendering articulated objects while controlling their poses is critical ...

Please sign up or login with your details

Forgot password? Click here to reset