Is That a Chair? Imagining Affordances Using Simulations of an Articulated Human Body
Hongtao Wu, Deven Misra, and Gregory S. Chirikjian

TL;DR
This paper introduces a simulation-based approach for robots to imagine object affordances, specifically chairs, by simulating physical interactions with an articulated human body, enabling better classification and pose prediction.
Contribution
It presents a novel simulation method for affordance reasoning that outperforms deep learning in limited data scenarios and predicts functional poses aligned with human judgments.
Findings
Outperforms deep learning methods with only 30 training models.
Accurately predicts upright and functional poses of chairs.
Aligns well with human judgments on synthetic and real objects.
Abstract
For robots to exhibit a high level of intelligence in the real world, they must be able to assess objects for which they have no prior knowledge. Therefore, it is crucial for robots to perceive object affordances by reasoning about physical interactions with the object. In this paper, we propose a novel method to provide robots with an ability to imagine object affordances using physical simulations. The class of chair is chosen here as an initial category of objects to illustrate a more general paradigm. In our method, the robot "imagines" the affordance of an arbitrarily oriented object as a chair by simulating a physical sitting interaction between an articulated human body and the object. This object affordance reasoning is used as a cue for object classification (chair vs non-chair). Moreover, if an object is classified as a chair, the affordance reasoning can also predict the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRobot Manipulation and Learning · Robotics and Sensor-Based Localization · Human Pose and Action Recognition
