Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction

TL;DR

This paper introduces FixIt, a dataset and FixNet framework that leverage learned physical simulation and perception to diagnose and fix malfunctional 3D objects, mimicking human mental reasoning.

Contribution

The paper presents a novel dataset and a framework combining perception and physical dynamics prediction to improve fixing malfunctional objects, advancing beyond static perception models.

Findings

FixNet outperforms baseline models significantly.

The framework generalizes well to similar interaction types.

Experimental results validate the effectiveness of the approach.

Abstract

This paper studies the problem of fixing malfunctional 3D objects. While previous works focus on building passive perception models to learn the functionality from static 3D objects, we argue that functionality is reckoned with respect to the physical interactions between the object and the user. Given a malfunctional object, humans can perform mental simulations to reason about its functionality and figure out how to fix it. Inspired by this, we propose FixIt, a dataset that contains about 5k poorly-designed 3D physical objects paired with choices to fix them. To mimic humans' mental simulation process, we present FixNet, a novel framework that seamlessly incorporates perception and physical dynamics. Specifically, FixNet consists of a perception module to extract the structured representation from the 3D point cloud, a physical dynamics prediction module to simulate the results of interactions on 3D objects, and a functionality prediction module to evaluate the functionality and choose the correct fix. Experimental results show that our framework outperforms baseline models by a large margin, and can generalize well to objects with similar interaction types.