A4T: Hierarchical Affordance Detection for Transparent Objects Depth Reconstruction and Manipulation

TL;DR

This paper introduces A4T, a hierarchical framework for detecting affordances and reconstructing depth maps of transparent objects, significantly improving accuracy and enabling effective robotic manipulation.

Contribution

The paper presents a novel hierarchical affordance detection framework and a multi-step depth reconstruction method tailored for transparent objects, along with a new dataset for evaluation.

Findings

Significantly reduced depth reconstruction error from 0.097 to 0.042 RMSE.

Accurate affordance maps enable effective manipulation of transparent objects.

Demonstrated successful robotic manipulation experiments.

Abstract

Transparent objects are widely used in our daily lives and therefore robots need to be able to handle them. However, transparent objects suffer from light reflection and refraction, which makes it challenging to obtain the accurate depth maps required to perform handling tasks. In this paper, we propose a novel affordance-based framework for depth reconstruction and manipulation of transparent objects, named A4T. A hierarchical AffordanceNet is first used to detect the transparent objects and their associated affordances that encode the relative positions of an object's different parts. Then, given the predicted affordance map, a multi-step depth reconstruction method is used to progressively reconstruct the depth maps of transparent objects. Finally, the reconstructed depth maps are employed for the affordance-based manipulation of transparent objects. To evaluate our proposed method, we construct a real-world dataset TRANS-AFF with affordances and depth maps of transparent objects, which is the first of its kind. Extensive experiments show that our proposed methods can predict accurate affordance maps, and significantly improve the depth reconstruction of transparent objects compared to the state-of-the-art method, with the Root Mean Squared Error in meters significantly decreased from 0.097 to 0.042. Furthermore, we demonstrate the effectiveness of our proposed method with a series of robotic manipulation experiments on transparent objects. See supplementary video and results at https://sites.google.com/view/affordance4trans.