STOPNet: Multiview-based 6-DoF Suction Detection for Transparent Objects on Production Lines
This addresses a challenging problem in robotic systems and modern industry for handling transparent objects, with incremental improvements in method and generalizability.
The authors tackled the problem of 6-DoF suction detection for transparent objects on production lines, where depth-based methods fail, by proposing STOPNet, a multiview stereo framework using only RGB input that reconstructs 3D scenes in real time and generalizes to novel environments and objects, significantly outperforming baselines in experiments.
In this work, we present STOPNet, a framework for 6-DoF object suction detection on production lines, with a focus on but not limited to transparent objects, which is an important and challenging problem in robotic systems and modern industry. Current methods requiring depth input fail on transparent objects due to depth cameras' deficiency in sensing their geometry, while we proposed a novel framework to reconstruct the scene on the production line depending only on RGB input, based on multiview stereo. Compared to existing works, our method not only reconstructs the whole 3D scene in order to obtain high-quality 6-DoF suction poses in real time but also generalizes to novel environments, novel arrangements and novel objects, including challenging transparent objects, both in simulation and the real world. Extensive experiments in simulation and the real world show that our method significantly surpasses the baselines and has better generalizability, which caters to practical industrial needs.