OptiGrasp: Optimized Grasp Pose Detection Using RGB Images for Warehouse Picking Robots

TL;DR

OptiGrasp introduces a novel RGB image-based grasp detection method for warehouse robots, leveraging foundation models trained on synthetic data to achieve high success rates without depth sensors.

Contribution

It presents an innovative approach that uses foundation models and synthetic training data to enable robust grasp detection solely from RGB images in warehouse settings.

Findings

Achieved 82.3% success rate in real-world grasping tasks.

Successfully generalized to new objects not seen during training.

Eliminated need for depth sensors, reducing hardware complexity.

Abstract

In warehouse environments, robots require robust picking capabilities to manage a wide variety of objects. Effective deployment demands minimal hardware, strong generalization to new products, and resilience in diverse settings. Current methods often rely on depth sensors for structural information, which suffer from high costs, complex setups, and technical limitations. Inspired by recent advancements in computer vision, we propose an innovative approach that leverages foundation models to enhance suction grasping using only RGB images. Trained solely on a synthetic dataset, our method generalizes its grasp prediction capabilities to real-world robots and a diverse range of novel objects not included in the training set. Our network achieves an 82.3\% success rate in real-world applications. The project website with code and data will be available at http://optigrasp.github.io.