Adaptive Grasping of Moving Objects in Dense Clutter via Global-to-Local Detection and Static-to-Dynamic Planning

TL;DR

This paper presents a novel robotic grasping system that effectively handles moving objects in cluttered environments by combining global-to-local detection and static-to-dynamic planning, improving adaptability and efficiency without extensive training.

Contribution

It introduces a unified approach integrating similarity matching, local detection, and dynamic planning with optimization for grasping moving objects in cluttered scenes.

Findings

Successfully grasped moving objects in dense clutter.

Operated effectively across various object types and speeds.

Achieved real-time performance with optimized planning methods.

Abstract

Robotic grasping is facing a variety of real-world uncertainties caused by non-static object states, unknown object properties, and cluttered object arrangements. The difficulty of grasping increases with the presence of more uncertainties, where commonly used learning-based approaches struggle to perform consistently across varying conditions. In this study, we integrate the idea of similarity matching to tackle the challenge of grasping novel objects that are simultaneously in motion and densely cluttered using a single RGBD camera, where multiple uncertainties coexist. We achieve this by shifting visual detection from global to local states and operating grasp planning from static to dynamic scenes. Notably, we introduce optimization methods to enhance planning efficiency for this time-sensitive task. Our proposed system can adapt to various object types, arrangements and movement speeds without the need for extensive training, as demonstrated by real-world experiments. Videos are available at https://youtu.be/sdC50dx-xp8?si=27oVr4dhG0rqN_tT.