Revolutionizing Packaging: A Robotic Bagging Pipeline with Constraint-aware Structure-of-Interest Planning

TL;DR

A robotic system for automated bagging tasks using an adaptive structure-of-interest (SOI) manipulation approach that relies on real-time visual feedback to dynamically adjust manipulation without requiring prior knowledge of bag materials or dynamics is developed.

Abstract

Bagging operations, common in packaging and assisted living applications, are challenging due to a bag's complex deformable properties. To address this, we develop a robotic system for automated bagging tasks using an adaptive structure-of-interest (SOI) manipulation approach. Our method relies on real-time visual feedback to dynamically adjust manipulation without requiring prior knowledge of bag materials or dynamics. We present a robust pipeline featuring state estimation for SOIs using Gaussian Mixture Models (GMM), SOI generation via optimization-based bagging techniques, SOI motion planning with Constrained Bidirectional Rapidly-exploring Random Trees (CBiRRT), and dual-arm manipulation coordinated by Model Predictive Control (MPC). Experiments demonstrate the system's ability to achieve precise, stable bagging of various objects using adaptive coordination of the manipulators. The proposed framework advances the capability of dual-arm robots to perform more sophisticated automation of common tasks involving interactions with deformable objects.

Figures (11)

• Figure 1: The dual-arm grasps two handles of a fabric bag to manipulate the SOI (i.e., the opening rim) for the bagging task.
• Figure 2: The dual robot grasp two handles of a deformable fabric bag to manipulate the SOI (i.e., the opening rim) for the bagging task.
• Figure 3: Schematic diagram of dual-arm manipulation approach of the bagging task. The algorithm aims to command the robot to manipulate the bag into the specified shape to cover the bottom part of $\mathbf{B}$, i.e., bagging manner. Experiments are conducted in the Cartesian space.
• Figure 4: The visual description of the GMM-based representation.
• Figure 5: (a) The visualization of the bagging SOI. (b) The projection of $\mathcal{F}_m$ in $\mathcal{F}_w$, and visualizing three constraints. The red square is the centroid of $^{\mathcal{F}_m} \Omega^v$ and blue is that of $^{\mathcal{F}_m} \Omega^e$.

Theorems & Definitions (1)

• Remark 1