Grasp Planning for Flexible Production with Small Lot Sizes based on CAD models using GPIS and Bayesian Optimization

TL;DR

This paper introduces a novel grasp planning method combining Bayesian optimization with GPIS shape modeling and dual-stage optimization, achieving high success rates in complex multi-fingered hand grasping tasks.

Contribution

It presents a new global optimization framework for grasp planning that integrates object shape via GPIS and refines grasp parameters using Bayesian optimization and ADMM.

Findings

Achieves 95% success rate on diverse objects

Effectively integrates shape information into grasp planning

Demonstrates superior performance in simulation experiments

Abstract

Grasp planning for multi-fingered hands is still a challenging task due to the high nonlinear quality metrics, the high dimensionality of hand posture configuration, and complex object shapes. Analytical-based grasp planning algorithms formulate the grasping problem as a constraint optimization problem using advanced convex optimization solvers. However, these are not guaranteed to find a globally optimal solution. Data-driven based algorithms utilize machine learning algorithm frameworks to learn the grasp policy using enormous training data sets. This paper presents a new approach for grasp generation by formulating a global optimization problem with Bayesian optimization. Furthermore, we parameterize the object shape utilizing the Gaussian Process Implicit Surface (GPIS) to integrate the object shape information into the optimization process. Moreover, a chart defined on the object surface is used to refine palm pose locally. We introduced a dual optimization stage to optimize the palm pose and contact points separately. We further extend the Bayesian optimization by utilizing the alternating direction method of multipliers (ADMM) to eliminate contact optimization constraints. We conduct the experiments in the graspit! Simulator that demonstrates the effectiveness of this approach quantitatively and qualitatively. Our approach achieves a 95% success rate on various commonly objects with diverse shapes, scales, and weights