Disentangled Iterative Surface Fitting for Contact-stable Grasp Planning

2025-02-17

AI Summary

Existing surface-fitting-based grasp planning methods neglect contact-point distribution stability, leading to frequent grasp failures. To address this, we propose a decoupled iterative surface fitting framework that explicitly optimizes contact stability while preserving geometric compatibility. Inspired by human grasping behavior, our method introduces a three-stage optimization pipeline—normal alignment, center-of-mass calibration, and gripper aperture adjustment—directly embedded within the surface fitting process. By jointly incorporating geometric modeling and contact mechanics constraints, the approach achieves an 80% improvement in grasp success rate on 10 objects from the YCB dataset, significantly enhancing contact robustness. Our key contributions are: (i) establishing a synergistic optimization paradigm that jointly balances geometric fidelity and contact stability; and (ii) proposing a novel, interpretable, and decoupled grasp planning framework grounded in physical principles.

Technology Category

• Intelligent Robots: Manipulation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

In this work, we address the limitation of surface fitting-based grasp planning algorithm, which primarily focuses on geometric alignment between the gripper and object surface while overlooking the stability of contact point distribution, often resulting in unstable grasps due to inadequate contact configurations. To overcome this limitation, we propose a novel surface fitting algorithm that integrates contact stability while preserving geometric compatibility. Inspired by human grasping behavior, our method disentangles the grasp pose optimization into three sequential steps: (1) rotation optimization to align contact normals, (2) translation refinement to improve Center of Mass (CoM) alignment, and (3) gripper aperture adjustment to optimize contact point distribution. We validate our approach through simulations on ten YCB dataset objects, demonstrating an 80% improvement in grasp success over conventional surface fitting methods that disregard contact stability. Further details can be found on our project page: https://tomoya-yamanokuchi.github.io/disf-project-page/.

Problem

• Improve grasp stability in surface fitting
• Integrate contact stability with geometric alignment
• Optimize contact point distribution for stable grasps

Innovation

• Integrates contact stability
• Disentangles grasp pose optimization
• Improves grasp success rate