Grasp Synthesis Matching From Rigid To Soft Robot Grippers Using Conditional Flow Matching

2026-02-19

AI Summary

This work addresses the representational gap between rigid and compliant gripper grasping strategies, which leads to high data requirements and poor accuracy when directly transferring policies. To bridge this gap, the study introduces conditional flow matching (CFM) for the first time to enable continuous mapping from rigid gripper poses to those of a compliant Fin-ray gripper. By integrating a U-Net-based autoencoder with geometric encoding derived from depth images, the proposed method achieves data-efficient adaptation of grasping policies. Experiments on a 7-degree-of-freedom robotic platform demonstrate that the approach attains grasp success rates of 34% and 46% on seen and unseen objects, respectively, significantly outperforming baseline methods—particularly excelling on cylindrical and spherical objects.

Technology Category

• Intelligent Robots: Manipulation
• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

A representation gap exists between grasp synthesis for rigid and soft grippers. Anygrasp [1] and many other grasp synthesis methods are designed for rigid parallel grippers, and adapting them to soft grippers often fails to capture their unique compliant behaviors, resulting in data-intensive and inaccurate models. To bridge this gap, this paper proposes a novel framework to map grasp poses from a rigid gripper model to a soft Fin-ray gripper. We utilize Conditional Flow Matching (CFM), a generative model, to learn this complex transformation. Our methodology includes a data collection pipeline to generate paired rigid-soft grasp poses. A U-Net autoencoder conditions the CFM model on the object's geometry from a depth image, allowing it to learn a continuous mapping from an initial Anygrasp pose to a stable Fin-ray gripper pose. We validate our approach on a 7-DOF robot, demonstrating that our CFM-generated poses achieve a higher overall success rate for seen and unseen objects (34% and 46% respectively) compared to the baseline rigid poses (6% and 25% respectively) when executed by the soft gripper. The model shows significant improvements, particularly for cylindrical (50% and 100% success for seen and unseen objects) and spherical objects (25% and 31% success for seen and unseen objects), and successfully generalizes to unseen objects. This work presents CFM as a data-efficient and effective method for transferring grasp strategies, offering a scalable methodology for other soft robotic systems.

Problem

• grasp synthesis
• rigid grippers
• soft grippers
• representation gap
• compliant behavior

Innovation

• Conditional Flow Matching
• Grasp Synthesis
• Soft Grippers
• Pose Transfer
• U-Net Autoencoder