DexFlow

Unified Framework for Dexterous Manipulation

Xiaoyi Lin1, Kunpeng Yao2, Lixin Xu3, Xueqiang Wang4, Xuetao Li1, Yuchen Wang1, Miao Li4,†
IEEE/RSJ IROS 2025

Technical Overview

Abstract

We present DexFlow, a novel framework for dexterous hand pose retargeting and object interaction modeling. Our method combines multi-source human demonstration data with physics-based optimization to generate natural robotic manipulation sequences. The key innovation lies in our contact-aware refinement system that preserves interaction fidelity while ensuring temporal coherence across frames.

Pipeline Overview

DexFlow Framework Architecture

Our proposed grasp retargeting framework comprises three main modules. First, the object segmented from the multi-frame MANO and object interaction sequence is scaled, and the human hand pose is retargeted to a robotic hand pose. Next, a double-threshold detection system extracts initial contact information between the retargeted hand and the object, which is then smoothed over adjacent frames and updated only if certain conditions are met. Finally, each finger is optimized in sequence, starting from the thumb and moving toward the pinky. At each stage of optimization, one finger is refined, and fingers without contact information, such as the index finger, are skipped, ensuring an efficient and accurate optimization procedure.

Interactive Demonstration

Human Demonstration

Retargeted from MoCap data

Robotic Execution

Optimized contact points

Result Demonstrations