Research Analyzer
← Back ICRA 2026

Suction Leap-Hand: Suction Cups on a Multi-Fingered Hand Enable Embodied Dexterity and In-Hand Teleoperation

Sun Zhaole, Xiaofeng Mao, Jihong Zhu, Yuanlong Zhang, Robert Fisher

PDF

AI summary

Key figure (auto-extracted from paper)
Replacing friction-based grasping with fingertip suction cups on a multi-fingered hand simplifies teleoperation and unlocks super-human in-hand manipulation tasks.
dexterous manipulation suction-based grasping robotic teleoperation non-anthropomorphic design in-hand manipulation embodied AI

Problem

Current dexterous manipulation relies on anthropomorphic hands and friction-based force-closure, which limits robotic capabilities to human-level tasks and makes teleoperation and data collection excessively difficult due to the cognitive burden of maintaining stable multi-point grasps.

Approach

The authors designed a three-fingered robotic hand equipped with suction cups on each fingertip and the palm, shifting from friction-based grasping to stable adhesion to simplify teleoperation and unlock novel manipulation capabilities.

Key results

  • Novel 15-DoF three-fingered hand design with integrated fingertip and palm suction cups
  • A simplified teleoperation system enabling stable, low-cognitive-load in-hand demonstrations
  • Successful execution of super-human tasks like one-handed paper cutting and in-hand writing
  • Demonstration that suction-based adhesion decouples grasp stability from complex multi-finger coordination

Why it matters

This work matters to robotics and AI researchers by demonstrating that abandoning anthropomorphic constraints in favor of adhesion-based embodiments can drastically simplify data collection and enable super-human dexterous manipulation.

Abstract

Dexterous in-hand manipulation remains a foun- dational challenge in robotics, with progress often constrained by the prevailing paradigm of imitating the human hand. This anthropomorphic approach creates two critical barriers: 1) it limits robotic capabilities to tasks humans can already perform, and 2) it makes data collection for learning-based methods exceedingly difficult. Both challenges are caused by traditional force-closure which requires coordinating complex, multi-point contacts based on friction, normal force, and gravity to grasp an object. In this work, we propose a paradigm shift: moving away from replicating human mechanics toward the design of novel robotic embodiments. We introduce the Suction Leap- Hand (SLeap Hand), a multi-fingered hand featuring integrated fingertip suction cups that realize a new form of suction- enabled dexterity. By replacing complex force-closure grasps with stable, single-point adhesion, our design fundamentally simplifies in-hand teleoperation and facilitates the collection of high-quality demonstration data. More importantly, this suction-based embodiment unlocks a new class of dexterous skills that are difficult or even impossible for the human hand, such as one-handed paper cutting and in-hand writing. Our work demonstrates that by moving beyond anthropomorphic constraints, novel embodiments can not only lower the barrier for collecting robust manipulation data but also enable the stable, single-handed completion of tasks that would typically require two human hands. Our webpage is https://sites. google.com/view/sleaphand.

Index terms

Dexterous Manipulation In-Hand Manipulation Multifingered Hands

Related papers