# Characterization, Analytical Planning, and Hybrid Force Control for the Inspire RH56DFX Hand

Source: [Characterization, Analytical Planning, and Hybrid Force Control for the Inspire RH56DFX Hand](<https://www.sota2.com/research/paper/69b0f6f32d603e6de3e45c38>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-12T05:00:04.726Z

Authors: Xuan Tan, William Xie, Nikolaus Correll

Published: 2026-03-09T22:25:38.000Z

## Abstract

Commercially accessible dexterous robot hands are increasingly prevalent, but many remain difficult to use as scientific instruments. For example, the Inspire RH56DFX hand exposes only uncalibrated proprioceptive information and shows unreliable contact behavior at high speed (up to 1618% force limit overshoot). Furthermore, its underactuated, coupled finger linkages make antipodal grasps non-trivial. We contribute three improvements to the Inspire RH56DFX to transform it from a black-box device to a research tool: (1) hardware characterization (force calibration, latency, and overshoot), (2) a sim2real validated MuJoCo model for analytical width-to-grasp planning, and (3) a hybrid, closed-loop speed-force grasp controller. We validate these components on peg-in-hole insertion, achieving 65% success and outperforming a wrist-force-only baseline of 10% and on 300 grasps across 15 physically diverse objects, achieving 87% success and outperforming plan-free grasps and learned grasps. Our approach is modular, designed for compatibility with external object detectors and vision-language models for width & force estimation and high-level planning, and provides an interpretable and immediately deployable interface for dexterous manipulation with the Inspire RH56DFX hand, open-sourced at this website https://correlllab.github.io/rh56dfx.html.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Grasp Synthesis on Full experiment real](<https://www.sota2.com/research/sota/grasp-synthesis-on-full-experiment-real.md>): Grasp Synthesis; Full experiment real; Success Rate: 87.

- [Grasp Synthesis on YCB sim](<https://www.sota2.com/research/sota/grasp-synthesis-on-ycb-sim.md>): Grasp Synthesis; YCB sim; Success Rate: not recorded.

- [Grasp Synthesis on Functional grasping tools real](<https://www.sota2.com/research/sota/grasp-synthesis-on-functional-grasping-tools-real.md>): Grasp Synthesis; Functional grasping tools real; Success Rate: not recorded.

- [Grasp Synthesis on Efficiency & generalisation real](<https://www.sota2.com/research/sota/grasp-synthesis-on-efficiency-and-generalisation-real.md>): Grasp Synthesis; Efficiency & generalisation real; Success Rate: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.08988>)

[PDF](<https://arxiv.org/pdf/2603.08988.pdf>)
