MIDAS Hand: Modular low-Impedance Direct-drive Anthropomorphic Sensing Hand

2026-07-15

AI Summary

Current dexterous hands struggle to simultaneously achieve human-scale dimensions, low cost, ease of maintenance, tactile sensing, and practical utility, thereby hindering advances in dexterous manipulation research. This work presents an open-source, human-scale dexterous hand platform with a material cost under \$3,000, featuring 13 active degrees of freedom and 283 triaxial tactile sensing units. Leveraging 3D-printed structures and direct-drive actuators, the design achieves low impedance, minimal backdrivable torque, and high maintainability. A full-stack open-source toolchain—including control APIs, simulation models, and a teleoperation pipeline—is provided alongside the hardware. Weighing 700 grams, the platform has been validated in terms of workspace, grasp categorization, payload capacity, and teleoperation performance, offering a robust, reproducible experimental foundation for tactile-driven dexterous manipulation studies.

Abstract

Dexterous manipulation is limited not only by algorithms but by a shortage of accessible hand hardware that combines human-scale morphology, ease of manufacturing or maintenance, tactile sensing, and practical cost. Existing dexterous hands tend to optimize some of these properties at the expense of others. We present MIDAS Hand, a low-cost, open-source, human-scale dexterous hand with integrated tactile sensing for manipulation research. MIDAS Hand provides 16 total degrees of freedom (DoF) with 13 active DoF, directly driven actuation with measurably low backdrive torque, and 283 three-axis tactile taxels in a compact 700 g package with a bill of materials under 3,000 USD. Built from 3D-printed components, it assembles in under three hours while providing the strength, repeatability, and maintainability needed for repeated real-world experiments. Alongside the hardware, we release a full stack: design files, build documentation, control and tactile Python APIs, simulation models, and retargeting and teleoperation pipelines. We characterize MIDAS Hand through workspace and grasp-taxonomy analysis, payload and reliability tests, backdrivability measurements, and teleoperation demonstrations with tactile sensing, showing that it offers a balanced, reproducible platform for tactile dexterous manipulation and human-to-robot data collection. Project page: https://midas-hand.com

Problem

• dexterous hand
• tactile sensing
• human-scale morphology
• accessible hardware
• low-cost robotics

Innovation

• direct-drive actuation
• tactile sensing
• dexterous hand
• low-cost robotics
• open-source hardware