Skip to main content

MULTI-FINGERED HAND

Dexterity, power, and durability.

The only hand realized at human scale.

16DOF Actuated joints
180deg/s Max. cont. joint velocity
50N Max. cont. fingertip force
150S Hold duration
450k+ Practical durability test cycles
1.23m/s Impact resistance
Publications HUMANOIDS SUMMIT 2026

A robotic hand that can manipulate objects like a human

Our robotic hand can grasp a wide range of objects and manipulate tools designed for humans. We are developing a new robotic hand that can perform the many kinds of work that humans do. We aim to create a society in which robots are useful to humans, working in harmony with people's lifestyles and becoming an integral part of their daily lives.

TECHNOLOGY

Technologies behind the multi-fingered hand

TECHNOLOGY / Details

Dexterity

Dexterity

16 DOF / 180 deg/s

16 active joints / Finger-thumb opposability / Maximum joint velocity 180 deg/sec

Power

50N / 150s

It can exert a maximum fingertip force of 50 N and sustain it for up to 150 seconds.

Power
Durability

Durability

450,000+ cycles

It has completed 450,000 durability cycles under various fingertip load conditions, including 24,000 cycles involving lifting a 5 kg weight.

Impact Resistance

1.23m/s

Even when the fingers hit an obstacle at 1.23m/s, the system can detect it and switch control mode to absorb the force.

Impact Resistance

FEATURES

While human hands are both dexterous and powerful, robots have struggled to achieve the same balance. Our multi-fingered hand provides the precision necessary to thread a needle, as well as an output of 50 N at a human scale. We have finally reached a practical level where it can “work like a human.”

WORK SCENES

Work Scenes

Threading a needle

Demonstration of threading a needle

Threading a needle

Tightening a small screw

Precisely tightening a small screw

Tightening a small screw

Manipulating a bolt

Tool-like rotational screw manipulation

Manipulating a bolt

Using scissors

Cutting with scissors

Using scissors

Publications

Published papers on multi-fingered hands

  • Naoki Morihira, Amal Nahar, Kartik Bharadwaj, Yasuhiro Kato, Akinobu Hayashi, Tatsuya Harada,

    “R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation”,

    In Proceedings of the International Conference on Learning Representations (ICLR), 2026, accepted.

  • Yohei Kitahara and Manoj Bhadu,

    “Relative Geometrical Constraint on Finger Motion for Dexterous Teleoperation of Multifingered Hand”,

    IEEE/SICE International Symposium on System Integration (SII), 2026.

  • Naoki Morihira, Pranav Deo, Manoj Bhadu, Akinobu Hayashi, Tadaaki Hasegawa, Satoshi Otsubo, Takayuki Osa,

    “Touch-Based Manipulation with Multi-Fingered Robot using Off-policy RL and Temporal Contrastive Learning”,

    IEEE International Conferences on Robotics and Automation (ICRA), 2024.

  • Tomohiro Chaki and Tomohiro Kawakami,

    “Quadratic Programming Based Inverse Kinematics for Precise Bimanual Manipulation”,

    IEEE International Conferences on Robotics and Automation (ICRA), 2024.

  • Takayuki Osa, Akinobu Hayashi, Pranav Deo, Naoki Morihira, Takahide Yoshiike,

    “Offline Reinforcement Learning with Mixture of Deterministic Policies”,

    Transactions on Machine Learning Research, 2023.

Publications

HUMANOIDS SUMMIT 2026

Humanoids Summit 2026
HUMANOIDS SUMMIT 2026

Overseas reseach branches

Research and development through a global network

Honda Research Institute Europe
Honda Research Institute Europe Offenbach/Main, Germany
Honda Research Institute USA
Honda Research Institute USA California & Ohio

MULTI-FINGERED HAND

Publications HUMANOIDS SUMMIT 2026