Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2022 Apr 25:16:861825.
doi: 10.3389/fnbot.2022.861825. eCollection 2022.

Dexterous Manipulation for Multi-Fingered Robotic Hands With Reinforcement Learning: A Review

Affiliations
Review

Dexterous Manipulation for Multi-Fingered Robotic Hands With Reinforcement Learning: A Review

Chunmiao Yu et al. Front Neurorobot. .

Abstract

With the increasing demand for the dexterity of robotic operation, dexterous manipulation of multi-fingered robotic hands with reinforcement learning is an interesting subject in the field of robotics research. Our purpose is to present a comprehensive review of the techniques for dexterous manipulation with multi-fingered robotic hands, such as the model-based approach without learning in early years, and the latest research and methodologies focused on the method based on reinforcement learning and its variations. This work attempts to summarize the evolution and the state of the art in this field and provide a summary of the current challenges and future directions in a way that allows future researchers to understand this field.

Keywords: dexterous manipulation; learn from demonstration; multi-fingered robotic hand; reinforcement learning; sim2real.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Typical tasks of dexterous manipulation with a multi-fingered hand. (A) Relocation, (B) Reorientation & Relocation, (C) Tool use, (D) Door opening, (E) Valve turning, (F) In-hand manipulation, (G) Screwing, (H) Dexterous manipulation, and (I) Pouring.
Figure 2
Figure 2
Overall presentation of this work.
Figure 3
Figure 3
Method based on an accurate model of multi-fingered hand and object.
Figure 4
Figure 4
Dexterous manipulation with a multi-fingered hand through reinforcement learning (part of this picture comes from [89]).
Figure 5
Figure 5
Basic process of learning dexterous manipulation by RL from scratch (part of this picture comes from Open et al., 2019).
Figure 6
Figure 6
Two types of combination of RL and demonstration.
Figure 7
Figure 7
Category of approaches for sim-to-real in this domain.

Similar articles

Cited by

References

    1. Alakuijala M., Dulac-Arnold G., Mairal J., Ponce J., Schmid C. (2021). Residual reinforcement learning from demonstrations. ArXiv210608050 Cs.
    1. Al-Gallaf E., Warwick K. (1995). Force distribution in manipulation by a robot hand with equality and inequality constraints. Mechatronics. 5, 561–583. 10.1016/0957-4158(95)00017-Y - DOI
    1. Allegro hand . Allegro hand, Available online at: https://github.com/simlabrobotics/allegro_hand_ros
    1. Allshire A., Mittal M., Lodaya V., Makoviychuk V., Makoviichuk D., Widmaier F., et al. . (2021). Transferring dexterous manipulation from GPU simulation to a remote real-world trifinger. ArXiv210809779 Cs.
    1. Anderson R. J., Spong M. W. (1988). Hybrid impedance control of robotic manipulators. IEEE J. Robot. Autom. 4, 549–556. 10.1109/56.20440 - DOI

LinkOut - more resources