Evolving Robotic Hand Morphology Through Grasping and Learning

Creatures can co-evolve their biological structures and behaviors under environmental pressures. Leveraging biomimetic evolution algorithms (referred to as co-design or co-optimization), a diverse range of robots with environmental adaptation has been generated. However, implementing these evolution...

Full description

Saved in:
Bibliographic Details
Published in:IEEE robotics and automation letters Vol. 9; no. 10; pp. 8475 - 8482
Main Authors: Yang, Bangchu, Jiang, Li, Wu, Wenhao, Zhen, Ruichen
Format: Journal Article
Language:English
Published: IEEE 01.10.2024
Subjects:
Deep learning
deep learning in grasping and manipulation
Evolutionary robotics
Grasping
Hands
Hardware
hardware gradient
methods and tools for robot system design
Morphology
Optimization
Reconfigurable devices
reconfigurable hand
Robot programming
Stability analysis
ISSN:2377-3766, 2377-3766
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Creatures can co-evolve their biological structures and behaviors under environmental pressures. Leveraging biomimetic evolution algorithms (referred to as co-design or co-optimization), a diverse range of robots with environmental adaptation has been generated. However, implementing these evolutionary methods or results in real-world robots, especially in the case of robotic hands, was not easy. In this context, this work presents a comprehensive self-optimization scheme for robotic hands that encompasses both software and hardware components. This scheme enables robots to autonomously refine their morphology through the integration of hardware gradients and reinforcement learning within parallel environments, thereby enhancing their adaptability to a variety of grasping tasks. For the hardware aspect, we developed a reconfigurable hand prototype with 37 variable hardware parameters (i.e., joint stiffness, the length of phalanges, finger location, and palm curvature) adjusted by mechanical components. Leveraging the adjustable hardware and 20 motors, this hand achieves full actuation and can dynamically adjust its morphology. The training results indicate that the fitness score of the self-optimizing hand exceeds that of original designs in this instance. The hardware parameters can be further fine-tuned in response to task variations. Moreover, the evolved hardware parameters are transferred to a real-world reconfigurable hand, demonstrating its grasping and adaptivity capabilities.
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2024.3440707