This paper presents a human-mimetic manipulator capable of shock absorption by using dislocation at the soft joint. A one degree-of-freedom (DOF) soft robot joint was developed based on the human elbow-joint structure, especially mimicking the humeroulnar joint in the elbow. Each component of the soft joint is combined by an elastic ligament, which is made up of elastic rubber and is attached to the pivot joint pin positioned at a predetermined place according to a specially designed pin guide. As an external impact is applied to the joint, the elastic ligament is elongated as the pivot joint pin is moved from the predetermined place. This state is defined as a dislocation, which is similar to the dislocation of a human joint when impacted. Dislocation in the proposed soft robot joint occurred when the external impact was larger than the predetermined threshold force. This threshold force can be predicted by the modulus of the elastic ligament and the shape of the pin guide, and the theoretical model was developed in this study. To evaluate the function of dislocation, dynamic and quasi-static impact tests were performed at the 1-DOF soft robot joint. Moreover, the human-mimetic manipulator is proposed based on the 2-DOF soft robot joint. This manipulator can realize four motions of a human arm using the pneumatic artificial muscles: flexion, extension, pronation and supination. Each artificial muscle and bone structure were similar to the human arm structure, and thus the configuration of each bone structure of the manipulator for each motion is similar to the configurations of a human skeletal structure. This manipulator was also capable of dislocation to absorb the external impact. The developed human-mimetic manipulator with a soft joint is expected to be applied to a naturally safe humanoid robot that works with humans in the same space.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1088/1748-3190/ab46f7 | DOI Listing |
Front Robot AI
December 2024
CREATE-Lab, Department of Mechanical Engineering, Swiss Federal Technology Institute of Lausanne (EPFL), Lausanne, Switzerland.
Creativity and style in music playing originates from constraints and imperfect interactions between instruments and players. Digital and robotic systems have so far been unable to capture this naturalistic playing. Whether as an additional tool for musicians, function restoration with prosthetics, or artificial intelligence-powered systems, the physical embodiment and interactions generated are critical for expression and connection with an audience.
View Article and Find Full Text PDFBiomimetics (Basel)
December 2024
School of Computer Science and Technology, Dongguan University of Technology, Dongguan 523808, China.
In this paper, a deep reinforcement learning (DRL) approach based on generative adversarial imitation learning (GAIL) and long short-term memory (LSTM) is proposed to resolve tracking control problems for robotic manipulators with saturation constraints and random disturbances, without learning the dynamic and kinematic model of the manipulator. Specifically, it limits the torque and joint angle to a certain range. Firstly, in order to cope with the instability problem during training and obtain a stability policy, soft actor-critic (SAC) and LSTM are combined.
View Article and Find Full Text PDFBiomimetics (Basel)
December 2024
School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, China.
Worms are organisms characterized by simple structures, low energy consumption, and stable movement. Inspired by these characteristics, worm-like soft robots demonstrate exceptional adaptability to unstructured environments, attracting considerable interest in the field of biomimetic engineering. The primary challenge currently involves improving the motion performance of worm-like robots from the perspectives of actuation and anchoring.
View Article and Find Full Text PDFBiomimetics (Basel)
December 2024
Department of Electrical and Computer Engineering, Hellenic Mediterranean University, GR-71410 Heraklion, Greece.
This paper addresses the design, development, control, and experimental evaluation of a soft robot arm whose actuation is inspired by the muscular structure of the octopus arm, one of the most agile biological manipulators. The robot arm is made of soft silicone and thus possesses enhanced compliance, which is beneficial in a variety of applications where the arm may come into contact with delicate features of its environment. The arm is composed of three elongated segments arranged in series, each one of which contains several pneumatically actuated chambers embedded in its silicone body, which may induce various types of deformations of the segment.
View Article and Find Full Text PDFSoft Robot
December 2024
Department of Surgical & Interventional Engineering, School of Biomedical Engineering & Imaging Sciences, King's College London (KCL), London, UK.
Modern industrial and medical applications require soft actuators with practical actuation methods, capable of precision control and high-speed performance. Within the realm of medical robotics, precision and speed imply less complications and reduced operational times. Soft fluidic actuators (SFAs) are promising candidates to replace the current rigid endoscopes due to their mechanical compliance, which offers safer human-robot interaction.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!