Evaluation of Brain Models to Control a Robotic Origami Arm Using Holographic Neural Networks

2015 ◽  
Author(s):  
J. A. Romero ◽  
L. A. Diago ◽  
J. Shinoda ◽  
I. Hagiwara
Keyword(s):  
Back Propagation ◽  
Motor Command ◽  
Control Model ◽  
Robotic Arm ◽  
Training Methods ◽  
Holographic Method ◽  
Modeling And Control ◽  
Paper Folding ◽  
Fast Movement ◽  
And Control

In robotics, one of the most difficult task is to perform a precisely and fast movement of a robotic arm. For paper-folding robots, it is still extremely difficult to execute the required manipulations of the paper mainly because the difficulties in modeling and control of the paper. In this paper two control models are proposed to solve this problem. One of the best approaches comes from Neuroscience, where using a human’s brain inspired control system known as Cerebellar control model (CCM), precisely and fast movements of a robotic arm can be performed. In the CCM a Feedback controller motor command is used as a target signal to train an Artificial Neural Network (NN), and use the output of the NN as a Feed-forward signal. In this paper two training methods were evaluated in order to improve the behavior in CCM: the traditional Back propagation and a Holographic method.

scholarly journals Design, fabrication, modeling and control of a fabric-based spherical robotic arm

Mechatronics ◽  
2020 ◽  
Vol 68 ◽  
pp. 102369
Author(s):  
Matthias Hofer ◽  
Raffaello D’Andrea
Keyword(s):  
Robotic Arm ◽  
Modeling And Control ◽  
And Control

Neural Network Designs for Partially Known Dynamic Systems

1994 ◽  
Vol 116 (3) ◽  
pp. 407-409 ◽  
Author(s):  
S. I. Mistry ◽  
S. S. Nair
Keyword(s):  
Dynamic Systems ◽  
Machine Tools ◽  
Hardware Implementation ◽  
Back Propagation ◽  
Neural Dynamic ◽  
Modeling And Control ◽  
Training Scheme ◽  
Network Training ◽  
On Line ◽  
And Control

Algorithms are investigated for system identification and control using neural networks and validated using on-line hardware implementation. Such algorithms require very little knowledge about the system which, together with their capability of learning, make them attractive for the modeling and control of nonlinear partially known dynamic systems. An implementation architecture for neural dynamic back propagation suitable for application to other machine tools and manufacturing processes, and a network training scheme with more general features are proposed.

scholarly journals Design and Control of an Inflatable Spherical Robotic Arm for Pick and Place Applications

Actuators ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 299
Author(s):  
Matthias Hofer ◽  
Jasan Zughaibi ◽  
Raffaello D’Andrea
Keyword(s):  
Lightweight Design ◽  
Joint Stiffness ◽  
Robotic Arm ◽  
Robot Arm ◽  
Allocation Strategy ◽  
Modeling And Control ◽  
Control Approach ◽  
Flow Capacity ◽  
Payload Mass ◽  
And Control

We present an inflatable soft robotic arm made of fabric that leverages state-of-the-art manufacturing techniques, leading to a robust and reliable manipulator. Three bellow-type actuators are used to control two rotational degrees of freedom, as well as the joint stiffness that is coupled to a longitudinal elongation of the movable link used to grasp objects. The design is motivated by a safety analysis based on first principles. It shows that the interaction forces during an unexpected collision are primarily caused by the attached payload mass, but can be reduced by a lightweight design of the robot arm. A control allocation strategy is employed that simplifies the modeling and control of the robot arm and we show that a particular property of the allocation strategy ensures equal usage of the actuators and valves. The modeling and control approach systematically incorporates the effect of changing joint stiffness and the presence of a payload mass. An investigation of the valve flow capacity reveals that a proper timescale separation between the pressure and arm dynamics is only given for sufficient flow capacity. Otherwise, the applied cascaded control approach can introduce oscillatory behavior, degrading the overall control performance. A closed form feed forward strategy is derived that compensates errors induced by the longitudinal elongation of the movable link and allows the realization of different object manipulation applications. In one of the applications, the robot arm hands an object over to a human, emphasizing the safety aspect of the soft robotic system. Thereby, the intrinsic compliance of the robot arm is leveraged to detect the time when the robot should release the object.

Sign in / Sign up

Export Citation Format

Share Document