Motion Primitive Recognition on Human Guided Robotic Arm using Machine Learning

2019 ◽  
Author(s):  
Shih-Kang Chen ◽  
Chin-Sheng Chen
Keyword(s):  
Machine Learning ◽  
Robotic Arm ◽  
Motion Primitive

ROBOTIC ARM WITH BIoT MACHINE LEARNING SYSTEM

Fractals ◽  
2020 ◽  
Vol 28 (04) ◽  
pp. 2050088
Author(s):  
R. CARREÑO AGUILERA ◽  
F. AGUILAR ACEVEDO ◽  
M. PATIÑO ORTIZ ◽  
J. PATIÑO ORTIZ
Keyword(s):  
Machine Learning ◽  
Expert System ◽  
Internet Of Things ◽  
Reference Points ◽  
Learning System ◽  
Artificial Vision ◽  
Robotic Arm ◽  
The Internet ◽  
Limiting Factor ◽  
Flat Surfaces

In this work, we present a robotic arm assisted by a visual system to decide whether an object with different colors, parallel flat surfaces and other types of surfaces would be subject to be manipulated without a drop risk. This robotic arm is assisted with sensors such as temperature, humidity, artificial vision, etc. and monitored with a Blockchain Internet of Things (BIoT) expert system assistance, which is shared and accessed by the internet by the users. A prototype for industrial purpose is launched to start providing data for training the expert system, achieving in this way an expert system with machine learning. The variations derived from the identification of the reference points and the characteristics of the robotic arm are a limiting factor of the system, however, it was possible to correctly locate the robotic arm in the workspace to take the object and manipulate it using machine learning based on a BIoT expert system.

Application of real-time machine learning to myoelectric prosthesis control: A case series in adaptive switching

2016 ◽  
Vol 40 (5) ◽  
pp. 573-581 ◽  
Author(s):  
Ann L Edwards ◽  
Michael R Dawson ◽  
Jacqueline S Hebert ◽  
Craig Sherstan ◽  
Richard S Sutton ◽  
...  
Keyword(s):  
Machine Learning ◽  
Adaptive Control ◽  
Cognitive Load ◽  
Real Time ◽  
Case Series ◽  
Robotic Arm ◽  
User Intent ◽  
Myoelectric Prostheses ◽  
Time Prediction ◽  
Case Series Study

Background: Myoelectric prostheses currently used by amputees can be difficult to control. Machine learning, and in particular learned predictions about user intent, could help to reduce the time and cognitive load required by amputees while operating their prosthetic device. Objectives: The goal of this study was to compare two switching-based methods of controlling a myoelectric arm: non-adaptive (or conventional) control and adaptive control (involving real-time prediction learning). Study design: Case series study. Methods: We compared non-adaptive and adaptive control in two different experiments. In the first, one amputee and one non-amputee subject controlled a robotic arm to perform a simple task; in the second, three able-bodied subjects controlled a robotic arm to perform a more complex task. For both tasks, we calculated the mean time and total number of switches between robotic arm functions over three trials. Results: Adaptive control significantly decreased the number of switches and total switching time for both tasks compared with the conventional control method. Conclusion: Real-time prediction learning was successfully used to improve the control interface of a myoelectric robotic arm during uninterrupted use by an amputee subject and able-bodied subjects. Clinical relevance Adaptive control using real-time prediction learning has the potential to help decrease both the time and the cognitive load required by amputees in real-world functional situations when using myoelectric prostheses.

scholarly journals Model approach of a robotic manipulator 3DOF using Machine Learning

2019 ◽  
Vol 5 (1) ◽  
Author(s):  
Darielson Souza ◽  
Josias Batista ◽  
Laurinda Reis ◽  
Antonio De Souza Junior
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Comparative Analysis ◽  
Computational Intelligence ◽  
Machine Learning Techniques ◽  
Robotic Arm ◽  
Learning Techniques ◽  
Three Phase ◽  
And Robotics ◽  
Model Approach

Applications of robotics have been steadily expanding in recent years, and robotics is evolving every day. Currently, robotics is seen as an important area in many applications. Robotics and computational intelligence are increasingly working in parallel with the goal of better performance and productivity. This work has the objective of making an modeling of a robotic arm with three phase induction motor through machine learning techniques to obtain a better model that represents the plant. The techniques used were Articial Neural Network (ANNs): MLP and ELM. The techniques obtained a good performance, and they were evaluated through the multi-correlation coecient for a comparative analysis.

Nonlinear Identification of a Robotic Arm Using Machine Learning Techniques

2019 ◽  
pp. 492-501 ◽  
Author(s):  
Darielson A. Souza ◽  
Laurinda L. N. Reis ◽  
Josias G. Batista ◽  
Jonatha R. Costa ◽  
Antonio B. S. Junior ◽  
...  
Keyword(s):  
Machine Learning ◽  
Machine Learning Techniques ◽  
Robotic Arm ◽  
Nonlinear Identification ◽  
Learning Techniques

scholarly journals EMG Controlled Bionic Robotic Arm using Artificial Intelligence and Machine Learning

2020 ◽  
Author(s):  
Farhan Fuad Rupom ◽  
Shafaitul Jannat ◽  
Farjana Ferdousi Tamanna ◽  
Gazi Musa Al Johan ◽  
Md. Motaharul Islam
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Robotic Arm

scholarly journals Intelligent robust control of redundant smart robotic arm Pt I: Soft computing KB optimizer - deep machine learning IT

2020 ◽  
Vol 2 (1) ◽  
Author(s):  
Alena V Nikolaeva ◽  
Sergey Victorovich Ulyanov
Keyword(s):  
Machine Learning ◽  
Control System ◽  
Robust Control ◽  
Control Systems ◽  
Soft Computing ◽  
Intelligent Control ◽  
Control Object ◽  
Robotic Arm ◽  
Control Laws ◽  
Intelligent Control Systems

Redundant robotic arm models as a control object discussed. Background of computational intelligence IT based on soft computing optimizer of knowledge base in smart robotic manipulators introduced. Soft computing optimizer is the toolkit of deep machine learning SW platform with optimal fuzzy neural network structure. The methods for development and design technology of intelligent control systems based on the soft computing optimizer presented in this Part 1 allow one to implement the principle of design an optimal intelligent control systems with a maximum reliability and controllability level of a complex control object under conditions of uncertainty in the source data, and in the presence of stochastic noises of various physical and statistical characters. The knowledge bases formed with the application of a soft computing optimizer produce robust control laws for the schedule of time dependent coefficient gains of conventional PID controllers for a wide range of external perturbations and are maximally insensitive to random variations of the structure of control object. The robustness of control laws is achieved by application a vector fitness function for genetic algorithm, whose one component describes the physical principle of minimum production of generalized entropy both in the control object and the control system, and the other components describe conventional control objective functionals such as minimum control error, etc. The application of soft computing technologies (Part I) for the development a robust intelligent control system that solving the problem of precision positioning redundant (3DOF and 7 DOF) manipulators considered. Application of quantum soft computing in robust intelligent control of smart manipulators in Part II described.

scholarly journals Multisensory Plucked Instrument Modeling in Unity3D: From Keytar to Accurate String Prototyping

2020 ◽  
Vol 10 (4) ◽  
pp. 1452 ◽  
Author(s):  
Federico Fontana ◽  
Razvan Paisa ◽  
Roberto Ranon ◽  
Stefania Serafin
Keyword(s):  
Machine Learning ◽  
Virtual Instrument ◽  
Haptic Feedback ◽  
Learning Algorithms ◽  
Software Tools ◽  
Machine Learning Algorithms ◽  
Robotic Arm ◽  
Virtual Instruments ◽  
Ongoing Work ◽  
Multisensory Interactions

Keytar is a plucked guitar simulation mockup developed with Unity3D that provides auditory, visual, and haptic feedback to the player through a Phantom Omni robotic arm. Starting from a description of the implementation of the virtual instrument, we discuss our ongoing work. The ultimate goal is the creation of a set of software tools available for developing plucked instruments in Unity3D. Using such tools, sonic interaction designers can efficiently simulate plucked string prototypes and realize multisensory interactions with virtual instruments for unprecedented purposes, such as testing innovative plucked string interfaces or training machine learning algorithms with data about the dynamics of the performance, which are immediately accessible from the machine.

Sign in / Sign up

Export Citation Format

Share Document