scholarly journals Optimization and improvement of a robotics gaze control system using LSTM networks

2021 ◽  
Author(s):  
Jaime Duque Domingo ◽  
Jaime Gómez-García-Bermejo ◽  
Eduardo Zalama
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Optimization Problem ◽  
Human Robot Interaction ◽  
Smooth Transition ◽  
Gaze Control ◽  
Robot Interaction ◽  
New Model ◽  
Competitive Neural Network ◽  
Competitive Network

AbstractGaze control represents an important issue in the interaction between a robot and humans. Specifically, deciding who to pay attention to in a multi-party conversation is one way to improve the naturalness of a robot in human-robot interaction. This control can be carried out by means of two different models that receive the stimuli produced by the participants in an interaction, either an on-center off-surround competitive network or a recurrent neural network. A system based on a competitive neural network is able to decide who to look at with a smooth transition in the focus of attention when significant changes in stimuli occur. An important aspect in this process is the configuration of the different parameters of such neural network. The weights of the different stimuli have to be computed to achieve human-like behavior. This article explains how these weights can be obtained by solving an optimization problem. In addition, a new model using a recurrent neural network with LSTM layers is presented. This model uses the same set of stimuli but does not require its weighting. This new model is easier to train, avoiding manual configurations, and offers promising results in robot gaze control. The experiments carried out and some results are also presented.

scholarly journals Symmetric Evaluation of Multimodal Human–Robot Interaction with Gaze and Standard Control

Symmetry ◽  
2018 ◽  
Vol 10 (12) ◽  
pp. 680
Author(s):  
Ethan Jones ◽  
Winyu Chinthammit ◽  
Weidong Huang ◽  
Ulrich Engelke ◽  
Christopher Lueg
Keyword(s):  
Eye Gaze ◽  
Target Selection ◽  
Human Robot Interaction ◽  
Gaze Control ◽  
Robot Arm ◽  
Spatial Accuracy ◽  
Robot Interaction ◽  
The Third ◽  
Robot Arms ◽  
Chess Piece

Control of robot arms is often required in engineering and can be performed by using different methods. This study examined and symmetrically compared the use of a controller, eye gaze tracker and a combination thereof in a multimodal setup for control of a robot arm. Tasks of different complexities were defined and twenty participants completed an experiment using these interaction modalities to solve the tasks. More specifically, there were three tasks: the first was to navigate a chess piece from a square to another pre-specified square; the second was the same as the first task, but required more moves to complete; and the third task was to move multiple pieces to reach a solution to a pre-defined arrangement of the pieces. Further, while gaze control has the potential to be more intuitive than a hand controller, it suffers from limitations with regard to spatial accuracy and target selection. The multimodal setup aimed to mitigate the weaknesses of the eye gaze tracker, creating a superior system without simply relying on the controller. The experiment shows that the multimodal setup improves performance over the eye gaze tracker alone ( p < 0.05 ) and was competitive with the controller only setup, although did not outperform it ( p > 0.05 ).

Control of magnetic levitation system using recurrent neural network-based adaptive optimal backstepping strategy

2020 ◽  
Vol 42 (13) ◽  
pp. 2382-2395
Author(s):  
Armita Fatemimoghadam ◽  
Hamid Toshani ◽  
Mohammad Manthouri
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Optimization Problem ◽  
Closed Loop ◽  
Magnetic Levitation ◽  
Backstepping Control ◽  
Loop System ◽  
Closed Loop System ◽  
Levitation System ◽  
Magnetic Levitation System

In this paper, a novel approach is proposed for adjusting the position of a magnetic levitation system using projection recurrent neural network-based adaptive backstepping control (PRNN-ABC). The principles of designing magnetic levitation systems have widespread applications in the industry, including in the production of magnetic bearings and in maglev trains. Levitating a ball in space is carried out via the surrounding attracting or repelling magnetic forces. In such systems, the permissible range of the actuator is significant, especially in practical applications. In the proposed scheme, the procedure of designing the backstepping control laws based on the nonlinear state-space model is carried out first. Then, a constrained optimization problem is formed by defining a performance index and taking into account the control limits. To formulate the recurrent neural network (RNN), the optimization problem is first converted into a constrained quadratic programming (QP). Then, the dynamic model of the RNN is derived based on the Karush-Kuhn-Tucker (KKT) optimization conditions and the variational inequality theory. The convergence analysis of the neural network and the stability analysis of the closed-loop system are performed using the Lyapunov stability theory. The performance of the closed-loop system is assessed with respect to tracking error and control feasibility.

Control of Autonomous Robots Using the Principles of Neuromodulation

2013 ◽  
Author(s):  
Akimul Prince ◽  
Biswanath Samanta
Keyword(s):  
Neural Network ◽  
Autonomous Robots ◽  
Neuronal Model ◽  
Autonomous Robot ◽  
Human Robot Interaction ◽  
Robot Interaction ◽  
Control Approach ◽  
The Neural Network ◽  
Simple Neural Network ◽  
Interesting Behavior

The paper presents a control approach based on vertebrate neuromodulation and its implementation on an autonomous robot platform. A simple neural network is used to model the neuromodulatory function for generating context based behavioral responses to sensory signals. The neural network incorporates three types of neurons — cholinergic and noradrenergic (ACh/NE) neurons for attention focusing and action selection, dopaminergic (DA) neurons for curiosity-seeking, and serotonergic (5-HT) neurons for risk aversion behavior. The implementation of the neuronal model on a relatively simple autonomous robot illustrates its interesting behavior adapting to changes in the environment. The integration of neuromodulation based robots in the study of human-robot interaction would be worth considering in future.

Gestures Identification for Myoelectric Based Control of the Robotic Arm

2020 ◽  
Vol 22 (12) ◽  
Author(s):  
Adhau P ◽  
◽  
Kadwane S. G ◽  
Shital Telrandhe ◽  
Rajguru V. S ◽  
...  
Keyword(s):  
Neural Network ◽  
Human Body ◽  
Human Robot Interaction ◽  
Robotic Arm ◽  
Human Hand ◽  
Robot Interaction ◽  
The Neural Network

Human robot interaction have been ever the topic of research to research scholars owing to its importance to help humanity. Robust human interacting robot where commands from Electromyogram (EMG) signals is recently being investigated. This article involves study of motions a system that allows signals recorded directly from a human body and thereafter can be used for control of a small robotic arm. The various gestures are recognized by placing the electrodes or sensors on the human hand. These gestures are then identified by using neural network. The neural network will thus train the signals. The offline control of the arm is done by controlling the motors of the robotic arm.

scholarly journals HUMAN-ROBOT INTERACTION: LANGUAGE ACQUISITION WITH NEURAL NETWORK

2018 ◽  
Vol 11 (1) ◽  
pp. 75-84
Author(s):  
Alvin Rindra Fazrie
Keyword(s):  
Neural Network ◽  
Language Acquisition ◽  
Language Processing ◽  
Language Game ◽  
Human Robot Interaction ◽  
Communication Process ◽  
Robot Interaction ◽  
Echo State Networks ◽  
Stochastic Learning ◽  
Communicative Efficiency

ABSTRACT The paper gives an overview about the process between two language processing methods towards Human-robot interaction. In this paper, Echo State Networks and Stochastic-learning grammar are explored in order to get an idea about generating human’s natural language and the possibilities of integrating these methods to make the communication process between robot to robot or robot to human to be more natural in dialogic syntactic language game. The methods integration could give several benefits such as improving the communicative efficiency and producing the more natural communication sentence.   ABSTRAK Tulisan ini memberikan penjabaran mengenai dua metode pemrosesan bahasa alami pada interaksi Manusia dan Robot. Echo State Networks adalah salah satu arsitektur dari Jaringan Syaraf Tiruan yang berdasarkan prinsip Supervised Learning untuk Recurrent Neural Network, dieksplorasi bersama Stochastic-learning Grammar yaitu salah satu framework tata bahasa dengan konsep probabilistik yang bertujuan untuk mendapatkan ide bagaimana proses bahasa alami dari manusia dan kemungkinannya mengintegrasikan dua metode tersebut untuk membuat proses komunikasi antara robot dengan robot atau robot dengan manusia menjadi lebih natural dalam dialogic syntactic language game. Metode integrasi dapat memberikan beberapa keuntungan seperti meningkatkan komunikasi yang efisien dan dapat membuat konstruksi kalimat saat komunikasi menjadi lebih natural. How To Cite : Fazrie, A.R. (2018). HUMAN-ROBOT INTERACTION: LANGUAGE ACQUISITION WITH NEURAL NETWORK. Jurnal Teknik Informatika, 11(1), 75-84.  doi 10.15408/jti.v11i1.6093 Permalink/DOI: http://dx.doi.org/10.15408/jti.v11i1.6093 

Sign in / Sign up

Export Citation Format

Share Document