scholarly journals Real-Time Motion Control of a Humanoid Robot Using Deep Learning

2021 ◽  
Vol 2115 (1) ◽  
pp. 012007
Author(s):  
A S Faraz Ahmed ◽  
V Sudharsan ◽  
Arockia Selvakumar Arockia Doss
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Humanoid Robot ◽  
Research Work ◽  
Upper Body ◽  
Personal Assistance ◽  
Time Motion ◽  
Novel Method ◽  
Cost Efficient ◽  
Work Done

Abstract This paper discusses the research work done for controlling the humanoid robot manually using deep learning. For teaching, personal assistance, search and rescue humanoid robot are used. Controlling manually makes it to do any task without any explicitly programming. Existing technique for manually controlling the humanoid are heavily dependent on hardware and they are not cost efficient. This paper proposes a novel method for controlling the humanoid using a 2D camera. The image from the 2D camera is processed and skeleton of the human body is captured using deep learning. Then the skeleton is used to control the actuators present in the humanoid robot using image classifier and ROS. As a proof of concept the upper body of the humanoid robot is controlled in real time using this method.

scholarly journals Application of deep learning in automatic detection of technical and tactical indicators of table tennis

PLoS ONE ◽  
2021 ◽  
Vol 16 (3) ◽  
pp. e0245259
Author(s):  
Fufeng Qiao
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Short Term Memory ◽  
Detection System ◽  
Minimum Mean Square Error ◽  
Automatic Detection ◽  
Table Tennis ◽  
Time Dynamic ◽  
Time Motion ◽  
Automatic Detection System

A DCNN-LSTM (Deep Convolutional Neural Network-Long Short Term Memory) model is proposed to recognize and track table tennis’s real-time trajectory in complex environments, aiming to help the audiences understand competition details and provide a reference for training enthusiasts using computers. Real-time motion features are extracted via deep reinforcement networks. DCNN tracks the recognized objects, and the LSTM algorithm predicts the ball’s trajectory. The model is tested on a self-built video dataset and existing systems and compared with other algorithms to verify its effectiveness. Finally, an overall tactical detection system is built to measure ball rotation and predict ball trajectory. Results demonstrate that in feature extraction, the Deep Deterministic Policy Gradient (DDPG) algorithm has the best performance, with a maximum accuracy rate of 89% and a minimum mean square error of 0.2475. The accuracy of target tracking effect and trajectory prediction is as high as 90%. Compared with traditional methods, the performance of the DCNN-LSTM model based on deep learning is improved by 23.17%. The implemented automatic detection system of table tennis tactical indicators can deal with the problems of table tennis tracking and rotation measurement. It can provide a theoretical foundation and practical value for related research in real-time dynamic detection of balls.

Ransomware Traffic Classification Using Deep Learning Models

2020 ◽  
Vol 12 (1) ◽  
pp. 1-11
Author(s):  
Arivudainambi D. ◽  
Varun Kumar K.A. ◽  
Vinoth Kumar R. ◽  
Visu P.
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Network Traffic ◽  
Classification Model ◽  
Traffic Classification ◽  
Learning Models ◽  
Learning Methods ◽  
Novel Method

Ransomware is a malware which affects the systems data with modern encryption techniques, and the data is recovered once a ransom amount is paid. In this research, the authors show how ransomware propagates and infects devices. Live traffic classifications of ransomware have been meticulously analyzed. Further, a novel method for the classification of ransomware traffic by using deep learning methods is presented. Based on classification, the detection of ransomware is approached with the characteristics of the network traffic and its communications. In more detail, the behavior of popular ransomware, Crypto Wall, is analyzed and based on this knowledge, a real-time ransomware live traffic classification model is proposed.

Resource Management in Real Time Distributed System with Security Constraints

2012 ◽  
pp. 230-251
Author(s):  
Sarsij Tripathi ◽  
Rama Shankar Yadav ◽  
Ranvijay ◽  
Rajib L. Jana
Keyword(s):  
Resource Management ◽  
Load Balancing ◽  
Real Time ◽  
Distributed System ◽  
Research Work ◽  
Tracking Systems ◽  
Global Village ◽  
Future Directions ◽  
The World ◽  
Work Done

The world has become a global village. Today applications are developed which require sharing of resources dispersed geographically to fulfill the need of the users. In most cases applications turn out to be time bound thus leading to Real Time Distributed System (RTDS). Online Banking, Online Multimedia Applications, Real Time Databases, and Missile tracking systems are some examples of these types of applications. These applications face many challenges in the present scenario particularly in resource management, load balancing, security, and deadlock. The heterogeneous nature of the system exacerbates the challenges. This paper provides a widespread survey of research work reported in RTDS. This review has covered the work done in the field of resource management, load balancing, deadlock, and security. The challenges involved in tackling these issues is presented and future directions are discussed.

Resource Management in Real Time Distributed System with Security Constraints

2011 ◽  
Vol 2 (2) ◽  
pp. 38-58 ◽  
Author(s):  
Sarsij Tripathi ◽  
Rama Shankar Yadav ◽  
Ranvijay ◽  
Rajib L. Jana
Keyword(s):  
Resource Management ◽  
Load Balancing ◽  
Real Time ◽  
Distributed System ◽  
Research Work ◽  
Global Village ◽  
Future Directions ◽  
The World ◽  
Heterogeneous Nature ◽  
Work Done

The world has become a global village. Today applications are developed which require sharing of resources dispersed geographically to fulfill the need of the users. In most cases applications turn out to be time bound thus leading to Real Time Distributed System (RTDS). Online Banking, Online Multimedia Applications, Real Time Databases, and Missile tracking systems are some examples of these types of applications. These applications face many challenges in the present scenario particularly in resource management, load balancing, security, and deadlock. The heterogeneous nature of the system exacerbates the challenges. This paper provides a widespread survey of research work reported in RTDS. This review has covered the work done in the field of resource management, load balancing, deadlock, and security. The challenges involved in tackling these issues is presented and future directions are discussed.

scholarly journals Survey on Neural Network Architectures with Deep Learning

2020 ◽  
Vol 2 (3) ◽  
pp. 186-194
Author(s):  
Smys S. ◽  
Joy Iong Zong Chen ◽  
Subarna Shakya
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Visual Recognition ◽  
Research Work ◽  
Network Architectures ◽  
Significant Performance ◽  
Recent Trends ◽  
Cost Efficient ◽  
The Cost ◽  
Learning Architectures

In the present research era, machine learning is an important and unavoidable zone where it provides better solutions to various domains. In particular deep learning is one of the cost efficient, effective supervised learning model, which can be applied to various complicated issues. Since deep learning has various illustrative features and it doesn’t depend on any limited learning methods which helps to obtain better solutions. As deep learning has significant performance and advancements it is widely used in various applications like image classification, face recognition, visual recognition, language processing, speech recognition, object detection and various science, business analysis, etc., This survey work mainly provides an insight about deep learning through an intensive analysis of deep learning architectures and its characteristics along with its limitations. Also, this research work analyses recent trends in deep learning through various literatures to explore the present evolution in deep learning models.

scholarly journals Real-time full body motion imitation on the COMAN humanoid robot

Robotica ◽  
2014 ◽  
Vol 33 (5) ◽  
pp. 1049-1061 ◽  
Author(s):  
Andrej Gams ◽  
Jesse van den Kieboom ◽  
Florin Dzeladini ◽  
Aleš Ude ◽  
Auke Jan Ijspeert
Keyword(s):  
Real Time ◽  
Humanoid Robot ◽  
Center Of Mass ◽  
Stability Control ◽  
Body Motion ◽  
Support Vector ◽  
Time Motion ◽  
Vector Machines ◽  
On Line ◽  
Full Body

SUMMARYOn-line full body imitation with a humanoid robot standing on its own two feet requires simultaneously maintaining the balance and imitating the motion of the demonstrator. In this paper we present a method that allows real-time motion imitation while maintaining stability, based on prioritized task control. We also describe a method of modified prioritized kinematic control that constrains the imitated motion to preserve stability only when the robot would tip over, but does not alter the motions otherwise. To cope with the passive compliance of the robot, we show how to model the estimation of the center of mass of the robot using support vector machines. In the paper we give detailed description of all steps of the algorithm, essentially providing a tutorial on the implementation of kinematic stability control. We present the results on a child-sized humanoid robot called Compliant Humanoid Platform or COMAN. Our implementation shows reactive and stable on-line motion imitation of the humanoid robot.

scholarly journals A Real-Time Upper-Body Robot Imitation System

2019 ◽  
Vol 2 (1) ◽  
pp. 49 ◽  
Author(s):  
Zhijun Zhang ◽  
Yaru Niu ◽  
Lingdong Kong ◽  
Shuyang Lin ◽  
Hao Wang
Keyword(s):  
Real Time ◽  
Humanoid Robot ◽  
Computational Cost ◽  
Human Head ◽  
Inverse Kinematic ◽  
Recognition Algorithm ◽  
Upper Body ◽  
State Recognition ◽  
Hand Motion ◽  
Arm Motions

An upper-body robot imitation (UBRI) system is proposed and developed to enable the human upper body imitation by a humanoid robot in real time. To achieve the imitation of arm motions, a geometry-based analytical method is presented and applied to extracting the joint angles of the human and mapping to the robot. Comparing to the traditional numerical methods of inverse kinematic computations, the geometrical analysis method generates a lower computational cost and maintains good imitation similarity. To map the human head motions to the head of the humanoid robot, a face tracking algorithm is employed to recognize the human face and track the human head poses in real time. A hand extraction and hand state recognition algorithm is proposed to achieve the hand motion mapping. At last, the completion rate and similarity evaluation experiments are conducted to verify the effectiveness of the proposed UBRI system.

Motion Control System Design of a Humanoid Robot Based on Stereo Vision

2011 ◽  
Vol 55-57 ◽  
pp. 877-880
Author(s):  
Qin Jun Du ◽  
Chao Sun ◽  
Xing Guo Huang
Keyword(s):  
Control System ◽  
Real Time ◽  
Motion Control ◽  
Visual Information ◽  
Humanoid Robot ◽  
Vision System ◽  
The Body ◽  
Real Time Control ◽  
Motion Control System ◽  
Time Motion

Vision is an important means of the humanoid robot to get external environmental information; vision system is an important part of humanoid robot. The system of a humanoid robot with the functions of visual perception and object manipulation is very complex because the body of the humanoid robot possesses many joint units and sensors. Two computers linked by Memolink communication unit is adopted to meet the needs of real time motion control and visual information processing tasks. The motion control system included coordination control computer, the distributed DSP joint controllers, DC motor drivers and sensors. Linux and real-time RT-Linux OS are used as the operating system to achieve the real-time control capability.

Sign in / Sign up

Export Citation Format

Share Document