scholarly journals Online learning of low dimensional strategies for high-level push recovery in bipedal humanoid robots

2013 ◽  
Author(s):  
Seung-Joon Yi ◽  
Byoung-Tak Zhang ◽  
Dennis Hong ◽  
Daniel D. Lee
Keyword(s):  
Online Learning ◽  
Humanoid Robots ◽  
Push Recovery ◽  
Low Dimensional ◽  
High Level

Whole-Body Balancing Walk Controller for Position Controlled Humanoid Robots

2016 ◽  
Vol 13 (01) ◽  
pp. 1650011 ◽  
Author(s):  
Seung-Joon Yi ◽  
Byoung-Tak Zhang ◽  
Dennis Hong ◽  
Daniel D. Lee
Keyword(s):  
Hierarchical Control ◽  
Humanoid Robots ◽  
Whole Body ◽  
Appropriate Behavior ◽  
Low Level ◽  
Push Recovery ◽  
Hierarchical Control Architecture ◽  
High Level ◽  
Experimental Trials ◽  
Decision Boundaries

Bipedal humanoid robots are intrinsically unstable against unforeseen perturbations. Conventional zero moment point (ZMP)-based locomotion algorithms can reject perturbations by incorporating sensory feedback, but they are less effective than the dynamic full body behaviors humans exhibit when pushed. Recently, a number of biomechanically motivated push recovery behaviors have been proposed that can handle larger perturbations. However, these methods are based upon simplified and transparent dynamics of the robot, which makes it suboptimal to implement on common humanoid robots with local position-based controllers. To address this issue, we propose a hierarchical control architecture. Three low-level push recovery controllers are implemented for position controlled humanoid robots that replicate human recovery behaviors. These low-level controllers are integrated with a ZMP-based walk controller that is capable of generating reactive step motions. The high-level controller constructs empirical decision boundaries to choose the appropriate behavior based upon trajectory information gathered during experimental trials. Our approach is evaluated in physically realistic simulations and on a commercially available small humanoid robot.

Investigation of Online Learning Satisfaction During COVID 19: In Relation to Academic Achievement

2020 ◽  
Vol 1 (1) ◽  
Author(s):  
Abdul Basith ◽  
Rosmaiyadi Rosmaiyadi ◽  
Susan Neni Triani ◽  
Fitri Fitri
Keyword(s):  
Academic Achievement ◽  
Online Learning ◽  
Random Sampling ◽  
Sampling Technique ◽  
Simple Random Sampling ◽  
Research Data ◽  
Student Academic Achievement ◽  
Learning Satisfaction ◽  
High Level ◽  
The Relationship

The aim of this research is; 1) investigating the level of online learning satisfaction among students during COVID 19; 2) analyzing the influence of differences in gender, years of study, major in determining online learning satisfaction among students during COVID 19; 3) to analyze the relationship between online learning satisfaction and student academic achievement during COVID 19. The population was 656 students at STKIP Singkawang, and then a sample of 357 students (87 males and 270 females) was taken using a simple random sampling technique. The instrument in this study was adapted from Aman's Satisfaction instrument, which was then used to collect research data. Data analysis using SPSS with descriptive statistical techniques, MANOVA, and correlation. The results showed that online learning satisfaction was at a high level, meaning that students were satisfied with the online learning that had been implemented. The major differences have a significant effect on determining online learning satisfaction. Intercorrelation shows that there is a significant relationship on each indicator of online learning satisfaction with academic achievement, meaning that the higher the satisfaction felt by students in online learning, the student's academic achievement will increase.

scholarly journals Perceptions of English Education Program Students Towards The Profesionalism of English Education Lecturers in Online Learning at IAIN Parepare

2020 ◽  
Vol 2 (2) ◽  
pp. 70-76
Author(s):  
Mujahidah ◽  
Nur Afiah ◽  
Syaiful
Keyword(s):  
Online Learning ◽  
Data Analysis ◽  
Quantitative Study ◽  
Education Program ◽  
Online Teaching ◽  
English Education ◽  
Teaching Skills ◽  
High Level ◽  
Survey Approach

Perception can be interpreted as a process of giving meaning to a phenomenon, event or object. professionalism is interpreted as a professional trait. Those traits are mastering the Science in their field and have high skills in carrying out their duties. This Study aimed to describe the students' perceptions of professionalism lecturer English Education Program, State Islamic Institute of Parepare. To achieve this goal a questionnaire was distributed to 50 students (40% of the population). This Research is a descriptive quantitative study with a survey approach. The data processed using simple tabulation techniques and the data qualitatively interpreted. There are five aspects of the professionalism observed, namely: the ability to speak English, online teaching skills, insights, timeliness and using of online learning application. By the results of data analysis found that, the lecturers of English Education Program, State Islamic Institute of Parepare has a high level of professionalism.

The Analysis of Students Mathematic Problem Solving Ability During Online Learning

2021 ◽  
Vol 6 (1) ◽  
pp. 62-68
Author(s):  
M. Arif Wahyu Daroini ◽  
Tri Novita Irawati ◽  
Sholahudin Al Ayubi
Keyword(s):  
Online Learning ◽  
Problem Solving ◽  
Mathematical Problem ◽  
Mathematical Problem Solving ◽  
Ability Level ◽  
Maximum Score ◽  
Low Level ◽  
Medium Level ◽  
Good For ◽  
High Level

This study aims to determine students' mathematical problem solving abilities based on their high, medium and low level of ability in solving the problem. This type of research is descriptive qualitative. The data collecting method that use are observation, test, and interview. The results showed that the problem-solving ability of high-level subjects reached an average of 75%, the problem-solving abilities of medium-level subjects reached an average of 67%, the problem-solving abilities of low-level subjects reached an average of 67%, out of a maximum score of 100. The result of interview, ability level high, medium, and low, students are capable and good even though it does not reach 100%. So, it can be concluded that high, medium, and low level abilities are good for going through the problem solving ability indicator.  Keywords: problem solving, online learning  

Authentication of Educational Practices in Online Learning

2021 ◽  
pp. 52-66
Author(s):  
O.V. Lukyanov ◽  
◽  
I.A. Dubinina ◽  
E.V. Bredun ◽  
◽  
...  
Keyword(s):  
Online Learning ◽  
Online Education ◽  
Learning Environment ◽  
Individual Learning ◽  
Educational Process ◽  
Educational Practices ◽  
Abstract Thinking ◽  
Field Independence ◽  
High Coefficient ◽  
High Level

The aim of online learning is to help forward the individualization of educational practices and self-determination of a student. From the technological point of view, it is supposed to reduce the costs on the teacher’s presence in educational process (it is not a teacher but a plat-form which holds the knowledge) and to increase investments in the student’s presence (a student completes the given knowledge with his own senses, motives, values and creativity). An important phase of educational process is rating. According to the trend of “high technolo-gies” (technologies that minimize the human presence in management) we may say that there is also a trend to increase the level of rating. In online learning environment we rate not only the results and actions of a student, but also the level of his abilities or competence and the means of rating authenticity. The article discusses the data received on using the “Self-attestation practice” online course. It is a means of final assessment for students who complete the BA in psychology. By the way of variance analysis, we verified the hypothesis that the high level of abstract thinking, high coefficient of categorization, high level of creativity, field independence and reflexivity on cognitive styles are favor for intellectual productivity in scientific, research and creative areas. A measured set of level characteristics for intellectual products is transformed into a com-plex of observed language qualities. The high level of abstract thinking is demonstrated in speech coherence, in discourse consistency. The high coefficient of categorization is demon-strated in the ability to interpret texts into different languages and scales. High creativity level can be seen in making preference for difficult, challenging creative tasks. Field independence and reflexivity is demonstrated in the ability to make an individual educational track. These characteristics are markers of successful study, including online education. They allow us esti-mating each student’s involvement into professional studies and defining the levels of intellectual success, predicting the model of individual learning environment (individual learning track).

Collaborative Autonomy between High-level Behaviors and Human Operators for Remote Manipulation Tasks using Different Humanoid Robots

2016 ◽  
Vol 34 (2) ◽  
pp. 333-358 ◽  
Author(s):  
Alberto Romay ◽  
Stefan Kohlbrecher ◽  
Alexander Stumpf ◽  
Oskar von Stryk ◽  
Spyros Maniatopoulos ◽  
...  
Keyword(s):  
Humanoid Robots ◽  
Remote Manipulation ◽  
Human Operators ◽  
High Level ◽  
Collaborative Autonomy

IMPROVEMENT OF IMAGE CLASSIFICATION USING WAVELET COEFFICIENTS WITH STRUCTURED-BASED NEURAL NETWORK

2008 ◽  
Vol 18 (03) ◽  
pp. 195-205 ◽  
Author(s):  
WEIBAO ZOU ◽  
ZHERU CHI ◽  
KING CHUEN LO
Keyword(s):  
Neural Network ◽  
Wavelet Analysis ◽  
Image Classification ◽  
Dimensional Space ◽  
Training Data ◽  
Wavelet Coefficients ◽  
Classification Rate ◽  
Data Set ◽  
Low Dimensional ◽  
High Level

Image classification is a challenging problem in organizing a large image database. However, an effective method for such an objective is still under investigation. A method based on wavelet analysis to extract features for image classification is presented in this paper. After an image is decomposed by wavelet, the statistics of its features can be obtained by the distribution of histograms of wavelet coefficients, which are respectively projected onto two orthogonal axes, i.e., x and y directions. Therefore, the nodes of tree representation of images can be represented by the distribution. The high level features are described in low dimensional space including 16 attributes so that the computational complexity is significantly decreased. 2800 images derived from seven categories are used in experiments. Half of the images were used for training neural network and the other images used for testing. The features extracted by wavelet analysis and the conventional features are used in the experiments to prove the efficacy of the proposed method. The classification rate on the training data set with wavelet analysis is up to 91%, and the classification rate on the testing data set reaches 89%. Experimental results show that our proposed approach for image classification is more effective.

scholarly journals Transportable open-source application program interface and user interface for generic humanoids: TOUGH

2020 ◽  
Vol 17 (3) ◽  
pp. 172988142092160
Author(s):  
Vinayak Jagtap ◽  
Shlok Agarwal ◽  
Ameya Wagh ◽  
Michael Gennert
Keyword(s):  
User Interface ◽  
Open Source ◽  
Humanoid Robots ◽  
Application Program Interface ◽  
Sensors And Actuators ◽  
Seamless Integration ◽  
Application Program ◽  
Diverse Field ◽  
High Level ◽  
Program Interface

Humanoid robotics is a complex and highly diverse field. Humanoid robots may have dozens of sensors and actuators that together realize complicated behaviors. Adding to the complexity is that each type of humanoid has unique application program interfaces, thus software written for one humanoid does not easily transport to others. This article introduces the transportable open-source application program interface and user interface for generic humanoids, a set of application program interfaces that simplifies the programming and operation of diverse humanoid robots. These application program interfaces allow for quick implementation of complex tasks and high-level controllers. Transportable open-source application program interface and user interface for generic humanoids has been developed for, and tested on, Boston Dynamics’ Atlas V5 and NASA’s Valkyrie R5 robots. It has proved successful for experiments on both robots in simulation and hardware, demonstrating the seamless integration of manipulation, perception, and task planning. To encourage the rapid adoption of transportable open-source application program interface and user interface for generic humanoids for education and research, the software is available as Docker images, which enable quick setup of multiuser simulation environments.

The relationship between social presence and cognitive load

2019 ◽  
Vol 16 (2) ◽  
pp. 172-182
Author(s):  
Jamie Costley
Keyword(s):  
Online Learning ◽  
Cognitive Load ◽  
Learning Environments ◽  
Social Presence ◽  
Online Learning Environments ◽  
Content Type ◽  
Germane Cognitive Load ◽  
High Level ◽  
The Relationship ◽  
Spearman’S Correlation

Purpose As online learning has become more prevalent, how learners interact with each other in those learning environments has become more salient. To develop effective levels of interaction, students must feel comfortable to express their ideas and views. For this reason, this paper aims to look at how individual students’ levels of social presence affect germane cognitive load. Germane cognitive load is the amount that students are able to construct schema and can be seen as analogous to learning. Design/methodology/approach This study looks at the results of survey data (n = 433) that investigate the relationship between social presence and germane cognitive load. The students were surveyed from the Open Cyber University of Korea in the fall semester of 2018. Findings The present study found a statistically significant positive relationship between social presence and germane cognitive load. The study found a Spearman’s correlation coefficient of 0.595. Furthermore, the sample was divided into a high, medium and low grouping of social presence. Among these groupings, the high level social presence had the highest level of germane cognitive load, and the low level social presence had the lowest level of germane cognitive load. Originality/value This result shows the importance and value of developing levels of social presence in online environments. Some research has shown relationships between student interaction and learning, but the present study looks directly at social presence and germane cognitive load. From this research, the authors can see the value of encouraging higher levels of social interaction in online learning environments.

scholarly journals A Hierarchical Behavioral Dynamic Approach for Naturally Adaptive Human-Agent Pick-and-Place Interactions

Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-16
Author(s):  
Maurice Lamb ◽  
Patrick Nalepka ◽  
Rachel W. Kallen ◽  
Tamara Lorenz ◽  
Steven J. Harrison ◽  
...  
Keyword(s):  
Human Robot Interaction ◽  
Robot Interaction ◽  
Agent Interactions ◽  
Human Agent ◽  
Dinner Table ◽  
Pick And Place ◽  
Low Dimensional ◽  
High Level ◽  
Near Future ◽  
Simple Interaction

Interactive or collaborative pick-and-place tasks occur during all kinds of daily activities, for example, when two or more individuals pass plates, glasses, and utensils back and forth between each other when setting a dinner table or loading a dishwasher together. In the near future, participation in these collaborative pick-and-place tasks could also include robotic assistants. However, for human-machine and human-robot interactions, interactive pick-and-place tasks present a unique set of challenges. A key challenge is that high-level task-representational algorithms and preplanned action or motor programs quickly become intractable, even for simple interaction scenarios. Here we address this challenge by introducing a bioinspired behavioral dynamic model of free-flowing cooperative pick-and-place behaviors based on low-dimensional dynamical movement primitives and nonlinear action selection functions. Further, we demonstrate that this model can be successfully implemented as an artificial agent control architecture to produce effective and robust human-like behavior during human-agent interactions. Participants were unable to explicitly detect whether they were working with an artificial (model controlled) agent or another human-coactor, further illustrating the potential effectiveness of the proposed modeling approach for developing systems of robust real/embodied human-robot interaction more generally.

Sign in / Sign up

Export Citation Format

Share Document