Human–Robot Interaction and Cooperation Through People Detection and Gesture Recognition

Pereira, Flávio Garcia; Vassallo, Raquel Frizera; Salles, Evandro Ottoni Teatini

doi:10.1007/s40313-013-0040-3

Cited by 20 publications

(11 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Human postures by robots can be broadly perceived as contacting postures (requiring sensors for touching the human body) and non-contacting postures (not requiring sensors that contact the human body). In the non-contacting category, human postures are mainly perceived by sensors such as Red-Green-Blue cameras [9], infrared, or laser sensors [10]. In one human-robot interaction and cooperation system, human postures were acquired by a depth camera [11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Standing-Posture Recognition in Human–Robot Collaboration Based on Deep Learning and the Dempster–Shafer Evidence Theory

Guan

Liu

Cai

et al. 2020

Sensors

View full text Add to dashboard Cite

During human–robot collaborations (HRC), robot systems must accurately perceive the actions and intentions of humans. The present study proposes the classification of standing postures from standing-pressure images, by which a robot system can predict the intended actions of human workers in an HRC environment. To this end, it explores deep learning based on standing-posture recognition and a multi-recognition algorithm fusion method for HRC. To acquire the pressure-distribution data, ten experimental participants stood on a pressure-sensing floor embedded with thin-film pressure sensors. The pressure data of nine standing postures were obtained from each participant. The human standing postures were discriminated by seven classification algorithms. The results of the best three algorithms were fused using the Dempster–Shafer evidence theory to improve the accuracy and robustness. In a cross-validation test, the best method achieved an average accuracy of 99.96%. The convolutional neural network classifier and data-fusion algorithm can feasibly classify the standing postures of human workers.

show abstract

Section: Introductionmentioning

confidence: 99%

Standing-Posture Recognition in Human–Robot Collaboration Based on Deep Learning and the Dempster–Shafer Evidence Theory

Guan

Liu

Cai

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…As novas possibilidades de serviços, lazer, transporte, dentre outras, que eles podem oferecer, têm chamado a atenção das pessoas para os robôs autônomos e, desse modo, vemos aumentar a coexistência de tais sistemas com os seres humanos a cada dia. São várias as tarefas que os robôs podem executar para ajudar as pessoas ou cooperar com elas, por exemplo, robôs de serviço podem realizar tarefas domésticas como a limpeza de casas, guias em museus, atendimento em recepções e transporte de cargas (Tiddi et al, 2020;Pereira et al, 2013).…”

Section: Introductionunclassified

Desenvolvimento de um robˆo autˆonomo em cen´ario educativo

Filho

Júnior

Cordeiro

et al. 2020

Anais Do Congresso Brasileiro De Automática 2020

View full text Add to dashboard Cite

A rob´otica, como recurso tecnol´ogico para a educa¸c˜ao, propicia a demonstra¸c˜ao pr´atica de conceitos te´oricos que integram diversas ´areas do conhecimento. De forma criativa e l´udica, os robˆos podem ser usados em ambientes formais de aprendizagem e em espa¸cos cient´ıficos interativos para facilitar o aprendizado e despertar o interesse de estudantes de diferentes n´ıveis de educa¸c˜ao. Neste artigo ´e apresentado o desenvolvimento de um robˆo autˆonomo de pequeno porte capaz de navegar em um cen´ario dinˆamico, interpretando alguns elementos da sinaliza¸c˜ao de trˆansito, e de realizar as a¸c˜oes de seguir a pista corretamente, detectar obst´aculos e obedecer a um sem´aforo. O robˆo autˆonomo foi desenvolvido utilizando um computador Raspberry Pi, sensores e outros elementos que possibilitam a execu¸c˜ao das tarefas que o robˆo precisa realizar no cen´ario. Experimentos foram realizados com os m´odulos do robˆo e os resultados indicam o potencial dos algoritmos na busca por um sistema que possibilite demonstra¸c˜oes com um funcionamento adequado e similares a um cen´ario real.

show abstract

“…Humans usually use motions or gestures in many cases, like pointing at objects and while speaking. Hence, many researchers are currently working on motions for interacting with robots [6][7][8][9][10]. The aim is to construct natural and intuitive interaction with minor training in real time.…”

Section: Introductionmentioning

confidence: 99%

Gesture imitation and recognition using Kinect sensor and extreme learning machines

Yavşan

Uçar

2016

Measurement

View full text Add to dashboard Cite

This study presents a framework that recognizes and imitates human upper-body motions in real time. The framework consists of two parts. In the first part, a transformation algorithm is applied to 3D human motion data captured by a Kinect. The data are then converted into the robot's joint angles by the algorithm. The human upper-body motions are successfully imitated by the NAO humanoid robot in real time. In the second part, the human action recognition algorithm is implemented for upper-body gestures. A human action dataset is also created for the upper-body movements. Each action is performed 10 times by twenty-four users. The collected joint angles are divided into six action classes. Extreme Learning Machines (ELMs) are used to classify the human actions. Additionally, the Feed-Forward Neural Networks (FNNs) and K-Nearest Neighbor (K-NN) classifiers are used for comparison. According to the comparative results, ELMs produce a good human action recognition performance.

show abstract

Human–Robot Interaction and Cooperation Through People Detection and Gesture Recognition

Cited by 20 publications

References 18 publications

Standing-Posture Recognition in Human–Robot Collaboration Based on Deep Learning and the Dempster–Shafer Evidence Theory

Standing-Posture Recognition in Human–Robot Collaboration Based on Deep Learning and the Dempster–Shafer Evidence Theory

Desenvolvimento de um robˆo autˆonomo em cen´ario educativo

Gesture imitation and recognition using Kinect sensor and extreme learning machines

Contact Info

Product

Resources

About