A review on humanoid robots

Mahum, Rabbia; Butt, Faisal Shafique; Ayyub, Kashif; Islam, Seema; Nawaz, Marriam; Abdullah, Daud Vicary

doi:10.21833/ijaas.2017.02.015

Cited by 7 publications

(7 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Humans have the ability to move their hands almost 30 DOF [28]. Some of the humanoid robots that were built cannot hold the unknown objects from the environment like humans.…”

Section: Manipulation Tasksmentioning

confidence: 99%

“…The reason behind this is lack of learning ability to perceive and sense the new objects. Improvements were needed so that they could hold the things and sense them by touching [28]. Also learning from demonstration can be used to train soft robotic hands to perform dexterous manipulation tasks.…”

Section: Manipulation Tasksmentioning

confidence: 99%

“…There are different types of sensors used in humanoid robots. But [28] focused on specific on sensors used to grasp the objects means arm"s sensors. Sometimes arms are small so according to them, sensors must be small according to the joints.…”

Section: Sensing Behaviormentioning

confidence: 99%

“…For loop gesture of hand, there should be a measurement of every joint. [28] Highlighted that from the many approaches that were used for this [30] gave concept of using plastic potentiometer at ever finger"s joints. Another technique by [31] gave that linear potentiometers at wrist joint to calculate the angles of joints.…”

Section: Sensing Behaviormentioning

confidence: 99%

See 3 more Smart Citations

A review on humanoid robotics in healthcare

et al. 2018

View full text Add to dashboard Cite

Humanoid robots have evolved over the years and today it is in many different areas of applications, from homecare to social care and healthcare robotics. This paper deals with a brief overview of the current and potential applications of humanoid robotics in healthcare settings. We present a comprehensive contextualization of humanoid robots in healthcare by identifying and characterizing active research activities on humanoid robot that can work interactively and effectively with humans so as to fill some identified gaps in current healthcare deficiency.

show abstract

“…Humans have the ability to move their hands almost 30 DOF [28]. Some of the humanoid robots that were built cannot hold the unknown objects from the environment like humans.…”

Section: Manipulation Tasksmentioning

confidence: 99%

Section: Manipulation Tasksmentioning

confidence: 99%

Section: Sensing Behaviormentioning

confidence: 99%

Section: Sensing Behaviormentioning

confidence: 99%

See 2 more Smart Citations

A review on humanoid robotics in healthcare

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Year by year, the innovation of automation enables robot developments, and over decades of technology improvement, many humanoid robots have been developed for social use, such as WABOT by Waseda University, Asimo by Honda, Robonaut by NASA, Nadine by Nanyang Technological University and Actroid by Kokoro. Some of the humanoid robots have the same body structure as humans and can walk, hold objects, run and jump [3]. Some of the humanoid robots have human-like faces, and these robots can sing, speak languages and make facial expressions; one of them named Sophia developed by Hong Kong-based company Hanson Robotics, even become a Saudi Arabian citizen.…”

Section: Introductionmentioning

confidence: 99%

Emotion classification using a CNN_LSTM-based model for smooth emotional synchronization of the humanoid robot REN-XIN

Liu

Ren

2019

PLoS ONE

View full text Add to dashboard Cite

In this paper, we propose an Emotional Trigger System to impart an automatic emotion expression ability within the humanoid robot REN-XIN, in which the Emotional Trigger is an emotion classification model trained from our proposed Word Mover’s Distance(WMD) based algorithm. Due to the long time delay of the WMD-based Emotional Trigger System, we propose an enhanced Emotional Trigger System to enable a smooth interaction with the robot in which the Emotional Trigger is replaced by a conventional convolution neural network and a long short term memory network (CNN_LSTM)-based deep neural network. In our experiments, the CNN_LSTM based model only need 10 milliseconds or less to finish the classification without a decrease in accuracy, while the WMD-based model needed approximately 6-8 seconds to give a result. In this paper, the experiments are conducted based on the same sub-data sets of the Chinese emotional corpus(Ren_CECps) used in former WMD experiments: one comprises 50% data for training and 50% for testing(1v1 experiment), and the other comprises 80% data for training and 20% for testing(4v1 experiment). The experiments are conducted using WMD, CNN_LSTM, CNN and LSTM. The results show that CNN_LSTM obtains the best F1 score (0.35) in the 1v1 experiment and almost the same accuracy of F1 scores (0.366 vs 0.367) achieved by WMD in the 4v1 experiment. Finally, we present demonstration videos with the same scenario to show the performance of robot control driven by CNN_LSTM-based Emotional Trigger System and WMD-based Emotional Trigger System. To improve the comparison, total manual-control performance is also recorded.

show abstract