Cargando…
A Bayesian Deep Neural Network for Safe Visual Servoing in Human–Robot Interaction
Safety is an important issue in human–robot interaction (HRI) applications. Various research works have focused on different levels of safety in HRI. If a human/obstacle is detected, a repulsive action can be taken to avoid the collision. Common repulsive actions include distance methods, potential...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8247479/ https://www.ncbi.nlm.nih.gov/pubmed/34222355 http://dx.doi.org/10.3389/frobt.2021.687031 |
_version_ | 1783716532676722688 |
---|---|
author | Shi, Lei Copot, Cosmin Vanlanduit, Steve |
author_facet | Shi, Lei Copot, Cosmin Vanlanduit, Steve |
author_sort | Shi, Lei |
collection | PubMed |
description | Safety is an important issue in human–robot interaction (HRI) applications. Various research works have focused on different levels of safety in HRI. If a human/obstacle is detected, a repulsive action can be taken to avoid the collision. Common repulsive actions include distance methods, potential field methods, and safety field methods. Approaches based on machine learning are less explored regarding the selection of the repulsive action. Few research works focus on the uncertainty of the data-based approaches and consider the efficiency of the executing task during collision avoidance. In this study, we describe a system that can avoid collision with human hands while the robot is executing an image-based visual servoing (IBVS) task. We use Monte Carlo dropout (MC dropout) to transform a deep neural network (DNN) to a Bayesian DNN, and learn the repulsive position for hand avoidance. The Bayesian DNN allows IBVS to converge faster than the opposite repulsive pose. Furthermore, it allows the robot to avoid undesired poses that the DNN cannot avoid. The experimental results show that Bayesian DNN has adequate accuracy and can generalize well on unseen data. The predictive interval coverage probability (PICP) of the predictions along x, y, and z directions are 0.84, 0.94, and 0.95, respectively. In the space which is unseen in the training data, the Bayesian DNN is also more robust than a DNN. We further implement the system on a UR10 robot, and test the robustness of the Bayesian DNN and the IBVS convergence speed. Results show that the Bayesian DNN can avoid the poses out of the reach range of the robot and it lets the IBVS task converge faster than the opposite repulsive pose. |
format | Online Article Text |
id | pubmed-8247479 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-82474792021-07-02 A Bayesian Deep Neural Network for Safe Visual Servoing in Human–Robot Interaction Shi, Lei Copot, Cosmin Vanlanduit, Steve Front Robot AI Robotics and AI Safety is an important issue in human–robot interaction (HRI) applications. Various research works have focused on different levels of safety in HRI. If a human/obstacle is detected, a repulsive action can be taken to avoid the collision. Common repulsive actions include distance methods, potential field methods, and safety field methods. Approaches based on machine learning are less explored regarding the selection of the repulsive action. Few research works focus on the uncertainty of the data-based approaches and consider the efficiency of the executing task during collision avoidance. In this study, we describe a system that can avoid collision with human hands while the robot is executing an image-based visual servoing (IBVS) task. We use Monte Carlo dropout (MC dropout) to transform a deep neural network (DNN) to a Bayesian DNN, and learn the repulsive position for hand avoidance. The Bayesian DNN allows IBVS to converge faster than the opposite repulsive pose. Furthermore, it allows the robot to avoid undesired poses that the DNN cannot avoid. The experimental results show that Bayesian DNN has adequate accuracy and can generalize well on unseen data. The predictive interval coverage probability (PICP) of the predictions along x, y, and z directions are 0.84, 0.94, and 0.95, respectively. In the space which is unseen in the training data, the Bayesian DNN is also more robust than a DNN. We further implement the system on a UR10 robot, and test the robustness of the Bayesian DNN and the IBVS convergence speed. Results show that the Bayesian DNN can avoid the poses out of the reach range of the robot and it lets the IBVS task converge faster than the opposite repulsive pose. Frontiers Media S.A. 2021-06-17 /pmc/articles/PMC8247479/ /pubmed/34222355 http://dx.doi.org/10.3389/frobt.2021.687031 Text en Copyright © 2021 Shi, Copot and Vanlanduit. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Robotics and AI Shi, Lei Copot, Cosmin Vanlanduit, Steve A Bayesian Deep Neural Network for Safe Visual Servoing in Human–Robot Interaction |
title | A Bayesian Deep Neural Network for Safe Visual Servoing in Human–Robot Interaction |
title_full | A Bayesian Deep Neural Network for Safe Visual Servoing in Human–Robot Interaction |
title_fullStr | A Bayesian Deep Neural Network for Safe Visual Servoing in Human–Robot Interaction |
title_full_unstemmed | A Bayesian Deep Neural Network for Safe Visual Servoing in Human–Robot Interaction |
title_short | A Bayesian Deep Neural Network for Safe Visual Servoing in Human–Robot Interaction |
title_sort | bayesian deep neural network for safe visual servoing in human–robot interaction |
topic | Robotics and AI |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8247479/ https://www.ncbi.nlm.nih.gov/pubmed/34222355 http://dx.doi.org/10.3389/frobt.2021.687031 |
work_keys_str_mv | AT shilei abayesiandeepneuralnetworkforsafevisualservoinginhumanrobotinteraction AT copotcosmin abayesiandeepneuralnetworkforsafevisualservoinginhumanrobotinteraction AT vanlanduitsteve abayesiandeepneuralnetworkforsafevisualservoinginhumanrobotinteraction AT shilei bayesiandeepneuralnetworkforsafevisualservoinginhumanrobotinteraction AT copotcosmin bayesiandeepneuralnetworkforsafevisualservoinginhumanrobotinteraction AT vanlanduitsteve bayesiandeepneuralnetworkforsafevisualservoinginhumanrobotinteraction |