A Bayesian Deep Neural Network for Safe Visual Servoing in Human–Robot Interaction

Abstract

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.1

Deep Residual Networks and Bayesian Data Priors in the Survival Prediction and Classification

“…Bayesian neural networks can be used in the medical field for more accurate classification of cancer types and their subtypes [25], as well as for predicting drug-protein interactions, which in turn also play an important role in drug screening [26]. In terms of the safety of human-computer interaction, Bayesian neural networks have higher accuracy and better generalization ability to unknown data [27].…”

Prediction-Based Human-Robot Collaboration in Assembly Tasks Using a Learning from Demonstration Model

“…Similar capabilities should be adapted to the robotic assembly coworkers, which can attain essential information from observation [12] and play the corresponding role in line with cooperative humans. By involving humans in the robot workspace, a lot of difficulties are introduced for this field research, i.e., learning from demonstration [13,14], human intention recognition [15], human-aware motion planning [16], visual servoing [17], etc. With the rise of collaborative robots, a lot of research is being conducted on safety as well.…”

Densely Connected Neural Networks for Nonlinear Regression

“…To tackle this issue, they introduce the so-called residual regression model by replacing convolution and pooling layers into fully connected (FC) layers in ResNet. By maintaining the shortcut within residual blocks, residual regression enhances data flow in the neural network and has been applied in many fields, such as computational fluid dynamics [ 30 , 31 ], computer-aided geometric design [ 32 ], and safety control in visual serving applications [ 33 , 34 ]. Besides the localness of convolution, the independence of input features also requires the replacement of convolution layers in a neural network regression model.…”