scholarly journals Uncertainty-Aware Knowledge Distillation for Collision Identification of Collaborative Robots

Sensors ◽  
2021 ◽  
Vol 21 (19) ◽  
pp. 6674
Author(s):  
Wookyong Kwon ◽  
Yongsik Jin ◽  
Sang Jun Lee
Keyword(s):  
Neural Network ◽  
Collision Detection ◽  
Deep Neural Network ◽  
Human Robot Interaction ◽  
Learning Method ◽  
Robot Interaction ◽  
Collaborative Robots ◽  
Knowledge Distillation ◽  
Articulated Robots ◽  
External Forces

Human-robot interaction has received a lot of attention as collaborative robots became widely utilized in many industrial fields. Among techniques for human-robot interaction, collision identification is an indispensable element in collaborative robots to prevent fatal accidents. This paper proposes a deep learning method for identifying external collisions in 6-DoF articulated robots. The proposed method expands the idea of CollisionNet, which was previously proposed for collision detection, to identify the locations of external forces. The key contribution of this paper is uncertainty-aware knowledge distillation for improving the accuracy of a deep neural network. Sample-level uncertainties are estimated from a teacher network, and larger penalties are imposed for uncertain samples during the training of a student network. Experiments demonstrate that the proposed method is effective for improving the performance of collision identification.

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

2021 ◽  
Vol 8 ◽  
Author(s):  
Lei Shi ◽  
Cosmin Copot ◽  
Steve Vanlanduit
Keyword(s):  
Neural Network ◽  
Visual Servoing ◽  
Deep Neural Network ◽  
Human Robot Interaction ◽  
Training Data ◽  
Robot Interaction ◽  
Field Methods ◽  
Distance Methods ◽  
Unseen Data ◽  
Interval Coverage

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

Human-robot interaction detection: a wrist and base force/torque sensors approach

Robotica ◽  
2006 ◽  
Vol 24 (4) ◽  
pp. 419-427 ◽  
Author(s):  
Shujun Lu ◽  
Jae H. Chung ◽  
Stevens A. Velinsky
Keyword(s):  
Neural Network ◽  
Collision Detection ◽  
Human Robot Interaction ◽  
Impact Model ◽  
Network Approach ◽  
Robot Interaction ◽  
Neural Network Approach ◽  
Identification Scheme ◽  
Interaction Detection ◽  
Detection And Identification

In this paper, a collision detection and identification method of a manipulator, using wrist and base force/torque sensors, is presented. An impact model is used to simulate the interaction between the manipulator and the human or environment. A neural network approach and a model based method are developed to detect the collision forces and disturbance torques on the joints of the manipulator. The experimental results illustrate the validity of the developed collision detection and identification scheme.

Soft magnetic skin for super-resolution tactile sensing with force self-decoupling

2021 ◽  
Vol 6 (51) ◽  
pp. eabc8801
Author(s):  
Youcan Yan ◽  
Zhe Hu ◽  
Zhengbao Yang ◽  
Wenzhen Yuan ◽  
Chaoyang Song ◽  
...  
Keyword(s):  
External Disturbance ◽  
Super Resolution ◽  
Tactile Sensor ◽  
Human Robot Interaction ◽  
Tactile Sensors ◽  
Dexterous Manipulation ◽  
Robot Interaction ◽  
Flexible Film ◽  
Challenging Tasks ◽  
External Forces

Human skin can sense subtle changes of both normal and shear forces (i.e., self-decoupled) and perceive stimuli with finer resolution than the average spacing between mechanoreceptors (i.e., super-resolved). By contrast, existing tactile sensors for robotic applications are inferior, lacking accurate force decoupling and proper spatial resolution at the same time. Here, we present a soft tactile sensor with self-decoupling and super-resolution abilities by designing a sinusoidally magnetized flexible film (with the thickness ~0.5 millimeters), whose deformation can be detected by a Hall sensor according to the change of magnetic flux densities under external forces. The sensor can accurately measure the normal force and the shear force (demonstrated in one dimension) with a single unit and achieve a 60-fold super-resolved accuracy enhanced by deep learning. By mounting our sensor at the fingertip of a robotic gripper, we show that robots can accomplish challenging tasks such as stably grasping fragile objects under external disturbance and threading a needle via teleoperation. This research provides new insight into tactile sensor design and could be beneficial to various applications in robotics field, such as adaptive grasping, dexterous manipulation, and human-robot interaction.

Control of Autonomous Robots Using the Principles of Neuromodulation

2013 ◽  
Author(s):  
Akimul Prince ◽  
Biswanath Samanta
Keyword(s):  
Neural Network ◽  
Autonomous Robots ◽  
Neuronal Model ◽  
Autonomous Robot ◽  
Human Robot Interaction ◽  
Robot Interaction ◽  
Control Approach ◽  
The Neural Network ◽  
Simple Neural Network ◽  
Interesting Behavior

The paper presents a control approach based on vertebrate neuromodulation and its implementation on an autonomous robot platform. A simple neural network is used to model the neuromodulatory function for generating context based behavioral responses to sensory signals. The neural network incorporates three types of neurons — cholinergic and noradrenergic (ACh/NE) neurons for attention focusing and action selection, dopaminergic (DA) neurons for curiosity-seeking, and serotonergic (5-HT) neurons for risk aversion behavior. The implementation of the neuronal model on a relatively simple autonomous robot illustrates its interesting behavior adapting to changes in the environment. The integration of neuromodulation based robots in the study of human-robot interaction would be worth considering in future.

Sign in / Sign up

Export Citation Format

Share Document