scholarly journals Enhancing learning capabilities of movement primitives under distributed probabilistic framework for flexible assembly tasks

2021 ◽  
Author(s):  
Likun Wang ◽  
Shuya Jia ◽  
Guoyan Wang ◽  
Alison Turner ◽  
Svetan Ratchev
Keyword(s):  
Industrial Robots ◽  
Training Dataset ◽  
Probabilistic Framework ◽  
Flexible Robot ◽  
Learning Abilities ◽  
Flexible Assembly ◽  
Learning Framework ◽  
Movement Primitives ◽  
Distributed Framework ◽  
Point Trajectories

AbstractThis paper presents a novel probabilistic distributed framework based on movement primitives for flexible robot assembly. Since the modern advanced industrial cell usually deals with various scenarios that are not fixed via-point trajectories but highly reconfigurable tasks, the industrial robots used in these applications must be capable of adapting and learning new in-demand skills without programming experts. Therefore, we propose a probabilistic framework that could accommodate various learning abilities trained with different movement-primitive datasets, separately. Derived from the Bayesian Committee Machine, this framework could infer new adapting trajectories with weighted contributions of each training dataset. To verify the feasibility of our proposed imitation learning framework, the simulation comparison with the state-of-the-art movement learning framework task-parametrised GMM is conducted. Several key aspects, such as generalisation capability, learning accuracy and computation expense, are discussed and compared. Moreover, two real-world experiments, i.e. riveting picking and nutplate picking, are further tested with the YuMi collaborative robot to verify the application feasibility in industrial assembly manufacturing.

Ensemble Learning Approach with LASSO for Predicting Catalytic Reaction Rates

Synlett ◽  
2020 ◽  
Author(s):  
Akira Yada ◽  
Kazuhiko Sato ◽  
Tarojiro Matsumura ◽  
Yasunobu Ando ◽  
Kenji Nagata ◽  
...  
Keyword(s):  
Ensemble Learning ◽  
Reaction Rates ◽  
Initial Reaction Rate ◽  
Training Dataset ◽  
Initial Reaction ◽  
Learning Approach ◽  
Learning Framework ◽  
Machine Learning Approach ◽  
Reasonable Prediction ◽  
Epoxidation Of Alkenes

AbstractThe prediction of the initial reaction rate in the tungsten-catalyzed epoxidation of alkenes by using a machine learning approach is demonstrated. The ensemble learning framework used in this study consists of random sampling with replacement from the training dataset, the construction of several predictive models (weak learners), and the combination of their outputs. This approach enables us to obtain a reasonable prediction model that avoids the problem of overfitting, even when analyzing a small dataset.

scholarly journals A machine learning framework to determine geolocations from metagenomic profiling

2020 ◽  
Vol 15 (1) ◽  
Author(s):  
Lihong Huang ◽  
Canqiang Xu ◽  
Wenxian Yang ◽  
Rongshan Yu
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Geographic Origin ◽  
Training Data ◽  
Metagenomic Data ◽  
Training Dataset ◽  
Kriging Interpolation ◽  
Learning Framework ◽  
Testing Data ◽  
Microbial Samples

Abstract Background Studies on metagenomic data of environmental microbial samples found that microbial communities seem to be geolocation-specific, and the microbiome abundance profile can be a differentiating feature to identify samples’ geolocations. In this paper, we present a machine learning framework to determine the geolocations from metagenomics profiling of microbial samples. Results Our method was applied to the multi-source microbiome data from MetaSUB (The Metagenomics and Metadesign of Subways and Urban Biomes) International Consortium for the CAMDA 2019 Metagenomic Forensics Challenge (the Challenge). The goal of the Challenge is to predict the geographical origins of mystery samples by constructing microbiome fingerprints.First, we extracted features from metagenomic abundance profiles. We then randomly split the training data into training and validation sets and trained the prediction models on the training set. Prediction performance was evaluated on the validation set. By using logistic regression with L2 normalization, the prediction accuracy of the model reaches 86%, averaged over 100 random splits of training and validation datasets.The testing data consists of samples from cities that do not occur in the training data. To predict the “mystery” cities that are not sampled before for the testing data, we first defined biological coordinates for sampled cities based on the similarity of microbial samples from them. Then we performed affine transform on the map such that the distance between cities measures their biological difference rather than geographical distance. After that, we derived the probabilities of a given testing sample from unsampled cities based on its predicted probabilities on sampled cities using Kriging interpolation. Results show that this method can successfully assign high probabilities to the true cities-of-origin of testing samples. Conclusion Our framework shows good performance in predicting the geographic origin of metagenomic samples for cities where training data are available. Furthermore, we demonstrate the potential of the proposed method to predict metagenomic samples’ geolocations for samples from locations that are not in the training dataset.

Dynamic Simulation of a Leadscrew Driven Flexible Robot Arm and Controller

1986 ◽  
Vol 108 (2) ◽  
pp. 119-126 ◽  
Author(s):  
Nabil G. Chalhoub ◽  
A. Galip Ulsoy
Keyword(s):  
High Performance ◽  
Industrial Robots ◽  
Body Motion ◽  
Structural Flexibility ◽  
Robot Arm ◽  
Flexible Robot ◽  
Spherical Coordinate ◽  
Performance Requirements ◽  
Simulation Results ◽  
Speed And Accuracy

High performance requirements in robotics have led to the consideration of structural flexibilty in robot arms. This paper employs an assumed modes method to model the flexible motion of the last link of a spherical coordinate robot arm. The model, which includes the non backdrivability of the leadscrews, is used to investigate relationships between the arm structural flexibility and a linear controller for the rigid body motion. This simple controller is used to simulate the controllers currently used in industrial robots. The simulation results illustrate the differences between leadscrew driven and unconstrained axes of the robot; they indicate the trade-off between speed and accuracy; and show potential instability mechanisms due to the interaction between the controller and the robot structural flexibility.

scholarly journals An Ensemble Learning Based Framework for Traditional Chinese Medicine Data Analysis with ICD-10 Labels

2015 ◽  
Vol 2015 ◽  
pp. 1-8
Author(s):  
Gang Zhang ◽  
Yonghui Huang ◽  
Ling Zhong ◽  
Shanxing Ou ◽  
Yi Zhang ◽  
...  
Keyword(s):  
Ensemble Learning ◽  
Learning Strategy ◽  
Computational Cost ◽  
Training Dataset ◽  
Support Vector ◽  
Learning Framework ◽  
Analysis Task ◽  
Icd 10 ◽  
Effective Diagnosis ◽  
Clinical Records

Objective.This study aims to establish a model to analyze clinical experience of TCM veteran doctors. We propose an ensemble learning based framework to analyze clinical records with ICD-10 labels information for effective diagnosis and acupoints recommendation.Methods.We propose an ensemble learning framework for the analysis task. A set of base learners composed of decision tree (DT) and support vector machine (SVM) are trained by bootstrapping the training dataset. The base learners are sorted by accuracy and diversity through nondominated sort (NDS) algorithm and combined through a deep ensemble learning strategy.Results.We evaluate the proposed method with comparison to two currently successful methods on a clinical diagnosis dataset with manually labeled ICD-10 information. ICD-10 label annotation and acupoints recommendation are evaluated for three methods. The proposed method achieves an accuracy rate of 88.2%  ±  2.8% measured by zero-one loss for the first evaluation session and 79.6%  ±  3.6% measured by Hamming loss, which are superior to the other two methods.Conclusion.The proposed ensemble model can effectively model the implied knowledge and experience in historic clinical data records. The computational cost of training a set of base learners is relatively low.

scholarly journals Development of Flexible Robot Skin for Safe and Natural Human–Robot Collaboration

Micromachines ◽  
2018 ◽  
Vol 9 (11) ◽  
pp. 576 ◽  
Author(s):  
Gaoyang Pang ◽  
Jia Deng ◽  
Fangjinhua Wang ◽  
Junhui Zhang ◽  
Zhibo Pang ◽  
...  
Keyword(s):  
Three Dimensional ◽  
Human Robot Interaction ◽  
Industrial Robots ◽  
Percentage Change ◽  
Flexible Robot ◽  
Robot Interaction ◽  
Industrial Manufacturing ◽  
Collision Force ◽  
The One ◽  
Robot Skin

For industrial manufacturing, industrial robots are required to work together with human counterparts on certain special occasions, where human workers share their skills with robots. Intuitive human–robot interaction brings increasing safety challenges, which can be properly addressed by using sensor-based active control technology. In this article, we designed and fabricated a three-dimensional flexible robot skin made by the piezoresistive nanocomposite based on the need for enhancement of the security performance of the collaborative robot. The robot skin endowed the YuMi robot with a tactile perception like human skin. The developed sensing unit in the robot skin showed the one-to-one correspondence between force input and resistance output (percentage change in impedance) in the range of 0–6.5 N. Furthermore, the calibration result indicated that the developed sensing unit is capable of offering a maximum force sensitivity (percentage change in impedance per Newton force) of 18.83% N−1 when loaded with an external force of 6.5 N. The fabricated sensing unit showed good reproducibility after loading with cyclic force (0–5.5 N) under a frequency of 0.65 Hz for 3500 cycles. In addition, to suppress the bypass crosstalk in robot skin, we designed a readout circuit for sampling tactile data. Moreover, experiments were conducted to estimate the contact/collision force between the object and the robot in a real-time manner. The experiment results showed that the implemented robot skin can provide an efficient approach for natural and secure human–robot interaction.

scholarly journals Optimizing Industrial Robots for Accurate High-Speed Applications

2013 ◽  
Vol 2013 ◽  
pp. 1-12 ◽  
Author(s):  
Hubert Gattringer ◽  
Roland Riepl ◽  
Matthias Neubauer
Keyword(s):  
High Speed ◽  
Industrial Robot ◽  
Optimization Techniques ◽  
Industrial Robots ◽  
Industrial Control ◽  
Geometric Calibration ◽  
One Step ◽  
Point Trajectories ◽  
Optimal Efficiency ◽  
Point To Point

Today’s standard robotic systems often do not meet the industry’s demands for accurate high-speed robotic applications. Any machine, be it an existing or a new one, should be pushed to its limits to provide “optimal” efficiency. However, due to the high complexity of modern applications, a one-step overall optimization is not possible. Therefore, this contribution introduces a step-by-step sequence of multiple nonlinear optimizations. Included are optimal configurations for geometric calibration, best-exciting trajectories for parameter identification, model-based control, and time/energy optimal trajectory planning for continuous path and point-to-point trajectories. Each of these optimizations contributes to the improvement of the overall system. Existing optimization techniques are adapted and extended for use with a standard industrial robot scenario and combined with a comprehensive toolkit with discussions on the interplay between the separate components. Most importantly, all procedures are evaluated in practical experiments on a standard robot with industrial control hardware and the recorded measurements are presented, a step often missing in publications in this area.

A novel approach to flexible robotic assembly systems

Robotica ◽  
1995 ◽  
Vol 13 (6) ◽  
pp. 583-589
Author(s):  
Samir B. Billatos
Keyword(s):  
Industrial Robots ◽  
Robotic Assembly ◽  
Assembly Systems ◽  
Flexible Assembly Systems ◽  
Flexible Assembly ◽  
Novel Approach ◽  
Robotic Wrist ◽  
The Way

SummaryThis paper presents a novel approach to designing and manufacturing of a universal gripper to be used with industrial robots in flexible assembly systems. Important issues that impact greatly on the efficiency of the gripper are also discussed in this paper. Such issues include the degree of compliance allowed by the robotic wrist and the way these grippers are actuated. The gripper has been proven to be extremely flexible and low in cost.

Design of Under-Actuated Open-Chain Planar Robots for Repetitive Cyclic Motions

2006 ◽  
Author(s):  
Sunil K. Agrawal ◽  
Vivek Sangwan
Keyword(s):  
Numerical Methods ◽  
Industrial Robots ◽  
Differential Flatness ◽  
Open Chain ◽  
Revolute Joints ◽  
Planar Robot ◽  
Point Trajectories ◽  
Point To Point ◽  
Three Degree Of Freedom ◽  
Output Space

Under-actuated systems are unavoidable in certain applications. For example, a biped can not have an actuator between the foot and the ground. For industrial robots, underactuation is preferable due to cost considerations. A fully actuated system can execute any joint trajectory. However, if the system is under-actuated, not all joint trajectories are attainable. For such systems, it is difficult to characterize attainable joint trajectories analytically and numerical methods are generally used to characterize them. This paper investigates the property of differential flatness for under-actuated planar open chain robots and study its dependence on inertia distribution within the system. Once this property is established, trajectory between any two points in its differentially flat output space is feasible and can be shown to be consistent with the dynamics of the under-actuated system. It is shown that certain choices of inertia distributions make an under-actuated open-chain planar robot with revolute joints feedback linearizable, i.e., also differentially flat. Hence, both cyclic and point to point trajectories can be guaranteed with these under-actuated systems. The methodology proposed is demonstrated with an under-actuated three degree-of-freedom planar robot.

Sign in / Sign up

Export Citation Format

Share Document