scholarly journals Hybrid Imitation Learning Framework for Robotic Manipulation Tasks

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3409
Author(s):  
Eunjin Jung ◽  
Incheol Kim
Keyword(s):  
Performance Improvement ◽  
Robotic Manipulation ◽  
Imitation Learning ◽  
Learning Method ◽  
Training Time ◽  
Learning Framework ◽  
State Recovery ◽  
Mixing Method ◽  
Series Of Experiments ◽  
Stable Learning

This study proposes a novel hybrid imitation learning (HIL) framework in which behavior cloning (BC) and state cloning (SC) methods are combined in a mutually complementary manner to enhance the efficiency of robotic manipulation task learning. The proposed HIL framework efficiently combines BC and SC losses using an adaptive loss mixing method. It uses pretrained dynamics networks to enhance SC efficiency and performs stochastic state recovery to ensure stable learning of policy networks by transforming the learner’s task state into a demo state on the demo task trajectory during SC. The training efficiency and policy flexibility of the proposed HIL framework are demonstrated in a series of experiments conducted to perform major robotic manipulation tasks (pick-up, pick-and-place, and stack tasks). In the experiments, the HIL framework showed about a 2.6 times higher performance improvement than the pure BC and about a four times faster training time than the pure SC imitation learning method. In addition, the HIL framework also showed about a 1.6 times higher performance improvement and about a 2.2 times faster training time than the other hybrid learning method combining BC and reinforcement learning (BC + RL) in the experiments.

scholarly journals An Adaptive Imitation Learning Framework for Robotic Complex Contact-Rich Insertion Tasks

2022 ◽  
Vol 8 ◽  
Author(s):  
Yan Wang ◽  
Cristian C. Beltran-Hernandez ◽  
Weiwei Wan ◽  
Kensuke Harada
Keyword(s):  
Force Control ◽  
Robotic Manipulation ◽  
Imitation Learning ◽  
Specific Class ◽  
High Quality ◽  
Single Task ◽  
Learning Framework ◽  
Dynamic Movement ◽  
Real Hardware ◽  
Dynamic Movement Primitives

Complex contact-rich insertion is a ubiquitous robotic manipulation skill and usually involves nonlinear and low-clearance insertion trajectories as well as varying force requirements. A hybrid trajectory and force learning framework can be utilized to generate high-quality trajectories by imitation learning and find suitable force control policies efficiently by reinforcement learning. However, with the mentioned approach, many human demonstrations are necessary to learn several tasks even when those tasks require topologically similar trajectories. Therefore, to reduce human repetitive teaching efforts for new tasks, we present an adaptive imitation framework for robot manipulation. The main contribution of this work is the development of a framework that introduces dynamic movement primitives into a hybrid trajectory and force learning framework to learn a specific class of complex contact-rich insertion tasks based on the trajectory profile of a single task instance belonging to the task class. Through experimental evaluations, we validate that the proposed framework is sample efficient, safer, and generalizes better at learning complex contact-rich insertion tasks on both simulation environments and on real hardware.

scholarly journals Performance Improvement Using CNN for Sentiment Analysis

2018 ◽  
Vol 2 (1) ◽  
Author(s):  
Moch. Ari Nasichuddin ◽  
Teguh Bharata Adji ◽  
Widyawan Widyawan
Keyword(s):  
Deep Learning ◽  
Sentiment Analysis ◽  
Performance Improvement ◽  
Processing Time ◽  
Great Accuracy ◽  
Learning Method ◽  
Training Process ◽  
Training Time ◽  
Accuracy Level ◽  
Filter Size

The approach using Deep Learning method provides great results in various field implementations, especially in the field of Sentiment Analysis. One of Deep Learning methods is CNN which has the ability to provide great accuracy in some previous research. However, there are some parts of the training process which can be improved to upgrade the accuracy level and the training time. In this paper, we try to improve the accuracy and processing time of sentiment analysis using CNN model. By tuning the filter size, frameworks, and pre-training, the results show that the use of smaller filter size and pre-training word2vec provide greater accuracy than some previous studies.

scholarly journals Nodule Detection with Convolutional Neural Network Using Apache Spark and GPU Frameworks

2021 ◽  
Vol 11 (6) ◽  
pp. 2838
Author(s):  
Nikitha Johnsirani Venkatesan ◽  
Dong Ryeol Shin ◽  
Choon Sung Nam
Keyword(s):  
Neural Network ◽  
Radiation Dose ◽  
Convolutional Neural Network ◽  
Model Performance ◽  
Performance Comparison ◽  
Apache Spark ◽  
Training Time ◽  
Learning Framework ◽  
Proposed Model

In the pharmaceutical field, early detection of lung nodules is indispensable for increasing patient survival. We can enhance the quality of the medical images by intensifying the radiation dose. High radiation dose provokes cancer, which forces experts to use limited radiation. Using abrupt radiation generates noise in CT scans. We propose an optimal Convolutional Neural Network model in which Gaussian noise is removed for better classification and increased training accuracy. Experimental demonstration on the LUNA16 dataset of size 160 GB shows that our proposed method exhibit superior results. Classification accuracy, specificity, sensitivity, Precision, Recall, F1 measurement, and area under the ROC curve (AUC) of the model performance are taken as evaluation metrics. We conducted a performance comparison of our proposed model on numerous platforms, like Apache Spark, GPU, and CPU, to depreciate the training time without compromising the accuracy percentage. Our results show that Apache Spark, integrated with a deep learning framework, is suitable for parallel training computation with high accuracy.

Fusion based learning approach for predicting concrete pouring productivity based on construction and supply parameters

2016 ◽  
Vol 16 (2) ◽  
pp. 185-202 ◽  
Author(s):  
Mojtaba Maghrebi ◽  
Ali Shamsoddini ◽  
S. Travis Waller
Keyword(s):  
Supply Chain ◽  
Production Rate ◽  
Learning Method ◽  
Data Set ◽  
Content Type ◽  
Field Database ◽  
The Stability ◽  
Stable Learning ◽  
Ready Mixed Concrete ◽  
Practical Implications

Purpose The purpose of this paper is to predict the concrete pouring production rate by considering both construction and supply parameters, and by using a more stable learning method. Design/methodology/approach Unlike similar approaches, this paper considers not only construction site parameters, but also supply chain parameters. Machine learner fusion-regression (MLF-R) is used to predict the production rate of concrete pouring tasks. Findings MLF-R is used on a field database including 2,600 deliveries to 507 different locations. The proposed data set and the results are compared with ANN-Gaussian, ANN-Sigmoid and Adaboost.R2 (ANN-Gaussian). The results show better performance of MLF-R obtaining the least root mean square error (RMSE) compared with other methods. Moreover, the RMSEs derived from the predictions by MLF-R in some trials had the least standard deviation, indicating the stability of this approach among similar used approaches. Practical implications The size of the database used in this study is much larger than the size of databases used in previous studies. It helps authors draw their conclusions more confidently and introduce more generalised models that can be used in the ready-mixed concrete industry. Originality/value Introducing a more stable learning method for predicting the concrete pouring production rate helps not only construction parameters, but also traffic and supply chain parameters.

scholarly journals Triple-GAIL: A Multi-Modal Imitation Learning Framework with Generative Adversarial Nets

2020 ◽  
Author(s):  
Cong Fei ◽  
Bin Wang ◽  
Yuzheng Zhuang ◽  
Zongzhang Zhang ◽  
Jianye Hao ◽  
...  
Keyword(s):  
Real World ◽  
Autonomous Vehicles ◽  
Data Augmentation ◽  
State Of The Art ◽  
Robot Learning ◽  
Imitation Learning ◽  
Proper Understanding ◽  
Learning Framework ◽  
Strategy Game ◽  
Real Time Strategy Game

Generative adversarial imitation learning (GAIL) has shown promising results by taking advantage of generative adversarial nets, especially in the field of robot learning. However, the requirement of isolated single modal demonstrations limits the scalability of the approach to real world scenarios such as autonomous vehicles' demand for a proper understanding of human drivers' behavior. In this paper, we propose a novel multi-modal GAIL framework, named Triple-GAIL, that is able to learn skill selection and imitation jointly from both expert demonstrations and continuously generated experiences with data augmentation purpose by introducing an auxiliary selector. We provide theoretical guarantees on the convergence to optima for both of the generator and the selector respectively. Experiments on real driver trajectories and real-time strategy game datasets demonstrate that Triple-GAIL can better fit multi-modal behaviors close to the demonstrators and outperforms state-of-the-art methods.

Survey of imitation learning for robotic manipulation

2019 ◽  
Vol 3 (4) ◽  
pp. 362-369
Author(s):  
Bin Fang ◽  
Shidong Jia ◽  
Di Guo ◽  
Muhua Xu ◽  
Shuhuan Wen ◽  
...  
Keyword(s):  
Robotic Manipulation ◽  
Imitation Learning

scholarly journals Joint Entity and Event Extraction with Generative Adversarial Imitation Learning

2019 ◽  
Vol 1 (2) ◽  
pp. 99-120 ◽  
Author(s):  
Tongtao Zhang ◽  
Heng Ji ◽  
Avirup Sil
Keyword(s):  
State Of The Art ◽  
Ground Truth ◽  
Event Extraction ◽  
Imitation Learning ◽  
Learning Method ◽  
Inverse Reinforcement Learning ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
The Difference ◽  
New Framework

We propose a new framework for entity and event extraction based on generative adversarial imitation learning—an inverse reinforcement learning method using a generative adversarial network (GAN). We assume that instances and labels yield to various extents of difficulty and the gains and penalties (rewards) are expected to be diverse. We utilize discriminators to estimate proper rewards according to the difference between the labels committed by the ground-truth (expert) and the extractor (agent). Our experiments demonstrate that the proposed framework outperforms state-of-the-art methods.

Sign in / Sign up

Export Citation Format

Share Document