A context-aware real-time human-robot collaborating reinforcement learning-based disassembly planning model under uncertainty

The intersection management system can increase traffic capacity, vehicle safety, and the smoothness of all vehicle movement. Platoons of connected vehicles (CVs) use communication technologies to share information with each other and with infrastructures. In this paper, we proposed a deep reinforcement learning (DRL) model that applies to vehicle platooning at an isolated signalized intersection with partial detection. Moreover, we identified hyperparameters and tested the system with different numbers of vehicles (1, 2, and 3) in the platoon. To compare the effectiveness of the proposed model, we implemented two benchmark options, actuated traffic signal control (ATSC) and max pressure (MP). The experimental results demonstrated that the DRL model has many outstanding advantages compared to other models. Through the learning process, the average waiting time of vehicles in the DRL method was improved by 20% and 28% compared with the ATSC and MP options. The results also suggested that the DRL model is effective when the CV penetration rate is over 20%.

This paper investigates stock portfolios by application of Deep Reinforcement Learning (DRL) Models to achieve an optimal tactical asset allocation. The research problem is described as an optimization scenario that seeks to maximize the portfolio risk adjusted returns for a given portfolio asset allocation. The problem is set up with an initial capital investment which is invested in a set of assets. The initial strategic allocation is determined, which in our case is the equal weight allocation, and all of the capital is invested in the set of assets. At each point in time, the assets are reallocated according to the allocation which will increase the portfolio value. Two DRL models are implemented. The performance of the DRL models is compared with the uniform weights portfolio. The results show that, generally, two DRL models have higher cumulative returns.

This article presents a disassembly task planning algorithm considering human–robot collaboration (HRC) and human behavior prediction (HBP). Unlike assembly procedures, the disassembly of end-of-life (EOL) products has been a labor-intensive process with uncertainties difficult to cope with. Meanwhile, it is usually challenging to obtain an optimal sequence efficiently without excessive computational cost. Also, the conventional human-centered task planning, in which the robot has to halt frequently due to unsafe interruptions by human motions, may decrease the efficiency of the disassembly process. In this article, a sequence planner is proposed to assign tasks in real time between a human operator and a robot to overcome the aforementioned challenges. The cost function includes the effort of the human and the robot in terms of both movement distance and time spent on the tasks. The constraints include the disassembly rules and the safety of the human operation. The optimal sequence is generated by solving an optimization problem in a receding-horizon way. In particular, at each step, the proposed disassembly sequence planner locates the workers (a human operator and a robot) and the to-be-disassembled components, predicts human movement for the next several steps, and obtains the optimal disassembly sequence for the next several steps following disassembly rules and safety constraints. Experiments have been extensively conducted on the disassembly of a wooden toybox and a used hard disk drive (HDD) to validate the proposed disassembly sequence planner. The planner has successfully generated the disassembly sequence in an HRC setting explicitly considering real-time human motion prediction and assigned the human operator and the robot to collaboratively complete disassembly tasks without violating disassembly rules and safety constraints.

Recent studies show that Deep Reinforcement Learning (DRL) models are vulnerable to adversarial attacks, which attack DRL models by adding small perturbations to the observations. However, some attacks assume full availability of the victim model, and some require a huge amount of computation, making them less feasible for real world applications. In this work, we make further explorations of the vulnerabilities of DRL by studying other aspects of attacks on DRL using realistic and efficient attacks. First, we adapt and propose efficient black-box attacks when we do not have access to DRL model parameters. Second, to address the high computational demands of existing attacks, we introduce efficient online sequential attacks that exploit temporal consistency across consecutive steps. Third, we explore the possibility of an attacker perturbing other aspects in the DRL setting, such as the environment dynamics. Finally, to account for imperfections in how an attacker would inject perturbations in the physical world, we devise a method for generating a robust physical perturbations to be printed. The attack is evaluated on a real-world robot under various conditions. We conduct extensive experiments both in simulation such as Atari games, robotics and autonomous driving, and on real-world robotics, to compare the effectiveness of the proposed attacks with baseline approaches. To the best of our knowledge, we are the first to apply adversarial attacks on DRL systems to physical robots.

The integration of artificial intelligence in education has shown great potential to improve student’s learning experience through emotion detection and the personalization of learning. Many educational settings lack adequate mechanisms to dynamically adapt to students’ emotions, which can negatively impact their academic performance and engagement. This study addresses this problem by implementing a deep reinforcement learning model to detect emotions in real-time and personalize teaching strategies in a hybrid educational environment. Using data from 500 students, captured through cameras, microphones, and biometric sensors and pre-processed with advanced techniques such as histogram equalization and noise reduction, the deep reinforcement learning model was trained and validated to improve the detection accuracy of emotions and the personalization of learning. The results showed a significant improvement in the accuracy of emotion detection, going from 72.4% before the implementation of the system to 89.3% after. Real-time adaptability also increased from 68.5 to 87.6%, while learning personalization rose from 70.2 to 90.1%. K-fold cross-validation with k = 10 confirmed the robustness and generalization of the model, with consistently high scores in all evaluated metrics. This study demonstrates that integrating reinforcement learning models for emotion detection and learning personalization can transform education, providing a more adaptive and student-centered learning experience. These findings identify the potential of these technologies to improve academic performance and student engagement, offering a solid foundation for future research and implementation.

With the spread of online platforms, problems such as manned/unmanned food delivery, cargo delivery, raw material delivery, are increasing the importance of logistics day by day. Vehicle routing problem, which is one of the most important problems in the field of logistics, is a combinatorial problem and as the problem space grows, it takes a long time to find a solution with human effort and in most cases it is not even possible. Thus, it becomes essential for the solution of this problem to be autonomous. Although it is possible to solve the problem with classical heuristic optimization methods, it takes a long time and sometimes does not give a good enough solution. Deep reinforcement learning models with attention mechanisms have great potential in this regard. However,in case of insufficient training in large problem space, it is possible to get away from the optimal solution. In this study, better results are taken in an acceptable time by using the deep reinforcement learning models with attention-model and heuristic methods in a hybrid way.

Time-driven feature-aware jointly deep reinforcement learning for financial signal representation and algorithmic trading

Design automation is undergoing a new generation of changes caused by artificial intelligence technologies represented by deep learning and reinforcement learning. Notably, the advantages of deep reinforcement learning in addressing solution optimisation and decision-making tasks with cognitive automation functionality have garnered attention in design. In the context of surrogate model-driven engineering design optimisation, this paper addresses current research challenges such as reliance on domain knowledge for local development, shortcomings in the self-learning and adaptive capabilities of optimisation algorithms for global exploration, etc. Centred around the deep reinforcement learning model, Deep Q-learning, and complemented by self-organising maps and neural network technologies, we propose a methodology considering multi-fidelity simulation data for design space exploration. This approach effectively reduces sampling costs and enables the optimisation model to learn the optimal direction for high-precision predictions and achieve rapid, accurate optimisation. Finally, the effectiveness of the proposed method is comprehensively validated through four typical optimisation scenarios and a case study involving the optimisation of a wheeled robot's suspension swing arm structure. This work will be a crucial reference for applying deep reinforcement learning in simulation-driven engineering design optimisation.

Attention-based deep learning models for predicting anomalous shock of wastewater treatment plants.

In recent years, the recommendation system and robot learning are undoubtedly the two most popular application fields, and the core algorithms supporting these two fields are deep learning based on perception and reinforcement learning based on exploration learning, respectively. How to combine these two fields to better improve the development of the whole machine learning field is the dream of numerous researchers. The Deep Reinforcement Network (DRN) model successfully embedded reinforcement learning into the recommendation system, which provided a good idea for subsequent researchers. However, the disadvantage is also obvious, that is, the DRN model is built for news recommendations, meaning that the DRN model is not transferable, which is also the defect of many current recommendation system models. Meanwhile, the agent learning method adopted by the DRN model is primitive and inefficient. Among many models and algorithms that have emerged in recent years, we use the newly proposed deployment efficiency to measure their comprehensive quality and found that few models focus on both efficiency and performance improvement. To fill the gap of model deployment efficiency neglected by many researchers and to create a model of reinforcement learning agents with stronger performance, we have been exploring and trying to complete research on the Gate Attentional Factorization Machines (GAFM) model. Finally, we successfully integrated the GAFM model and reinforcement learning. The Deep Reinforcement Factorization Machines (DRFM) model proposed in this paper is based on the combination of deep learning with high perception ability and reinforcement learning with high exploration ability, centered on improving the deployment efficiency and learning performance of the model. The GAFM model is modified and upgraded using multidisciplinary techniques, and a new model-based random exploration strategy is proposed to update and optimize the recommendation list efficiently. Through parallel contrast experiments on various datasets, it is proved that the DRFM model surpasses the traditional recommendation system model in all aspects. The DRFM model is far superior to other models in terms of performance and robustness, and also significantly improved in terms of deployment efficiency. At the same time, we conduct a comparative analysis with the latest deep reinforcement learning algorithm and prove the unique advantages of the DRFM model.

PurposeTo conduct a head-to-head comparison between deep learning (DL) and radiomics models across institutions for predicting microvascular invasion (MVI) in hepatocellular carcinoma (HCC) and to investigate the model robustness and generalizability through rigorous internal and external validation.MethodsThis retrospective study included 2304 preoperative images of 576 HCC lesions from two centers, with MVI status determined by postoperative histopathology. We developed DL and radiomics models for predicting the presence of MVI using B-mode ultrasound, contrast-enhanced ultrasound (CEUS) at the arterial, portal, and delayed phases, and a combined modality (B + CEUS). For radiomics, we constructed models with enlarged vs. original regions of interest (ROIs). A cross-validation approach was performed by training models on one center’s dataset and validating the other, and vice versa. This allowed assessment of the validity of different ultrasound modalities and the cross-center robustness of the models. The optimal model combined with alpha-fetoprotein (AFP) was also validated. The head-to-head comparison was based on the area under the receiver operating characteristic curve (AUC).ResultsThirteen DL models and 25 radiomics models using different ultrasound modalities were constructed and compared. B + CEUS was the optimal modality for both DL and radiomics models. The DL model achieved AUCs of 0.802–0.818 internally and 0.667–0.688 externally across the two centers, whereas radiomics achieved AUCs of 0.749–0.869 internally and 0.646–0.697 externally. The radiomics models showed overall improvement with enlarged ROIs (P < 0.05 for both CEUS and B + CEUS modalities). The DL models showed good cross-institutional robustness (P > 0.05 for all modalities, 1.6–2.1% differences in AUC for the optimal modality), whereas the radiomics models had relatively limited robustness across the two centers (12% drop-off in AUC for the optimal modality). Adding AFP improved the DL models (P < 0.05 externally) and well maintained the robustness, but did not benefit the radiomics model (P > 0.05).ConclusionCross-institutional validation indicated that DL demonstrated better robustness than radiomics for preoperative MVI prediction in patients with HCC, representing a promising solution to non-standardized ultrasound examination procedures.

COVID-19 is highly infectious and causes acute respiratory disease. Machine learning (ML) and deep learning (DL) models are vital in detecting disease from computerized chest tomography (CT) scans. The DL models outperformed the ML models. For COVID-19 detection from CT scan images, DL models are used as end-to-end models. Thus, the performance of the model is evaluated for the quality of the extracted feature and classification accuracy. There are four contributions included in this work. First, this research is motivated by studying the quality of the extracted feature from the DL by feeding these extracted to an ML model. In other words, we proposed comparing the end-to-end DL model performance against the approach of using DL for feature extraction and ML for the classification of COVID-19 CT scan images. Second, we proposed studying the effect of fusing extracted features from image descriptors, e.g., Scale-Invariant Feature Transform (SIFT), with extracted features from DL models. Third, we proposed a new Convolutional Neural Network (CNN) to be trained from scratch and then compared to the deep transfer learning on the same classification problem. Finally, we studied the performance gap between classic ML models against ensemble learning models. The proposed framework is evaluated using a CT dataset, where the obtained results are evaluated using five different metrics The obtained results revealed that using the proposed CNN model is better than using the well-known DL model for the purpose of feature extraction. Moreover, using a DL model for feature extraction and an ML model for the classification task achieved better results in comparison to using an end-to-end DL model for detecting COVID-19 CT scan images. Of note, the accuracy rate of the former method improved by using ensemble learning models instead of the classic ML models. The proposed method achieved the best accuracy rate of 99.39%.

Hybrid residual deep learning models with physical knowledge for improving plant transpiration estimation

Electricity load forecasting is a crucial undertaking within all the deregulated markets globally. Among the research challenges on a global scale, the investigation of deep transfer learning (DTL) in the field of electricity load forecasting represents a fundamental effort that can inform artificial intelligence applications in general. In this paper, a comprehensive study is reported regarding day-ahead electricity load forecasting. For this purpose, three sequence-to-sequence (Seq2seq) deep learning (DL) models are used, namely the multilayer perceptron (MLP), the convolutional neural network (CNN) and the ensemble learning model (ELM), which consists of the weighted combination of the outputs of MLP and CNN models. Also, the study focuses on the development of different forecasting strategies based on DTL, emphasizing the way the datasets are trained and fine-tuned for higher forecasting accuracy. In order to implement the forecasting strategies using deep learning models, load datasets from three Greek islands, Rhodes, Lesvos, and Chios, are used. The main purpose is to apply DTL for day-ahead predictions (1–24 h) for each month of the year for the Chios dataset after training and fine-tuning the models using the datasets of the three islands in various combinations. Four DTL strategies are illustrated. In the first strategy (DTL Case 1), each of the three DL models is trained using only the Lesvos dataset, while fine-tuning is performed on the dataset of Chios island, in order to create day-ahead predictions for the Chios load. In the second strategy (DTL Case 2), data from both Lesvos and Rhodes concurrently are used for the DL model training period, and fine-tuning is performed on the data from Chios. The third DTL strategy (DTL Case 3) involves the training of the DL models using the Lesvos dataset, and the testing period is performed directly on the Chios dataset without fine-tuning. The fourth strategy is a multi-task deep learning (MTDL) approach, which has been extensively studied in recent years. In MTDL, the three DL models are trained simultaneously on all three datasets and the final predictions are made on the unknown part of the dataset of Chios. The results obtained demonstrate that DTL can be applied with high efficiency for day-ahead load forecasting. Specifically, DTL Case 1 and 2 outperformed MTDL in terms of load prediction accuracy. Regarding the DL models, all three exhibit very high prediction accuracy, especially in the two cases with fine-tuning. The ELM excels compared to the single models. More specifically, for conducting day-ahead predictions, it is concluded that the MLP model presents the best monthly forecasts with MAPE values of 6.24% and 6.01% for the first two cases, the CNN model presents the best monthly forecasts with MAPE values of 5.57% and 5.60%, respectively, and the ELM model achieves the best monthly forecasts with MAPE values of 5.29% and 5.31%, respectively, indicating the very high accuracy it can achieve.

Vision-based object positioning is very important in the electronic industry for assembly and inspection tasks. Many methods have been proposed to tackle the problem, either by traditional machine vision or by deep learning (DL) techniques. The traditional methods rely on template matching or feature point correspondence. They are computationally intensive and are easily affected by illumination changes and noise. DL models such as convolutional neural networks (CNNs) are computationally very efficient but are also sensitive against environmental changes. In this article, a deep reinforcement learning (DRL) model based on the Actor-Critic style Proximal Policy Optimization algorithm(s) (AC-PPO) is proposed. The proposed method is applied for the positioning of printed circuit boards (PCBs). The model uses as the current environment the sensed image and the reference template as a guide. It requires only a single manually marked template in the reference image. All possible training images are automatically and randomly generated during the neural network training without human intervention. The proposed reinforcement learning (RL) model is shown to be adaptive to environmental changes, including illumination, noise, de-focusing, and template occlusion, compared with the CNN regressor. Experimental results indicate that the proposed model on average can achieve estimation errors less than 1 pixel in translation and 1° in orientation, with fast evaluation for the real-time PCB positioning task.