Search results

This paper aims to realize a fully distributed multi-UAV collision detection and avoidance based on deep reinforcement learning (DRL). To deal with the problem of low sample efficiency in DRL and speed up the training. To improve the applicability and reliability of the DRL-based approach in multi-UAV control problems.

In this paper, a fully distributed collision detection and avoidance approach for multi-UAV based on DRL is proposed. A method that integrates human experience into policy training via a human experience-based adviser is proposed. The authors propose a hybrid control method which combines the learning-based policy with traditional model-based control. Extensive experiments including simulations, real flights and comparative experiments are conducted to evaluate the performance of the approach.

A fully distributed multi-UAV collision detection and avoidance method based on DRL is realized. The reward curve shows that the training process when integrating human experience is significantly accelerated and the mean episode reward is higher than the pure DRL method. The experimental results show that the DRL method with human experience integration has a significant improvement than the pure DRL method for multi-UAV collision detection and avoidance. Moreover, the safer flight brought by the hybrid control method has also been validated.

The fully distributed architecture is suitable for large-scale unmanned aerial vehicle (UAV) swarms and real applications. The DRL method with human experience integration has significantly accelerated the training compared to the pure DRL method. The proposed hybrid control strategy makes up for the shortcomings of two-dimensional light detection and ranging and other puzzles in applications.

Methodological pluralism in consumer research is usually confined to post‐positivist interpretive approaches. Argues, however, that a positivistic stance, radical behaviourism, can enrich epistemological debate among researchers with the recognition of radical behaviourism′s ultimate reliance on interpretation as well as science. Although radical behaviourist explanation was initially founded on Machian positivism, its account of complex social behaviours such as purchase and consumption is necessarily interpretive, inviting comparison with the hermeneutical approaches currently emerging in consumer research. Radical behaviourist interpretation attributes meaning to behaviour by identifying its environmental determinants, especially the learning history of the individual in relation to the consequences similar prior behaviour has effected. The nature of such interpretation is demonstrated for purchase and consumption responses by means of a critique of radical behaviourism as applied to complex human activity. In the process, develops and applies a framework for radical behaviourist interpretation of purchase and consumption to four operant equifinality classes of consumer behaviour: accomplishment, pleasure, accumulation and maintenance. Some epistemological implications of this framework, the behavioural perspective model (BPM) of purchase and consumption, are discussed in the context of the relativity and incommensurability of research paradigms. Finally, evaluates the interpretive approach, particularly in terms of its relevance to the nature and understanding of managerial marketing.

This paper aim to solve the problem of low assembly success rate for 3c assembly lines designed based on classical control algorithms due to inevitable random disturbances and other factors,by incorporating intelligent algorithms into the assembly line, the assembly process can be extended to uncertain assembly scenarios.

This work proposes a reinforcement learning framework based on digital twins. First, the authors used Unity3D to build a simulation environment that matches the real scene and achieved data synchronization between the real environment and the simulation environment through the robot operating system. Then, the authors trained the reinforcement learning model in the simulation environment. Finally, by creating a digital twin environment, the authors transferred the skill learned from the simulation to the real environment and achieved stable algorithm deployment in real-world scenarios.

In this work, the authors have completed the transfer of skill-learning algorithms from virtual to real environments by establishing a digital twin environment. On the one hand, the experiment proves the progressiveness of the algorithm and the feasibility of the application of digital twins in reinforcement learning transfer. On the other hand, the experimental results also provide reference for the application of digital twins in 3C assembly scenarios.

In this work, the authors designed a new encoder structure in the simulation environment to encode image information, which improved the model’s perception of the environment. At the same time, the authors used the fixed strategy combined with the reinforcement learning strategy to learn skills, which improved the rate of convergence and stability of skills learning. Finally, the authors transferred the learned skills to the physical platform through digital twin technology and realized the safe operation of the flexible printed circuit assembly task.

This paper aims to propose a bilateral robotic system for lower extremity hemiparesis rehabilitation. The hemiplegic patients can complete rehabilitation exercise voluntarily with the assistance of the robot. The reinforcement learning is included in the robot control system, enhancing the muscle activation of the impaired limbs (ILs) efficiently with ensuring the patients’ safety.

A bilateral leader–follower robotic system is constructed for lower extremity hemiparesis rehabilitation, where the leader robot interacts with the healthy limb (HL) and the follow robot is worn by the IL. The therapeutic training is transferred from the HL to the IL with the assistance of the robot, and the IL follows the motion trajectory prescribed by the HL, which is called the mirror therapy. The model reference adaptive impedance control is used for the leader robot, and the reinforcement learning controller is designed for the follower robot. The reinforcement learning aims to increase the muscle activation of the IL and ensure that its motion can be mastered by the HL for safety. An asynchronous algorithm is designed by improving experience relay to run in parallel on multiple robotic platforms to reduce learning time.

Through clinical tests, the lower extremity hemiplegic patients can rehabilitate with high efficiency using the robotic system. Also, the proposed scheme outperforms other state-of-the-art methods in tracking performance, muscle activation, learning efficiency and rehabilitation efficacy.

Using the aimed robotic system, the lower extremity hemiplegic patients with different movement abilities can obtain better rehabilitation efficacy.

The aim of the paper is to test and demonstrate the potential benefits in applying reinforcement learning instead of traditional methods to optimize the content of a company's mobile application to best help travellers finding their ideal flights. To this end, two approaches were considered and compared via simulation: standard randomized experiments or A/B testing and multi-armed bandits.

The simulation of the two approaches to optimize the content of its mobile application and, consequently, increase flights conversions is illustrated as applied by Skyscanner, using R software.

The first results are about the comparison between the two approaches – A/B testing and multi-armed bandits – to identify the best one to achieve better results for the company. The second one is to gain experiences and suggestion in the application of the two approaches useful for other industries/companies.

The case study demonstrated, via simulation, the potential benefits to apply the reinforcement learning in a company. Finally, the multi-armed bandit was implemented in the company, but the period of the available data was limited, and due to its strategic relevance, the company cannot show all the findings.

The right algorithm can change according to the situation and industry but would bring great benefits to the company's ability to surface content that is more relevant to users and help improving the experience for travellers. The study shows how to manage complexity and data to achieve good results.

The paper describes the approach used by an European leading company operating in the travel sector in understanding how to adapt reinforcement learning to its strategic goals. It presents a real case study and the simulation of the application of A/B testing and multi-armed bandit in Skyscanner; moreover, it highlights practical suggestion useful to other companies.

This work aims to combine the cloud robotics technologies with deep reinforcement learning to build a distributed training architecture and accelerate the learning procedure of autonomous systems. Especially, a distributed training architecture for navigating unmanned aerial vehicles (UAVs) in complicated dynamic environments is proposed.

This study proposes a distributed training architecture named experience-sharing learner-worker (ESLW) for deep reinforcement learning to navigate UAVs in dynamic environments, which is inspired by cloud-based techniques. With the ESLW architecture, multiple worker nodes operating in different environments can generate training data in parallel, and then the learner node trains a policy through the training data collected by the worker nodes. Besides, this study proposes an extended experience replay (EER) strategy to ensure the method can be applied to experience sequences to improve training efficiency. To learn more about dynamic environments, convolutional long short-term memory (ConvLSTM) modules are adopted to extract spatiotemporal information from training sequences.

Experimental results demonstrate that the ESLW architecture and the EER strategy accelerate the convergence speed and the ConvLSTM modules specialize in extract sequential information when navigating UAVs in dynamic environments.

Inspired by the cloud robotics technologies, this study proposes a distributed ESLW architecture for navigating UAVs in dynamic environments. Besides, the EER strategy is proposed to speed up training processes of experience sequences, and the ConvLSTM modules are added to networks to make full use of the sequential experiences.

This paper aims to propose an improved reinforcement learning-based fuzzy-PID controller for load frequency control (LFC) of an island microgrid.

To evaluate the performance of the proposed controller, three different types of controllers including optimal proportional-integral-derivative (PID) controller, optimal fuzzy PID controller and the proposed reinforcement learning-based fuzzy-PID controller are compared. Optimal PID controller and classic fuzzy-PID controller parameters are tuned using Non-dominated Sorting Genetic Algorithm-II algorithm to minimize overshoot, settling time and integral square error over a wide range of load variations. The simulations are carried out using MATLAB/SIMULINK package.

Simulation results indicated the superiority of the proposed reinforcement learning-based controller over fuzzy-PID and optimal-PID controllers in the same operational conditions.

In this paper, an improved reinforcement learning-based fuzzy-PID controller is proposed for LFC of an island microgrid. The main advantage of the reinforcement learning-based controllers is their hardiness behavior along with uncertainties and parameters variations. Also, they do not need any knowledge about the system under control; thus, they can control any large system with high nonlinearities.

Drawing on the social learning theory, the purpose of this paper is to examine the antecedents and consequences of users’ excessive online social gaming. Specifically, the authors develop a model to propose that observational learning and reinforcement learning mechanisms together determine excessive online social gaming, which further foster adverse consequences.

The model is empirically validated by a longitudinal survey among users of a popular online social game: Arena of Valor. The empirical data are analyzed using component-based structural equation modeling approach.

The empirical results offer two key findings. First, excessive online social gaming is determined by observational learning factors, i.e. social frequency and social norm, and reinforcement learning factors, i.e. perceived enjoyment and perceived escapism. Second, excessive online social gaming leads to three categories of adverse consequences: technology-family conflict, technology-work conflict and technology-person conflict. Meanwhile, technology-family conflict and technology-work conflict further foster technology-person conflict.

This study contributes to the literature by developing a nomological framework of excessive online social gaming and by extending the social learning theory to excessive technology use.

Entity relation extraction is an important research direction to obtain structured information. However, most of the current methods are to determine the relations between entities in a given sentence based on a stepwise method, seldom considering entities and relations into a unified framework. The joint learning method is an optimal solution that combines relations and entities. This paper aims to optimize hierarchical reinforcement learning framework and provide an efficient model to extract entity relation.

This paper is based on the hierarchical reinforcement learning framework of joint learning and combines the model with BERT, the best language representation model, to optimize the word embedding and encoding process. Besides, this paper adjusts some punctuation marks to make the data set more standardized, and introduces positional information to improve the performance of the model.

Experiments show that the model proposed in this paper outperforms the baseline model with a 13% improvement, and achieve 0.742 in F1 score in NYT10 data set. This model can effectively extract entities and relations in large-scale unstructured text and can be applied to the fields of multi-domain information retrieval, intelligent understanding and intelligent interaction.

The research provides an efficient solution for researchers in a different domain to make use of artificial intelligence (AI) technologies to process their unstructured text more accurately.

At present, teaching methods based on 2D drawings are still commonly used for educating students on the location of steel reinforcement bars in concrete. However, traditional teaching methods have limitations as students can find it difficult to understand 2D drawings. This study aims to develop an interactive and collaborative augmented reality environment (ICARE) using augmented reality (AR) technology to improve students' engagement in learning.

This study develops an ICARE prototype, which is organized into two stages: (1) The augmented teaching environment comprising of models and interactive components; (2) The AR collaborative application which uses Photon Unity Networking (PUN) plugin and Azure spatial anchors cloud service. The AR-based teaching environment runs with Universal Windows Platform (UWP) to enable development in the HoloLens 2 through Microsoft Visual Studio.

An experimental study was conducted, where 60 students were divided into three groups employing Drawings-based, building information modeling (BIM)-based and AR-based methods for teaching. After the test, the three groups of students were requested to complete a questionnaire. According to the analysis of the experimental results, the ICARE can improve students' comprehension, memory of learned materials and their ability to read and understand steel reinforcement drawings improving the quality of teaching, especially interactivity and engagement.

As illustrated in the experiments, the developed ICARE has outstanding performance over conventional approaches in civil engineering courses that can improve students' comprehension and memory of knowledge and their ability to read and understand steel bar drawings. This study provides empirical evidence that AR is a promising technology that can be integrated with traditional classroom instruction and can improve students' comprehension and memory of knowledge and their ability to read and understand steel bar drawings.