Search

Robotic Mobile Fulfillment Systems (RMFSs) face challenges in handling large-scale orders and navigating complex environments, frequently encountering a series of intricate decision-making problems, such as order allocation, shelf selection, and robot scheduling. To address these challenges, this paper integrates Deep Reinforcement Learning (DRL) technology into an RMFS, to meet the needs of efficient order processing and system stability. This study focuses on three key stages of RMFSs: order allocation and sorting, shelf selection, and coordinated robot scheduling. For each stage, mathematical models are established and the corresponding solutions are proposed. Unlike traditional methods, DRL technology is introduced to solve these problems, utilizing a Genetic Algorithm and Ant Colony Optimization to handle decision making related to large-scale orders. Through simulation experiments, performance indicators—such as shelf access frequency and the total processing time of the RMFS—are evaluated. The experimental results demonstrate that, compared to traditional methods, our algorithms excel in handling large-scale orders, showcasing exceptional superiority, capable of completing approximately 110 tasks within an hour. Future research should focus on integrated decision-making modeling for each stage of RMFSs and designing efficient heuristic algorithms for large-scale problems, to further enhance system performance and efficiency. [ABSTRACT FROM AUTHOR]

Variational auto-encoders (VAE) have been widely used in process modeling due to the ability of deep feature extraction and noise robustness. However, the construction of a supervised VAE model still faces huge challenges. The data generated by the existing supervised VAE models are unstable and uncontrollable due to random resampling in the latent subspace, meaning the performance of prediction is greatly weakened. In this paper, a new multi-layer conditional variational auto-encoder (M-CVAE) is constructed by injecting label information into the latent subspace to control the output data generated towards the direction of the actual value. Furthermore, the label information is also used as the input with process variables in order to strengthen the correlation between input and output. Finally, a neural network layer is embedded in the encoder of the model to achieve online quality prediction. The superiority and effectiveness of the proposed method are demonstrated by two real industrial process cases that are compared with other methods. [ABSTRACT FROM AUTHOR]

Product assembly is often one of the last steps in the production process. Product assembly is often carried out by workers (assemblers) rather than robots, as it is generally challenging to adapt automation to any product. When assembling complex products, it can take a long time before the assembler masters all the steps and can assemble the product independently. Training time has no added value; therefore, it should be reduced as much as possible. This paper presents a custom-developed system that enables the guided assembly of complex and diverse products using modern technologies. The system is based on pick-to-light (PTL) modules, used primarily in logistics as an additional aid in the order picking process, and Computer Vision technology. The designed system includes a personal computer (PC), several custom-developed PTL modules and a USB camera. The PC with a touchscreen visualizes the assembly process and allows the assembler to interact with the system. The developed PC application guides the operator through the assembly process by showing all the necessary assembly steps and parts. Two-step verification is used to ensure that the correct part is picked out of the bin, first by checking that the correct pushbutton on the PTL module has been pressed and second by using a camera with a Computer Vision algorithm. The paper is supported by a use case demonstrating that the proposed system reduces the assembly time of the used product. The presented solution is scalable and flexible as it can be easily adapted to show the assembly steps of another product. [ABSTRACT FROM AUTHOR]

This article concerns the research of the HUBO full-body scanner, which includes the analysis and selection of the scanner's geometrical parameters in order to obtain the highest possible accuracy of the reconstruction of a human figure. In the scanner version analyzed in this paper, smartphone cameras are used as sensors. In order to process the collected photos into a 3D model, the photogrammetry technique is applied. As part of the work, dependencies between the geometrical parameters of the scanner are derived, which allows to significantly reduce the number of degrees of freedom in the selection of its geometrical parameters. Based on these dependencies, a numerical analysis is carried out, as a result of which the initial values of the geometrical parameters are pre-selected and distribution of scanner cameras is visualized. As part of the experimental research, the influence of selected scanner parameters on the scanning accuracy is analyzed. For the experimental research, a specially prepared dummy was used instead of the participation of a real human, which allowed to ensure the constancy of the scanned object. The accuracy of the object reconstruction was assessed in relation to the reference 3D model obtained with a scanner of superior measurement uncertainty. On the basis of the conducted research, a method for the selection of the scanner's geometrical parameters was finally verified, leading to the arrangement of cameras around a human, which guarantees high accuracy of the reconstruction. Additionally, to quantify the results, the quality rates were used, taking into account not only the obtained measurement uncertainty of the scanner, but also the processing time and the resulting efficiency. [ABSTRACT FROM AUTHOR]

The existing multi-manipulator sorting method for gangue that utilizes a multi-task allocation strategy is not satisfactory. The single manipulator working space is fixed, lowering the cooperation degree between the manipulators and leading to a low sorting rate. Therefore, this paper proposes a multi-manipulator cooperative sorting method that can work globally. First, a benefit function based on the sorting time and quality of the gangue is constructed by combining the gangue flow information and the manipulator state. The time parameter is obtained via the manipulator's dynamic target tracking trajectory planning algorithm based on PID control. Secondly, the benefits matrix is standardized and updated many times to improve the Hungarian algorithm to achieve task allocation, and the initial solution with priority is obtained. Finally, the solutions are analyzed and processed cooperatively in order of priority. The conflicts between multiple robotic arms are eliminated through task cooperation and trajectory cooperation until the sorting task that the robot arm can execute is obtained from the allocation results. Experiments involving different sorting methods were completed on a multi-arm coal and gangue sorting experimental robot platform. The experimental results show that the sorting efficiency of the proposed method is about 10% and 20% higher than that of the fixed space dynamic and designated space fixed points methods, respectively, under different belt speeds. This method can guarantee system benefits, effectively implements cooperative control of multi-manipulator operations in the whole area, and improves the efficiency of coal gangue sorting. [ABSTRACT FROM AUTHOR]

With the development of portable EEG acquisition systems, the collected EEG has gradually changed from being multi-channel to few-channel or single-channel, thus the removal of single-channel EEG signal artifacts is extremely significant. For the artifact removal of single-channel EEG signals, the current mainstream method is generally a combination of the decomposition method and the blind source separation (BSS) method. Between them, a combination of empirical mode decomposition (EMD) and its derivative methods and ICA has been used in single-channel EEG artifact removal. However, EMD is prone to modal mixing and it has no relevant theoretical basis, thus it is not as good as variational modal decomposition (VMD) in terms of the decomposition effect. In the ICA algorithm, the implementation method based on high-order statistics is widely used, but it is not as effective as the implementation method based on second order statistics in processing EMG artifacts. Therefore, aiming at the main artifacts in single-channel EEG signals, including EOG and EMG artifacts, this paper proposed a method of artifact removal combining variational mode decomposition (VMD) and second order blind identification (SOBI). Semi-simulation experiments show that, compared with the existing EEMD-SOBI method, this method has a better removal effect on EOG and EMG artifacts, and can preserve useful information to the greatest extent. [ABSTRACT FROM AUTHOR]

This paper proposes a method to improve the angular velocity measured by a low-cost magnetic rotary encoder attached to a brushed direct current (DC) motor. The low-cost magnetic rotary encoder used in brushed DC motors use to have a small magnetic ring attached to the rotational axis and one or more fixed Hall-effect sensors next to the magnet. Then, the Hall-effect sensors provide digital pulses with a duration and frequency proportional to the angular rotational velocity of the shaft of the encoder. The drawback of this mass produced rotary encoder is that any structural misalignment between the rotating magnetic field and the Hall-effect sensors produces asymmetric pulses that reduces the precision of the estimation of the angular velocity. The hypothesis of this paper is that the information provided by this low-cost magnetic rotary encoder can be processed and improved in order to obtain an accurate and precise estimation of the angular rotational velocity. The methodology proposed has been validated in four compact motorizations obtaining a reduction in the ripple of the estimation of the angular rotational velocity of: 4.93%, 59.43%, 76.49%, and 86.75%. This improvement has the advantage that it does not add time delays and does not increases the overall cost of the rotary encoder. These results showed the real dimension of this structural misalignment problem and the great improvement in precision that can be achieved. [ABSTRACT FROM AUTHOR]

The detection and localization of the ball in sport videos is crucial to better understand events and actions occurring in those sports. Despite recent advances in the field of object detection, the automatic detection of balls remains a challenging task due to the unsteady nature of balls in images. In this paper, we address the detection of small, fast-moving balls in sport video data and introduce a real-time ball detection approach based on the YOLOv3 object detection model. We apply specific adjustments to the network architecture and training process in order to enhance the detection accuracy and speed: We facilitate an efficient integration of motion information, avoiding a complex modification of the network architecture. Furthermore, we present a customized detection approach that is designed to primarily focus on the detection of small objects. We integrate domain-specific knowledge to adapt image pre-processing and a data augmentation strategy that takes advantage of the special features of balls in images in order to improve the generalization ability of the detection network. We demonstrate that the general trade-off between detection speed and accuracy of the YOLOv3 model can be enhanced in consideration of domain-specific prior knowledge. [ABSTRACT FROM AUTHOR]

The main problem for the expansion of the use of microfluidic paper-based analytical devices and, thus, their mass production is their inherent lack of fluid flow control due to its uncontrolled fabrication protocols. To address this issue, the first step is the generation of uniform and reliable microfluidic channels. The most common paper microfluidic fabrication method is wax printing, which consists of two parts, printing and heating, where heating is a critical step for the fabrication of reproducible device dimensions. In order to bring paper-based devices to success, it is essential to optimize the fabrication process in order to always get a reproducible device. Therefore, the optimization of the heating process and the analysis of the parameters that could affect the final dimensions of the device, such as its shape, the width of the wax barrier and the internal area of the device, were performed. Moreover, we present a method to predict reproducible devices with controlled working areas in a simple manner. [ABSTRACT FROM AUTHOR]

As one classical anomaly detection technology, support vector data description (SVDD) has been successfully applied to nonlinear chemical process monitoring. However, the basic SVDD model cannot achieve a satisfactory fault detection performance in the complicated cases because of its intrinsic shallow learning structure. Motivated by the deep learning theory, one improved SVDD method, called ensemble deep SVDD (EDeSVDD), is proposed in order to monitor the process faults more effectively. In the proposed method, a deep support vector data description (DeSVDD) framework is firstly constructed by introducing the deep feature extraction procedure. Different to the traditional SVDD with only one feature extraction layer, DeSVDD is designed with multi-layer feature extraction structure and optimized by minimizing the data-enclosing hypersphere with the regularization of the deep network weights. Further considering the problem that DeSVDD monitoring performance is easily affected by the model structure and the initial weight parameters, an ensemble DeSVDD (EDeSVDD) is presented by applying the ensemble learning strategy based on Bayesian inference. A series of DeSVDD sub-models are generated at the parameter level and the structure level, respectively. These two levels of sub-models are integrated for a holistic monitoring model. To identify the cause variables for the detected faults, a fault isolation scheme is designed by applying the distance correlation coefficients to measure the nonlinear dependency between the original variables and the holistic monitoring index. The applications to the Tennessee Eastman process demonstrate that the proposed EDeSVDD model outperforms the traditional SVDD model and the DeSVDD model in terms of fault detection performance and can identify the fault cause variables effectively. [ABSTRACT FROM AUTHOR]

Roadside light detection and ranging (LiDAR) is an emerging traffic data collection device and has recently been deployed in different transportation areas. The current data processing algorithms for roadside LiDAR are usually developed assuming normal weather conditions. Adverse weather conditions, such as windy and snowy conditions, could be challenges for data processing. This paper examines the performance of the state-of-the-art data processing algorithms developed for roadside LiDAR under adverse weather and then composed an improved background filtering and object clustering method in order to process the roadside LiDAR data, which was proven to perform better under windy and snowy weather. The testing results showed that the accuracy of the background filtering and point clustering was greatly improved compared to the state-of-the-art methods. With this new approach, vehicles can be identified with relatively high accuracy under windy and snowy weather. [ABSTRACT FROM AUTHOR]

Bin-picking of small parcels and other textureless planar-faced objects is a common task at warehouses. A general color image–based vision-guided robot picking system requires feature extraction and goal image preparation of various objects. However, feature extraction for goal image matching is difficult for textureless objects. Further, prior preparation of huge numbers of goal images is impractical at a warehouse. In this paper, we propose a novel depth image–based vision-guided robot bin-picking system for textureless planar-faced objects. Our method uses a deep convolutional neural network (DCNN) model that is trained on 15,000 annotated depth images synthetically generated in a physics simulator to directly predict grasp points without object segmentation. Unlike previous studies that predicted grasp points for a robot suction hand with only one vacuum cup, our DCNN also predicts optimal grasp patterns for a hand with two vacuum cups (left cup on, right cup on, or both cups on). Further, we propose a surface feature descriptor to extract surface features (center position and normal) and refine the predicted grasp point position, removing the need for texture features for vision-guided robot control and sim-to-real modification for DCNN model training. Experimental results demonstrate the efficiency of our system, namely that a robot with 7 degrees of freedom can pick randomly posed textureless boxes in a cluttered environment with a 97.5% success rate at speeds exceeding 1000 pieces per hour. [ABSTRACT FROM AUTHOR]

As the fundamental element of the Internet of Things, the QR code has become increasingly crucial for connecting online and offline services. Concerning e-commerce and logistics, we mainly focus on how to identify QR codes quickly and accurately. An adaptive binarization approach is proposed to solve the problem of uneven illumination in warehouse automatic sorting systems. Guided by cognitive modeling, we adaptively select the block window of the QR code for robust binarization under uneven illumination. The proposed method can eliminate the impact of uneven illumination of QR codes effectively whilst meeting the real-time needs in the automatic warehouse sorting. Experimental results have demonstrated the superiority of the proposed approach when benchmarked with several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In this paper, a cluster-based approach is used to address the distributed fusion estimation problem (filtering and fixed-point smoothing) for discrete-time stochastic signals in the presence of random deception attacks. At each sampling time, measured outputs of the signal are provided by a networked system, whose sensors are grouped into clusters. Each cluster is connected to a local processor which gathers the measured outputs of its sensors and, in turn, the local processors of all clusters are connected with a global fusion center. The proposed cluster-based fusion estimation structure involves two stages. First, every single sensor in a cluster transmits its observations to the corresponding local processor, where least-squares local estimators are designed by an innovation approach. During this transmission, deception attacks to the sensor measurements may be randomly launched by an adversary, with known probabilities of success that may be different at each sensor. In the second stage, the local estimators are sent to the fusion center, where they are combined to generate the proposed fusion estimators. The covariance-based design of the distributed fusion filtering and fixed-point smoothing algorithms does not require full knowledge of the signal evolution model, but only the first and second order moments of the processes involved in the observation model. Simulations are provided to illustrate the theoretical results and analyze the effect of the attack success probability on the estimation performance. [ABSTRACT FROM AUTHOR]

Many logistics companies adopt a manual order picking system. In related research, the effect of emotion and engagement on work efficiency and human errors was verified. However, related research has not established a method to predict emotion and engagement during work with high exercise intensity. Therefore, important variables for predicting the emotion and engagement during work with high exercise intensity are not clear. In this study, to clarify the mechanism of occurrence of emotion and engagement during order picking. Then, we clarify the explanatory variables which are important in predicting the emotion and engagement during work with high exercise intensity. We conducted verification experiments. We compared the accuracy of estimating human emotion and engagement by inputting pulse wave, eye movements, and movements to deep neural networks. We showed that emotion and engagement during order picking can be predicted from the behavior of the worker with an accuracy of error rate of 0.12 or less. Moreover, we have constructed a psychological model based on the questionnaire results and show that the work efficiency of workers is improved by giving them clear targets. [ABSTRACT FROM AUTHOR]