In construction, a large-scale 3D printing method for construction is used to build houses quickly, based on Computerized Aid Design. Currently, the construction industry is beginning to apply quite a lot of 3D printing technologies to create buildings that require a quick construction time and complex structures that classical methods cannot implement. In this paper, a Cable-Driven Parallel Robot (CDPR) is described for the 3D printing of concrete for building a house. The CDPR structures are designed to be suitable for 3D printing in a large workspace. A linear programming algorithm was used to quickly calculate the inverse kinematic problem with the force equilibrium condition for the moving platform; this method is suitable for the flexible configuration of a CDPR corresponding to the various spaces. Cable sagging was also analyzed by the Trust-Region-Dogleg algorithm to increase the accuracy of the inverse kinematic problem for controlling the robot to perform basic trajectory interpolation movements. The paper also covers the design and analysis of a concrete extruder for the 3D printing method. The analytical results are experimented with based on a prototype of the CDPR to evaluate the work ability and suitability of this design. The results show that this design is suitable for 3D printing in construction, with high precision and a stable trajectory printing. The robot configuration can be easily adjusted and calculated to suit the construction space, while maintaining rigidity as well as an adequate operating space. The actuators are compact, easy to disassemble and move, and capable of accommodating a wide variety of dimensions.

The goal of the global path planning task is to produce an optimal safe path for robot respect to the given map. There are many global path planning methods that have been studied. In this paper, we propose a novel Hybrid Genetic Algorithm (HGA) that is used to generating smooth paths for differential wheeled robots. The main idea of HGA is to provide the dynamic mutation rate and switchable global-local search method to the mutation operator of ordinary genetic algorithm. By deploying these modifications, the premature convergence of the generic genetic algorithm and the high time-consuming fitness calculation of the memetic algorithm are reduced. HGA also takes care of chromosome length (defined by the size of a set of points that construct a path) by applying the population replacement method. Our algorithm satisfies the important criteria in the path planning task: safe and minimum-length. Based on continuous-curvature Piecewise Cubic Bezier Curve, HGA directly provides the smoothed paths for differential wheeled robots. Therefore, our proposed algorithm does not need any third-party algorithm for smoothing planned path. Several experiments regarding the proposed algorithm on our robot and its results are analyzed and presented.

Currently, most agricultural products in developing countries are exported to many countries around the world. Therefore, the classification of these products according to different standards is necessary. In Vietnam, dragon fruit is considered as the fruit with the highest export rate. Currently, the classification of dragon fruit is carried manually, lead to low-quality classification high labor costs. Therefore, this study describes an automatic dragon fruit classifying system using non-destructive measurements, based on a convolutional neural network (CNN). This classifying system uses a combination of a model of machine learning and image processing using a convolutional neural network to identify the external features of dragon fruits; the fruits are then classified and evaluated by groups. The dragon fruit is recognized by the system, which extracts the objects combined with the signal obtained from the loadcell to calculate and determine dragon fruit in each group. The training data are collected from the dragon fruit processing system, with a dataset of images obtained from more than 1287 dragon fruits, to train the model. In this system, the classification of the processing speed and accuracy are the two most important factors. The results show that the classification system achieves high efficiency. The system is effective with existing dragon fruit types. In Vietnamese factories, the processing speed of the system increases the sorting capacity of export packing facilities to six times higher than that of the manual method, with an accuracy of more than 96%.

Triple-layered composite plates are created by joining three composite layers using shear connectors. These layers, which are assumed to be always in contact and able to move relatively to each other during deformation, could be the same or different in geometric dimensions and material. They are applied in various engineering fields such as ship-building, aircraft wing manufacturing, etc. However, there are only a few publications regarding the calculation of this kind of plate. This paper proposes novel equations, which utilize Mindlin’s theory and finite element modelling to simulate the forced vibration of triple-layered composite plates with layers connected by shear connectors subjected to a moving load. Moreover, a Matlab computation program is introduced to verify the reliability of the proposed equations, as well as the influence of some parameters, such as boundary conditions, the rigidity of the shear connector, thickness-to-length ratio, and the moving load velocity on the dynamic response of the composite plate.

In this work, we present a complete hybrid navigation system for a two-wheel differential drive mobile robot that includes static-environment- global-path planning and dynamic environment obstacle-avoidance tasks. By the given map, we propose a multi-agent A-heuristic algorithm for finding the optimal obstacle-free path. The result is less time-consuming and involves fewer changes in path length when dealing with multiple agents than the ordinary A-heuristic algorithm. The obtained path was smoothed based on curvature-continuous piecewise cubic Bézier curve (C² PCBC) before being used as a trajectory by the robot. In the second task of the robot, we supposed any unforeseen obstacles were recognized and their moving frames were estimated by the sensors when the robot tracked on the trajectory. In order to adapt to the dynamic environment with the presence of constant velocity obstacles, a weighted-sum model (WSM) was employed. The 2D LiDAR data, the robot’s frame and the detected moving obstacle’s frame were collected and fed to the WSM during the movement of the robot. Through this information, the WSM chose a temporary target and a C² PCBC-based subtrajectory was generated that led the robot to avoid the presented obstacle. Experimentally, the proposed model responded well in existing feasible solution cases with fine-tuned model parameters. We further provide the re-path algorithm that helped the robot track on the initial trajectory. The experimental results show the real-time performance of the system applied in our robot.

Nowadays, mangoes and other fruits are classified according to human perception of low productivity, which is a poor quality of classification. Therefore, in this study, we suggest a novel evaluation of internal quality focused on external features of mango as well as its weight. The results show that evaluation is more effective than using only one of the external features or weight combining an expensive nondestructive (NDT) measurement. Grading of fruits is implemented by four models of machine learning as Random Forest (RF), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN). Models have inputs such as length, width, defect, weight, and outputs being mango classifications such as grade G₁, G₂, and G₃. The unstructured data of 4983 of captured images combining with load-cell signals are transferred to structured data to generate a completed dataset including density. The data normalization and elimination of outliers (DNEO) are used to create a better dataset which prepared for machine learning algorithms. Moreover, an unbiased performance estimate for the training process carried out by the nested cross-validation (NCV) method. In the experiment, the methods of machine learning have high accurate over 87.9%, especially the model of RF gets 98.1% accuracy.