Coffee is main agricultural product of export in Honduras, during the 2016-2017 harvest 9.5 million (46 kg) bags of coffee were exported, this represents around 5 % of the GDP (Gross Domestic Product) and approximately 30 % of agricultural GDP in Honduras generating profits for about 1 billion dollars per year. In recent years’ coffee production has decreased significantly due to migration issues, leaving farms with no workers. Manual methods of coffee harvest take long times and are not cost effective. A single crop could take several days and its highly labor intensive. This research work aims to present a system that detects and classify a coffee fruit, which allows coffee producers to reduce costs, time and increase the quality of final product.Using a methodology with a qualitative approach and an experimental design, an algorithm was designed to classify the coffee fruit as “ripe” or “not ripe”. The deep learning algorithm was trained with 196 images, where 108 were positives and 88 negatives. As results the system can classify correctly 41/42 tests, having an efficiency of 97.6 %. Therefore, it is concluded that the recognition of coffee fruit with artificial vision and neural networks allows coffee producers to accelerate the process and increase quality.

Owing to their compliance with most shapes, soft actuators are regarded as cost-effective solutions for grasping irregular objects. The material properties of nonlinear elastic polymers are considered necessary for the correct implementation of these actuators. The analysis tends to be complex even for simple movements defined by theoretically infinite degrees of freedom. This study offers a mathematical model that outlines a relationship between the energy provided by a pressure source and the expected behavior of multi-chamber pneumatic soft actuators through hyper-elastic material deformation interpretation, geometric approximations, and the vectorial representations of their segments. Digitally analyzed empirical results measured through lateral pictures of an actuator were taken at different pressure references. Direct comparisons between the average value of the tested angles and those calculated through the tuned mathematical model provide a maximum error of 0.647° for small deformations and an improved accuracy at higher pressure inputs. This study offers a valid tool applicable to the design of soft actuators and their further analysis without the need for overly complex methods.

Owing to their ease of implementation, proportional-integral-derivative (PID) control systems are widely used to control physical systems. However, when environmental disturbances or changes in system parameters occur, the complexity of tuning the gains of PID controllers increases because, in these cases, their performance decreases. To solve this problem, an AI-based online self-tuning algorithm adjusts the PID gains when system parameters are changed. Thus, the objective of this study was to develop a PID control algorithm with adaptive parameter tuning using artificial hydrocarbon networks, which is a supervised learning artificial intelligence technique inspired by hydrocarbon networks. Artificial hydrocarbon networks were designed to be trained using a prior set of data. Therefore, the motivation of this study was to demonstrate that they can be trained in real time for use in the control of nonlinear systems. Because this type of network has not been commonly used for this specific application, existing studies on adaptive control based on artificial neural networks were taken as a reference. The AMSGrad optimization algorithm was used to train the parameters in real time, for which a “continuous” model of artificial hydrocarbon networks was also proposed. Finally, an algorithm capable of adapting to variations in the operating conditions of a tank system was successfully designed, although its performance was similar to that of the Ziegler-Nichols method.

Mobile robotics has been used in recent years to provide various types of services in fields such as agriculture, surveillance, rehabilitation, space exploration, and logistics, among others. In many cases, mobile robots need to overcome complex obstacles where traditional wheels are not the best solution, and many researchers have proposed legged wheel hybrid designs. This paper presents a comprehensive study on the effect of the geometry of legged wheels on the performance of mobile robots in climbing stairs. The method used to develop this research is dynamic simulation, in which the parameters that affect the kinematics and dynamics of the robot are included. Subsequently, the results of how the robot manages to perform the test, the torque of the motors, and the contact force of the wheels are analyzed. The main hypothesis of this research is that the opening of the legs of the wheels is a geometric parameter that determines whether the structure will be able to climb the stairs. After 63 simulations, the proportional relationship between the diagonal of the stands and the opening of the wheel legs ranges between 1.11 and 1.53. This parameter showed a strong correlation with the torque of the motors and significant differences in terms of the simulations that succeeded in climbing the stairs and those that did not. These results were used to state a design method for flat, robotic structures using legged wheels. This method was validated by an additional simulation that was performed for a four-legged wheel. It can be concluded that the contribution of this work is a series of steps with which to design these mechanical structures to climb the stairs based on the proposed indicator.

This paper provides a general description of the steps followed to construct an automated Voice Picking Robot. The proposed unit can avoid obstacles, identify objects picking and placing them at their right location. The model is equipped with wireless connectivity to allow its remote control, and it features four wheels and 45-degree rollers. The robot materials are aluminum plates, Polylactic Acid plastic, six NEMA 17 stepper motors, and the ATmega3287P microcontroller. Testing conducted on the robot functioning demonstrates that it behaves as expected and that it can become a useful technological aid in a variety of logistics, industrial, or manufacturing processes.

Existing direct and inverse kinematic models of planar parallel robots assume that the robot’s active joints are all at the bases. However, this approach becomes excessively complex when modeling a planar parallel robot in which the active joints are within one single kinematic chain. To address this problem, our article unveils an alternative for a 3RRR symmetric planar robot modeling technique for the derivation of the robot workspace and the analysis of its direct and inverse kinematics. The workspace was defined using a system of inequalities, and the direct and inverse kinematics models were generated using vectorial analysis and an optimized geometrical approach, respectively. The resulting models are systematically presented and validated. Two final model renditions are delivered supplying a thorough equation analysis and an applicability discussion based on the importance of the robot’s mobile platform orientation. The advantages of this model are discussed in comparison to the traditional modeling approach: whereas conventional techniques require the solution of complex eighth-degree polynomials for the analysis of the active joint configuration of these robots, these models provide an efficient back-of-the-envelope analysis approach that requires the solution of a simple second-degree polynomial.