Santiago Tosetti

Direct visual tracking control of remote cellular robots

Abstract This paper presents the design of a stable non-linear control system for the remote visual tracking of cellular robots. The robots are controlled through visual feedback based on the processing of the image captured by a fixed video camera observing the workspace. The control algorithm is based only on measurements on the image plane of the visual camera–direct visual control–thus avoiding the problems related to camera calibration. In addition, the camera plane may have any (unknown) orientation with respect to the robot workspace. The controller uses an on-line estimation of the image Jacobians. Considering the Jacobians’ estimation errors, the control system is capable of tracking a reference point moving on the image plane–defining the reference trajectory–with an ultimately bounded error. An obstacle avoidance strategy is also developed in the same context, based on the visual impedance concept. Experimental results show the performance of the overall control system.

Neural Network-Based Irrigation Control for Precision Agriculture

In the present work, a design of an automatic irrigation neuro-controller for precision agriculture is presented. The irrigation neuro-controller regulates the level of moisture in agricultural soils, specifically in the root zone, using an on-off control-type that opens and closes the valves of the irrigation system (IS). The changes in the moisture levels in the roots area can be modeled as a non-linear differential function depending mainly on the amount of water supplied by the IS, the crop consumption, and the soil characteristics. This dynamic model is identified by a neural network (NN). After the NN is trained, it is used as a prediction model within the control algorithm, which determines the irrigation time necessary to take the moisture level up to a user desired level. At the same time, the NN is re-trained in order to get a new and improved model of the moistures soils, giving to the IS the capability of adapt to the changing soil characteristics and water crop needs. In this work, it is also presented the main advantages of using this irrigation closed-loop adaptive controller instead of traditional systems that operates to open-loop, such as timed irrigation control.

Optimization methodology to fruit grove mapping in precision agriculture

A method capable of efficiently mapping a semi-structured environment is presented.Grove mapping based on LiDAR and the GPS locations of the corner trees is given.An optimization tool that adjusts measurements acquired by a mobile robot is used.The technique was tested in an olive grove located in San Juan - Argentina.It is incorporated a novel filtering technique of unlikely data. The mapping of partially structured agricultural environments is a valuable resource for precision agriculture. In this paper, a technique for the mapping of a fruit grove by a mobile robot is proposed, which uses only front laser information of the environment and the exact position of the grove corners. This method is based on solving an optimization problem with nonlinear constraints, which reduces errors inherent to the measurement process, ensuring an efficient and precise map construction. The resulting algorithm was tested in a real orchard environment. For this, it is also developed a data filtering method capable to comply efficiently the observation-feature matching. The maximum average error obtained by the methodology in simulations was about 13cm, and in real experimentation was about 36cm.

Intelligent Irrigation in Grapevines: A Way to Obtain Different Wine Characteristics

This work presents the field implementation of an intelligent irrigation controller, applied to grapevine crops. The proposed irrigation system includes the moisture measurements and the development of an intelligent control system, in order to maintain the moisture level around a set value. Moisture reference value for different irrigation treatments, such as water stress or field capacity, is decided by the user according to the desired enological grape quality. This technology is an appropriate tool for crops managing and, in addition helps to overcome difficulties imposed by a growing water demand and to reduce extraction costs.

Laboratorio Virtual y Remoto para Simular, Monitorizar y Controlar un Sistema de Riego por Goteo en Olivos

This article presents the development and application of a laboratory designed for simulating control an irrigation strategies that can be then applied in field, in a drip irrigation system installed in a pilot plant. The system presented in this work involves the development of a simulation software, the monitoring of different variables, and the remote control of a pilot plant. This article also describes other components of the system, such as the moisture sensor network, the communication network, and the remainder hardware required for the remote control. The laboratory as well as the pilot plant is installed in olive groves located in the province of San Juan, Argentina.

Dynamic Modeling and Identification of an Agriculture Autonomous Vehicle

In the present article, it is presented the modeling and identification of an autonomous vehicle that has been designed for agricultural tasks. With the purpose of defining the best model structure, different models have been presented. Particularly, it is assumed that the lateral and longitudinal dynamics are decoupled dynamics, and based on this assumption these are modeled and identified in an isolated way. Particular emphasis was made in lateral and rotational dynamics. The vehicle under study is a quadricycle (ATV) that has been modified and adapted to work in an autonomous way. It has been presented simulation proofs and experimentation with the real vehicle that allows guaranteeing the performance of the developed models.

Control of a production-inventory system using a PID controller and demand prediction

Abstract A common and important problem in business is the determination of inventory policies for a production system within a changing business environment and market demand. In this paper, an automatic pipeline feedback order-based production control system (APIOBPCS), considering a demand with cyclic and stochastic components, is proposed. The dynamics and delays of the production process are modeled as a pure delay. The control system structure consists of a PID (Proportional, Integrative and Derivative) controller with an Extended Kalman Filter-based demand prediction. The main objective of the this dynamic controller is to stabilize and regulate the inventory levels in function of a desired set-point level. The Extended Kalman Filter (EKF) estimates the parameters of a Volterra time-series model to forecast future values of the demand. A control error analysis is also performed for the proposed inventory control system, in order to obtain bounds for the control errors and to probe its stability. This methodology is useful to make an appropriate decision about the desired inventory level for a given demand prediction error. The inventory control system is evaluated by simulations showing a good performance.

Bounded memory probabilistic mapping of out-of-structure objects in fruit crops environments

Abstract Spatial awareness and memory are key factors for a robot to evolve in semi-structured and dynamic environments as those found in agriculture, and particularly in fruit crops where the trees are regularly distributed. This paper proposes a probabilistic method for mapping out-of-structure objects (weeds, workers, machines, fallen branches, etc.) using a Kernel density estimator. The methodology has theoretical and practical advantages over the well-known occupancy grid map estimator such as optimization of storage resources, online update, high resolution, and straightforward adaptability to dynamic environments. An example application would be a control scheme through which a robot is able to perform cautious navigation in areas with high probability of finding obstacles. Simulations and experiments show that large extensions can be online mapped with few data and high spatial resolution.

Use of site-specific measurement stations for irrigation management and crops water demand monitoring. An experience in almonds, in the province of San Juan, Argentina

In the context of modern agriculture, it is important for farmers and agricultural consultants to count with technological tools that allow an appropriate monitoring of the development of the crop, and of the water and fertilizers applied among other. These objectives can be achieved if information of the soil-water-crop-atmosphere complex system is organized and on-line available for the users. This work describes our experience during the installation and set up in field of a group of measurement stations, intended to give site-specific information regarding what is going inside the crop. Each station measures the ambient temperature and humidity at four different heights, the atmospheric pressure, the solar radiation index, wind velocity and direction, crop temperature, trunk growth, soil moisture at four depths, soil temperature, amount of water supplied, and pressure and caudal in the pipes. Information is saved, at regular intervals, in a data logger, and then transmitted to a PC located in an office. The system is complemented with a PLC-based irrigation controller that allows to automatically performing the irrigation schedule. The experience was realized in a young almonds crop, located in the province of San Juan. It is expected to use this system along the 2015/2016 season in order to determine the crop coefficient (Kc) in four almond varieties and verify the effects of applying regulated deficit irrigation (RDF) treatments.

Approximate dynamic programming based controller for a production-inventory system

This article presents the design and development of a control system based on Approximate Dynamic Programming, applied to a particular case of a single echelon, single product production inventory-system. The structure presented in this work allows to find an approximate solution to the optimal control problem. The developed controller is feasible to be implemented in real-time mode. In addition it also allows to manage dynamic variations in the process to be controlled. Theoretical results are obtained and compared to a classical LQR controller. Simulation experiments showed the good performance and the feasibility of the proposed structure.