Kelen Cristiane Teixeira Vivaldini

Robotic forklifts for intelligent warehouses: Routing, path planning, and auto-localization

Today, robotic systems are bridging the gaps between global economy, social needs, and logistics focusing on sustainable development solutions. Everyday new robotic applications can be found in literature and media. Some of them are basically entertainment toys. Nevertheless, the great majority of them is used inside industries, performing several tasks (painting, welding, moving materials, etc.). In a scenario of global economy growth, any sustainable solution that can reduce the product final cost is welcome. This article presents researches on robotic forklifts for intelligent warehouses developed at the Mechatronics Lab at USP-EESC in Brazil. We show three key-routines that determine the Automated Guided Vehicle (AGV) behavior: the routing algorithm (that computes the overall task execution time and the minimum global path of each AGV using a topological map of the warehouse), the local path planning algorithm (based on A* it searches for the local minimum path between two nodes of the warehouse topological map), and an auto-localization algorithm (that applies an Extended Kalman Filter - EKF - to estimate the AGVs actual positions). In order to validate the algorithms developed, several tests were carried out using the simulation software Player/Stage. The results obtained were encouraging and the router developed was able to solve traffic jams and collisions, before sending the final paths to the robots. In a near future all algorithms will be implemented using mini- robotic forklifts and a scaled environment built in our lab.

Battery state estimation for applications in intelligent warehouses

When it comes to AGVs (Automated Guide Vehicles) working in intelligent warehouse systems it is necessary to take into account that the use of batteries may impact the performance of the overall system. They need to be recharged or changed, and the time required to execute these operations might interfere in the AGV availability. Therefore, it is necessary to carry out a battery management procedure to ensure that the batteries have sufficient charges to perform the desired tasks. This paper describes a method based on the Extended Kalman Filter (EKF) to estimate the Batteries State of Charge (SOC). The estimated consumption is compared with the SOC obtained by the EKF. A series of experiments using mini-robotic forklifts were performed to evaluate the method. The experimental results have shown its effectiveness using resistive loads. This methodology allowed estimating the battery consumption for a certain route of the mini-robotic forklift in the warehouse and verifying the load capacity available for the mini-robotic forklift to accomplish a task assigned by the warehouse routing system.

Automatic detection of Ceratocystis wilt in Eucalyptus crops from aerial images

One of the challenges in precision agriculture is the detection of diseased crops in agricultural environments. This paper presents a methodology to detect the Ceratocystis wilt disease in Eucalyptus crops. An unmanned aerial vehicle is used to obtain high-resolution RGB images of a predefined area. The methodology enables the extraction of visual features from image regions and uses several supervised machine learning (ML) techniques to classify regions into three classes: ground, healthy and diseased plants. Several learning techniques were compared using data obtained from a commercial Eucalyptus plantation. Experimental results show that the GP learning model is more reliable than the other learning methods for accurately identifying diseased trees.

Route planning for active classification with UAVs

The mapping of agricultural crops by capturing images obtained with UAVs enables fast environmental monitoring and diagnosis in large areas. Airborne monitoring in agriculture can a substantially impacts on the identification of diseases and produce accurate information on affected areas. The problem can be formulated as a classification task on aerial images with significant opportunities to impact other fields. This paper presents an active learning method through route planning for improvements in the knowledge on visited areas and minimization uncertainties about the classification of diseases in crops. Binary Logistic Regression and Gaussian Process were used for the detection of pathologies and map interpolation, respectively. A Bayesian optimization strategy is also proposed for the planning of an informative trajectory, which resulted in a maximized search for affected areas in an initially unknown environment.

Comprehensive Review of the Dispatching, Scheduling and Routing of AGVs

Automated Guided Vehicle System (AGVS) has become an important strategic tool for automated warehouses. In a very competitive business scenario, they can increase productivity and reduce costs of FMS (Flexible Manufacturing System) transportation systems. The AGV System provides efficient material flow and distribution among workstations at the right time and place. To attend such requirements, AGVS involves dispatching and scheduling of tasks and routing of AGVs. Some studies have approached such procedures in a similar form, although they have different functionalities. This paper reviews the literature related to the dispatching, scheduling and routing of AGVs (Automated Guided Vehicles) and highlights their main differences in comparison with the common management of vehicles transportation systems. To obtain a theoretical base, the definitions of dispatching, routing and scheduling procedures for materials handling applications are presented and the main methods to solve them are discussed.

Intelligent Warehouse Product Position Optimization by Applying a Multi-criteria Tool

The operational optimization process applied to warehouses can lead to cost reductions by means of the correct positioning of the products. The definition of the product localization will determine the distance to be traveled to handle the materials and directly impact on warehousing costs. In this context, this article focuses on the positioning optimization of finished products in intelligent warehouses, which allows reducing the distance traveled and the order fulfillment time. The Analytic Hierarchy Process (AHP) was used for the optimization process. This technique consists in hierarchizing the products analyzed by employing pairwise comparisons through the judgment of their characteristics (size, fragility and weight). A simulated intelligent warehouse environment was used to analyze the results of allocation of the product based on AHP tool, where task were distributed for AGVs (Automated Guided Vehicle). As a result, a better positioning of the products and a reduction in the operation time of material handling were achieved.

PID control applied on a line-follower AGV using a RGB camera

This paper aims to develop a control algorithm for a unicycle type AGV (Automated Guided Vehicle) to follow a trajectory predefined by a line avoiding oscillation on its movements. At the first tests the PID controller will be applied. On some applications cameras are used to help a robot follow a track (instead of infra red sensors), determining if it should keep a forward movement or turn to any sides. On this application, the camera is used in the PID control loop as a sensor to give feedback information, thus evaluating the efficiency of the control system allied with computer vision. This type of application simplifies the sensing system of a line follower AGV and makes possible to use the camera to other means, such as token and color identification. Considering a simplified model and a classic control technique, the results presented have showed stability on lower speeds.

Battery charge state estimate for a robotic forklift routing system

In the context of robotic forklift, battery management is essential and may be considered a key issue in the logistic system management for intelligent warehouses, where goods must be delivered on time according to the monitoring battery State of Charge (SOC) applied to routing system is a tendency to be considered in the planning of warehouses. Based on this scenario, this paper describes a method based on the use of Extended Kalman Filter (EKF), which uses the cell combined model to estimate the battery SOC. Tests were performed to evaluate the estimated battery consumption considering Open Voltage Circuit (OCV) and SOC EKF method applied in a mini robotic forklift. It was possible to verify the battery consumption needed to execute a determined task path and assign a route for the robotic forklift considering the actual SOC.

Communication Infrastructure in the Centralized Management System for Intelligent Warehouses

The automation of logistic systems is essential to improve productivity and reduce costs. An effective way to introduce automation in materials handling is applying Automated Guided Vehicles (AGVs). The design of an AGV System requires decision making regarding the best strategies to solve the various problems associated with its functioning (efficient routes, AGVs selection, collision, deadlocks, battery management, etc.). In this context, this paper presents a centralized architecture AGV System for intelligent warehouses. In this architecture, the Intelligent Supervisor controls the AGVs and exchanges information with the Warehouse Management System (WMS). A middleware-based communication infrastructure was developed to ensure the communication interoperability among the components of the system and the information manager. By measuring the response time and performing tests of the network overload for a different number of AGVs controlled by the Intelligent Supervisor, a reliable standard to exchange information could be achieved.