Over the past few years, decentralization of multi-agent robotic systems has become an important research area. These systems do not depend on a central control unit, which enables the control and assignment of distributed, asynchronous and robust tasks. However, in some cases, the network communication process between robotic agents is overlooked, and this creates a dependency for each agent to maintain a permanent link with nearby units to be able to fulfill its goals. This article describes a communication framework, where each agent in the system can leave the network or accept new connections, sending its information based on the transfer history of all nodes in the network. To this end, each agent needs to comply with four processes to participate in the system, plus a fifth process for data transfer to the nearest nodes that is based on Received Signal Strength Indicator (RSSI) and data history. To validate this framework, we use differential robotic agents and a monitoring agent to generate a topological map of an environment with the presence of obstacles.
Planning tasks performed by a robotic agent require previous access to a map of the environment and the position where the agent is located. This creates a problem when the agent is placed in a new environment. To solve it, the RA must execute the task known as Simultaneous Location and Mapping (SLAM) which locates the agent in the new environment while generating the map at the same time, geometrically or topologically. One of the big problems in SLAM is the amount of memory required for the RA to store the details of the environment map. In addition, environment data capture needs a robust processing unit to handle data representation, which in turn is reflected in a bigger RA unit with higher energy use and production costs. This article presents a design for a system capable of a decentralized implementation of SLAM that is based on the use of a system comprised of wireless agents capable of storing and distributing the map as it is being generated by the RA. The proposed system was validated in an environment with a surface area of 25 m , in which it was capable of generating the topological map online, and without relying on external units connected to the system.
The analysis of traffic jams has become an interesting topic for smart cities. This analysis allows to perform studies for the reduction of environmental contamination, fuel consumption and the driving time. In this article, a wireless autonomous system to estimate the vehicle traffic, oriented to be used in the Internet of Things (IoT) applications is presented. In order to perform the estimation of the speed and orientation of the moving vehicles, the optical flow technique is used through the method of Gunnar Farneback, applying segmentation by morphology to avoid false information captured in situations where the optical flow may not detect the movement. To process and monitor the information in real time, the data is sent to the cloud using Flask framework, making it available for multiple users. The system is designed and verified through a Raspberrypi 2 development card, with a wi-fi module compatible with Ad-Hoc networks
Due to the development of Internet of Things (IoT) and extensive use of Wireless Sensor Networks (WSN) in precision agriculture, we take potato crops as a study domain for sensors and their behavior on their deployment in a particular area. We study how application responsiveness is determined by performance metrics in wireless communications. We also describe how data collected by the sensors aids in finding solutions to the cropfis domain problems through data aggregation over time. The aim of this work is to analyze traffic behavior of a grid-topology wireless sensor network, chosen based on the distance between rows and potato plants within a hectare, by analyzing the performance of a service request from an IoT application.
Counting the number of pedestrians in urban environments has become an area of interest over the past few years. Its applications include studies to control vehicular traffic lights, urban planning, market studies, and detection of abnormal behaviors. However, these tasks require the use of intelligent algorithms of high computational demand that need to be trained in the environment being studied. This article presents a novel method to estimate pedestrian flow in uncontrolled environments by using the fractal dimension measured through the box-counting algorithm, which does not require the use of image pre-processing and intelligent algorithms. Four scenarios were used to validate the method presented in this article, of which the last scene was a low-light surveillance video, showing experimental results with a mean relative error of 4.92% when counting pedestrians. After comparing the results with other techniques that depend on intelligent algorithms, we can confirm that this method achieves improved performance in the estimation of pedestrian traffic.
In planning tasks a Robotic Agent (RA) must know a priori the environment map where it is located, which is a problem if the same RA faces a different environment. To overcome this problem, the RA must perform the task of Simultaneous Localization and Mapping (SLAM), to locate the agent in the environment while simultaneously generate the geometric or topological map. This article presents the design of a decentralized online system for SLAM by an autonomous RA, responsible for placing wireless sensor nodes based on its Received Signal Strength Indication (RSSI) and programming them with the estimated position by processing the RA odometry, creating a Multi-Agent System (MAS) by the construction of a Wireless Sensor Network (WSN). The validation of this system is driven in a non-uniform two-dimensional environment with respect to RA, showing the generation of an online topological map with an error of 8%, without the dependence of a central unit.