Fig 3 - uploaded by Juan Calderon
Content may be subject to copyright.
Source publication
An important application of cooperative robotics is search and rescue of victims in disaster zones. The cooperation between robots requires multiple factors that need to be taken into consideration such as communication between agents, distributed control, power autonomy, cooperation, navigation strategy, locomotion, among others. This work focuses...
Contexts in source publication
Context 1
... Obstacles: This part of the experiment depicts how the swarm goes around obstacles in order to avoid them. This is possible, because the obstacles are relatively small and the agents are able to tolerate the obstacles between the attraction forces, as depicted by fig.3. This case uses nine obstacles distributed throughout the area between the start point and the goal point. ...
Citations
... Collaborative robots, often referred to as cooperative robots or multi-agent systems, can significantly improve human life in various ways. They can assist in heavy object manipulation [3], [4], perform inspection and infrastructure services [5], monitor and map the environment [6], and engage in search and rescue operations [7]. Additionally, in the field of healthcare, these robots can be utilized, for example, for remote surgeries [8], where the Internet of Things (IoT) can also play a role, or in rehabilitation programs to assist individuals with mobility impairments. ...
... Robot swarms use simple local behavioral rules to achieve an emergent behavior over time. The study of swarms gained considerable interest in the scientific community due to its applicability in a variety of areas, such as search and rescue (Chen, Wang and Li (2009) ;Skinner, Urdahl, Harrington, Balchanos, Garcia and Mavris (2018); León, Cardona, Botello and Calderón (2016)), space exploration (Nguyen, Harman and Fairchild (2019); Marco Sabatini and Giovanni B.Palmerini (2009); Huan Huang, Leping Yang, Yan-wei Zhu and Yuan-wen Zhang (2014)) and disaster relief (Schurr, Marecki, Tambe, Scerri, Kasinadhuni and Lewis (2005); Kazi T.A.Siddiqui, David Feil-Seifer, Tianyi Jiang, Sonu Jose, Siming Liu and Sushil Louis (2017); Subramanium Ganesan, Manish Shakya, Aqueel F.Aqueel and Lakshmi M.Nambiar (2011)). As a part of these various applications, swarm members may need to achieve an agreement over a set of variables using local interactions among themselves. ...
Reaching a consensus in a swarm of robots is one of the fundamental problems in swarm robotics, examining the possibility of reaching an agreement within the swarm members. The recently-introduced contamination problem offers a new perspective of the problem, in which swarm members should reach a consensus in spite of the existence of adversarial members that intentionally act to divert the swarm members towards a different consensus. In this paper, we search for a consensus-reaching algorithm under the contamination problem setting by taking a top-down approach: We transform the problem to a centralized two-player game in which each player controls the behavior of a subset of the swarm, trying to force the entire swarm to converge to an agreement on its own value. We define a performance metric for each players performance, proving a correlation between this metric and the chances of the player to win the game. We then present the globally optimal solution to the game and prove that unfortunately it is unattainable in a distributed setting, due to the challenging characteristics of the swarm members. We therefore examine the problem on a simplified swarm model, and compare the performance of the globally optimal strategy with locally optimal strategies, demonstrating its superiority in rigorous simulation experiments.
... Current scientific works have addressed the problem raised and have used multi-agent robotics as a solution strategy. For example, in [1] is approached the robot swarm theory for navigation, obstacle avoidance, and victims localization. Similarly, in [2] is presented a navigation and detection victims system using robot swarm. ...
... SR plays an important role in the development of collective artificial intelligence. SR promises to be efficient in several application areas such as search and rescue in disaster zones [3], [10], supply chain management, precision agriculture, remote sensing, surveillance, last-mile package delivery, and an ample number of military applications among others. ...
Monitoring environmental variables in lower layers of the atmosphere is an important activity to measure changes that result from natural events and human interventions. Volcano eruptions, commercial aviation, and the massive spread of pesticides using light aircraft are just some examples of low layer atmosphere polluters. Twice a day, every day of the year, weather balloons are released simultaneously from almost 900 locations worldwide to monitor environmental variables. The flight of these synthetic rubber balloons last for around 2 hours, then they become pollution too. Recent advances in small unmanned aerial vehicles (UAVs) with built-in sensors and their emerging role in the business supply chain make UAVs ideal participants for environmental monitoring. In this paper, we present an incentive mechanism for UAV-Crowdsensing. The core of the proposed mechanism consists of a recurrent reverse action and a recruitment model. By these two components, the system encourages UAVs sensing from locations that maximize volume coverage within a given budget. Through extensive simulations, we evaluate the performance of the proposed incentive mechanism.
... Finalmente, en [37] se encuentra un estudio semejante, pero alejado al objetivo principal de este trabajo donde proponen la solución para el procesamiento de datos y la difusión de estos en un enjambre de drones en un centro urbano, utilizando técnicas de aprendizaje para equilibrar de manera adaptativa la velocidad de transmisión entre los agentes, donde el enjambre se adapta mediante la ejecución de transiciones de estado mientras están conectados, también se tiene en cuenta el equilibrio en el almacenamiento de datos y la asignación de energía que se le da a cada dron, entre los datos que estos pueden tomar se encuentra el ruido del ambiente, entre otros. Realizando un contraste con la idea a desarrollar en este trabajo, la referencia encontrada logra obtener la comunicación eficiente entre los 4. JUSTIFICACIÓN Las aplicaciones de vehículos aéreos no tripulados (UAVs), ha permitido facilitar las diferentes tareas que el ser humano realiza, disminuyendo el tiempo de su ejecución y mejorando la eficiencia con la que actúan, como por ejemplo el seguimiento de los cultivos, logrando obtener mejores productos de las cosechas como se muestra en el documento "Vehículos Aéreos no tripulados, Drones" [14]. ...
Autonomous navigation in unstructured environments is one of the most challenging tasks for unmanned aerial vehicles (UAVs). To face this kind of challenge, it is necessary to use complex control and learning algorithms that collaborate in processes of adaptation of the unmanned vehicle to the continuous changes of the environment in which it navigates. One of the most promising fields of artificial intelligence in unsupervised learning tasks is Reinforcement Learning. This work proposes the use of Q-Learning in real time, to generate the navigation learning system of a UAV. Since the learning process takes a long time and the UAVs have a flight autonomy quite limited by the battery capacity. For this, it is proposed to use a simulation environment that allows the evolution of the learning system regardless of the limitations of autonomy of a real robot, where the robot will learn to navigate autonomously and avoid obstacles. A proposal is presented using Reinforcement Learning more specifically the Q-Learning technique to solve the problem of autonomous navigation in a UAV, in the proposed solution the states of the agent are established taking into account several factors, such as the reading of the sensors in the detection of obstacles, the distance between the agent and the target, and the direction where the GOAL is located. For this solution, 8 actions are established, which are the movements that the UAV can perform, a policy of rewards and punishments to evaluate the learning of the agent. The technique proposed in the MATLAB mathematical software and the virtual simulation environment V-REP is implemented. To get as close as possible to a real scenario such as the rescue of people in natural disasters, in the delivery of packages, in precision agriculture, among other applications.
... First, the development of a navigation swarm system based on the artificial potential approach, which uses attraction and repulsion forces to keep swarm communication between agents and avoiding collisions, respectively. Additionally, an attraction force pointing to the location of a possible victim is added to the navigation system in the same way as proposed in our previous projects [14][15][16]. Second, the policy of sub-swarm generation when some robots detect a possible victim, through creating a weighted graph based on the distance in order to perform a k-nearest algorithm and then break the agents' links to the main swarm. ...
Cooperative behaviors in multi-robot systems emerge as an excellent alternative for collaboration in search and rescue tasks to accelerate the finding survivors process and avoid risking additional lives. Although there are still several challenges to be solved, such as communication between agents, power autonomy, navigation strategies, and detection and classification of survivors, among others. The research work presented by this paper focuses on the navigation of the robot swarm and the consensus of the agents applied to the victims detection. The navigation strategy is based on the application of particle swarm theory, where the robots are the agents of the swarm. The attraction and repulsion forces that are typical in swarm particle systems are used by the multi-robot system to avoid obstacles, keep group compact and navigate to a target location. The victims are detected by each agent separately, however, once the agents agree on the existence of a possible victim, these agents separate from the general swarm by creating a sub-swarm. The sub-swarm agents use a modified rendezvous consensus algorithm to perform a formation control around the possible victims and then carry out a consensus of the information acquired by the sensors with the aim to determine the victim existence. Several experiments were conducted to test navigation, obstacle avoidance, and search for victims. Additionally, different situations were simulated with the consensus algorithm. The results show how swarm theory allows the multi-robot system navigates avoiding obstacles, finding possible victims, and settling down their possible use in search and rescue operations.
... Some works as [6] performed a fuzzy logic system in which a robot swarm navigates through a place based on the information from leader, usually known as leader formation control. On the other hand, artificial potential functions is another approach to navigate in a non-convex space, working as magnetic fields with an attraction to the target place and repulsion effect to avoid collisions between robots and the robots with obstacles as is depicted in [7], [8]. ...
This paper proposes the use of reinforcement learning to provide navigation and adaptation skills to a mobile robot in unknown environments. The use of sensor information is developed instead of the spatial location of the robot with the aim to perform the navigation and exploration process. The use of the Q-learning algorithm is proposed, however, the states are established based on the information coming from the sensors. A reward policy is applied to focus on guide the robot away from obstacles and allowing the exploration of unknown environments. Additionally, an exploration policy is generated which collaborates in the adaptation process of the robot. The complete system is evaluated using a robot simulation environment known as V-Rep. The results show that the robot learns to navigate avoiding to collide with obstacles, besides presenting skills to explore unknown environments.
... Considerando el enfoque de este proyecto de grado, se buscaron proyectos que estudiaron temas similares a los abordados en este trabajo. José León León en su trabajo: simulación de enjambres de robots en labores de exploración para detección de posibles víctimas [17,19,20] el cual fue presentado en 2017 como Tesis de Maestría de la Facultad de Ingeniería Electrónica de la Universidad Santo Tomás de Colombia, propone y simula un algoritmo para la navegación y el consenso de múltiples agentes enfocado a localizar víctimas en desastres. El autor propone para la navegación un algoritmo bio-inspirado en las abejas basado en fuerzas virtuales de atracción y repulsión, y para el consenso un protocolo distribuido para tomar una decisión cuando se disponga de la evidencia suficiente. ...
En este trabajo se hace uso de técnicas de aprendizaje por refuerzo (Q-Learning) con el objetivo de entrenar un grupo de robots para generar comportamientos de enjambre.
Se presentan dos posibles soluciones con diferentes enfoques. En la primera solución propuesta se establecen los estados del robot en función de la distancia de sus dos vecinos más cercanos. En la segunda solución propuesta se definen un radio de atracción y otro radio de repulsión, y los estados se establecen según la cantidad de vecinos dentro de cada uno de los radios divididos en los cuatro cuadrantes locales del robot. Para cada solución propuesta se definen las acciones del robot y se propone una política de premios y castigos. Cada robot se conecta con sus vecinos una vez que ha alcanzado una distancia prudente. Se hace uso de teoría de grafos para medir la conectividad del enjambre y saber si la topología del grafo que forma el enjambre al final de la simulación es conexo o no. En este trabajo se asume que la comunicación de cada agente con sus vecinos ya está resuelta. Se realizan varias pruebas en Matlab para cada una de las soluciones propuestas variando el número de robots del enjambre. Finalmente se prueba la segunda solución propuesta en V-rep usando robots cuadricópteros virtuales.
Este documento está estructurado de la siguiente forma: En el capítulo 1 y 2 se define el problema y la justificación. El capítulo 3 y 4 contienen una revisión de trabajos relacionados con robótica de enjambre y se definen los objetivos del proyecto. En el capítulo 5 se presentan los conceptos teóricos necesarios utilizados en el desarrollo de este proyecto. En el capítulo 6 y 7 se muestra el diseño metodológico, la administración del proyecto, cronograma de actividades y presupuesto para el proyecto. En el capítulo 8 se muestra el trabajo previo a la realización de este proyecto usando lógica difusa. En el capítulo 9 y 10 se muestra el diseño del proyecto, el planteamiento de las soluciones propuestas, - las pruebas y resultados de las dos soluciones. Finalmente, las conclusiones se muestran en el capítulo 11.
... Thus, those left behind and with close proximity to the target form a new swarm, this new swarm changes its state to still and send the target's coordinates to the rescue station. Fig. 1: Sub-Swarm [8] As can be seen in Figure 1 the targets are colored in blue, and the swarm agents are colored with red. Around the targets there is a group of agents, those are the ones which were left behind from the main swarm and thus, forming a new small swarm. ...
... There are many applications where multi-robot systems become important because they can perform well in multiple tasks, for example in [2] they show how to make localization of the robots using relative observation between them, this is one of the main challenges to work with multi-robot systems, it is necessary to know all time about the self-localization and the distance with the neighbors. Another approach has been bioinspiration of animals such as ants or the case of swarm bees presented in [3], [4], since it may be the case to have a swarm of robots working on the same goal, avoiding collisions and seeking for points of interest how is shown in [5]. Similarly in [6] explore the idea of the implementation of heterogeneous robot network for search and rescue operations. ...
This paper proposes an algorithm based on a fuzzy logic approach, capable to guide a robot swarm with the aim to keep a leader-follower formation without colliding with other swarm agents. The fuzzy system is programmed and evaluated originally in Matlab, where several experiments were performed. The results depicted a robot swarm showing some bio-inspired behaviors, such as swarm agents surrounding the leader when it is in a static position or when it is traveling from one place to another place. Finally, the proposed fuzzy system was implemented on a drone swarm using V-Rep. The drones simulation shows the swarm navigating together and keeping the leader in the center of the swarm when it is static and following the leader when it is moving. These results could be evaluated in a future work using drone robot swarm in real environments.
