Nature-Inspired Swarm Intelligence and Its Applications

This chapter discusses and reviews the application of swarm intelligence (SI) and swarm robotics (SR) to architecture and construction from a history of science and technology perspective. In a first step, it explores the conceptual entanglements of swarm intelligence and adaptive environments and situates them in the context of a recent theoretical discourse about “media ecologies”. The second part provides a critical overview of seminal SI approaches for architectural design. These scrutinize novel connections between architecture as a site of material composition and as a site of spatial practices by computer experiments in software environments. Its guiding hypothesis is that SI technologies here are primarily used to create diversity. Subsequently, the third part of the chapter examines in which ways recent advances in collective robotics lead to further materializations of the adaptive capabilities of swarming that go beyond software applications. It presents three state-of-the-art examples of SR for architectural construction and demonstrates that SR in architectural construction—in contrast to the paradigm of diversity discussed in the context of architectural design—work best in context with a high degree of standardization and pre-defined modularization, or, on the basis of regularity.

Swarm intelligence, inspired by the collective behavior observed in social organisms, has emerged as a powerful paradigm in both natural and artificial systems. The concept of a swarm refers to a large group of simple agents that interact locally with one another and their environment, giving rise to complex and intelligent behavior at the group level. Swarm intelligence, on the other hand, represents the ability of a swarm to self-organize, adapt, and solve complex problems without central control. In nature, swarms of social insects such as bees, ants, termites, and birds exhibit remarkable abilities in foraging, navigation, resource allocation, and defense. These organisms demonstrate how the interactions of simple individuals can lead to efficient and robust solutions to various challenges faced in their environments. In artificial systems, researchers have successfully translated the principles of swarm intelligence into algorithms and techniques for optimization, decision-making, and problem-solving. Popular swarm intelligence algorithms, such as Ant Colony Optimization, Particle Swarm Optimization, and Artificial Bee Colony, have shown great promise in tackling complex optimization and search tasks. This paper provides an overview of the fundamental concepts of swarm intelligence and explores the similarities and differences between natural and artificial swarms. It delves into the principles of self-organization, decentralized decision-making, and adaptation that underpin swarm intelligence, allowing these systems to cope with dynamic and uncertain environments. Furthermore, the paper examines the application domains of swarm intelligence, ranging from robotics and autonomous systems to data clustering, image processing, and network routing. The potential of swarm robotics in solving real-world challenges, such as environmental monitoring, disaster response, and precision agriculture, is also explored. Swarm intelligence presents a compelling avenue for understanding and harnessing emergent collective behavior in both biological and computational contexts. The interplay of simplicity, local interactions, and adaptation enables swarms to tackle complex problems efficiently, making them a valuable source of inspiration for the design of intelligent systems in various fields. The study of swarm intelligence continues to advance, offering exciting possibilities for creating adaptive, robust, and scalable solutions in the ever-evolving landscape of artificial intelligence and beyond.

Background: With the curiosity of exploring the underwater world, science has devised various technologies and machines that can help them in performing activities like exploring, navigating and plunging into the unknown world of oceanography. Underwater Robot or vehicle can be claimed as an outcome of extensive research done by the scientists who aimed at discovering the unknown mysterious world of ocean and how it can benefit humanity. Swarm robotics is an entirely new section of robotics that has been developed based on swarm intelligence. Considering the fact, swarm robotics being still in nuptial stage, researchers have provided immense contribution with an aim to develop this technology. The objective of the paper is to present a comprehensive review covering the various technical and conceptual aspects of underwater swarm robotic system. Methods: A systematic review on state-of-the-art has been performed where contributions of various researchers was considered. The study emphasis on the concepts, technical background, architecture and communication medium along with its applicability in various fields that also include various issues and challenges faced while attaining them. Results: The incorporation of swarm intelligence in underwater robotics provides a new angle altogether into the working pattern of underwater robotic system. Conclusion: The article is a systematic presentation of swarm robot technologies, their mechanisms, conceived and designed communication medium with respect to adaptability of the vehicle to the versatile nature of water. The paper delineates the various conceptual and technical details and its beneficence to humanity.

Fuzzy systems (FSs) have been extensively applied to automatic control, pattern recognition, and decision analysis. However, a common bottleneck is encountered in the derivation of fuzzy rules, which is often difficult, time consuming, and relies on expert knowledge. To automate the design of FSs, many metaheuristic learning algorithms have been proposed. One major optimization category uses Swarm Intelligence (SI) model (Kennedy et al., 2001). The SI technique studies collective behavior in decentralized systems. Its development was based on mimicking the social behavior of animals or insects in an effort to find the optima in the problem space. SI models are initialized with a population of random solutions. One well-known SI model is particle swarm optimization (PSO) (Kennedy & Eberhart, 1995). Many modified PSO models have been proposed and successfully applied to different optimization problems (Clerc & Kennedy, 2002; Bergh & Engelbrecht, 2004; Ratnaweera et al., 2004; Juang, 2004; Kennedy & Mendes, 2006; Parrott & Li, 2006; Chen & Li, 2007). FS design using PSO has also been proposed in several studies (Juang, 2004; Chatterjee et al., 2005; Juang et al., 2007; Araujo & Coelho, 2008; Sharma et al., 2009). Another well-known SI is ant colony optimization (ACO) (Dorigo & Stutzle, 2004). The ACO technique is inspired by real ant colony observations. It is a multi-agent approach that was originally proposed to solve difficult discrete combinatorial optimization problems, such as the traveling salesman problem (TSP) (Dorigo et al., 1996; Dorigo & Gambardella, 1997). In the original ACO meta-heuristic, artificial ant colonies cooperate to find good solutions for difficult discrete optimization problems. Different ACO models have been applied to FS design problems (Cassillas et al., 2000; Cassillas et al., 2005; Mucientes & Casillas; 2007; Juang & Lo, 2007; Juang et al., 2008; Juang & Lu; 2009). In (Cassillas et al.,2000; Mucientes & Casillas; 2007; Juang et al., 2008; Juang & Lu; 2009), the FS input space was partitioned in grid type with antecedent part parameters of an FS manually assigned in advance. In (Juang & Lo, 2007), the FS input space was flexibly partitioned using a fuzzy clustering-like algorithm in order to reduce the total number of rules. For all of these studies, the consequent part parameters were optimized in discrete space using ACO. Since only the consequent part parameters are optimized, and the optimization space is restricted to be discrete, the designed FSs are unsuitable for problems where high accuracy is a major concern. Source: Fuzzy Systems, Book edited by: Ahmad Taher Azar, ISBN 978-953-7619-92-3, pp. 216, February 2010, INTECH, Croatia, downloaded from SCIYO.COM

a great interest has evolved recently in the study and synthesis of cooperative robots with decentralized control. The basic problem is the development of efficient algorithms that could be inspired from the behavior of social insects. This paper develops from different perspective; the theory of decentralized discrete control systems. This leads to a little increase in the computational complexity in each individual, still non-intelligent, robot. Swarm intelligence appears as a result of the mutual control signals that replace coordination signals in usual centralized control systems. The study of asymptotic stability and the convergence to the global goal follows directly from the stability of algorithms derived within system theory and are reached stepwise in an efficient way. Through the paper we derive the necessary algorithms and procedures and finally we introduce the experimental results that validate the developed theory.

Swarm intelligence systems for transportation engineering: Principles and applications

This thesis presents some different techniques designed to drive a swarm of robots in an a-priori unknown environment in order to move the group from a starting area to a final one avoiding obstacles. The presented techniques are based on two different theories used alone or in combination: Swarm Intelligence (SI) and Graph Theory. Both theories are based on the study of interactions between different entities (also called agents or units) in Multi- Agent Systems (MAS). The first one belongs to the Artificial Intelligence context and the second one to the Distributed Systems context. These theories, each one from its own point of view, exploit the emergent behaviour that comes from the interactive work of the entities, in order to achieve a common goal. The features of flexibility and adaptability of the swarm have been exploited with the aim to overcome and to minimize difficulties and problems that can affect one or more units of the group, having minimal impact to the whole group and to the common main target. Another aim of this work is to show the importance of the information shared between the units of the group, such as the communication topology, because it helps to maintain the environmental information, detected by each single agent, updated among the swarm. Swarm Intelligence has been applied to the presented technique, through the Particle Swarm Optimization algorithm (PSO), taking advantage of its features as a navigation system. The Graph Theory has been applied by exploiting Consensus and the application of the agreement protocol with the aim to maintain the units in a desired and controlled formation. This approach has been followed in order to conserve the power of PSO and to control part of its random behaviour with a distributed control algorithm like Consensus.

The contemporary robotics technology is broadening its applications from factory to more general-purpose applications in domestic and public use, e.g., partner to the elderly, rehabilitations, search and rescue, etc. If robotics technology is to be successful in such complex, unstructured, dynamic environments with high level of uncertainties, it will need to meet new levels of robustness, physical dexterity and cognitive capability. This presentation discusses an emerging field called cognitive robotics. The one solution for building cognitive robots in order to cope with imprecise, incomplete, and inconsistent information that arises in complex technical systems, is computational intelligence that uses biologically inspired soft-computing techniques, like artificial neural networks, evolutionary approaches, and swarm intelligence. Research topics, features and challenges of cognitive robotics will be introduced. Key challenges in constructing these robots include the systematic treatment of uncertainties, the modeling of the environmental state, the coordination of teams of cooperating robots in dynamic environments, the interaction with humans, development, and learning. It is important to notice that in order to realize cognitive robots many overlapping disciplines are needed, e.g. robotics, artificial intelligence, cognitive science, neuroscience, biology, psychology, and cybernetics. Some important research topics from this area will be specially analyzed: Advanced perception (vision, tactile sensing, haptic sensing, multi-sensor fusion), Advanced locomotion and manipulation, SLAM, Learning including imitation learning, reinforcement learning, supervised learning, Human-robot interaction, Reasoning and Making Decisions, Intelligent planning and navigation, Swarm intelligence, etc. A case study of cognitive methods applied for humanoid and service mobile robots will be introduced.

Multi-robot systems have drawn the attention of many different research communities, such as physics, electronics, control, computer science, mathematics, and biology. Motivated by the growing popularity of multi-robot system and related coordination approaches, this paper surveys and analyzes the relevant literature, including six classification dimensions: system architectures, communication and robotic sensor networks, swarm intelligence and swarm robotics, cooperation among robots, applications, and research projects.

Swarm robotics is an approach to the coordination of large numbers of robots that has become an increasingly popular field of research in recent years, not least because properly engineered robot swarms are scalable, flexible, and robust, making them an attractive alternative to single-robot systems in many application domains. Since its inception, the field of swarm robotics has grown beyond its roots in purely decentralised control inspired by social insect behaviour, now often utilising hybrid centralised/decentralised control architectures that incorporate human operators who guide swarm actions during tasks such as firefighting, or the localisation of radiation sources. This kind of human-swarm interaction has attracted significant interest from the research community, spawning an entire sub-field of its own that investigates how human operators, supervisors, and team-mates can interact with robot swarms and receive feedback from them. To date, human-swarm control methods such as the use of graphical user interfaces and spatial gestures have received much attention, but there has been little investigation into the potential of controlling swarm robotic systems with an operator’s voice. The few studies that have explored this idea are restricted to the use of specific predefined phrases that the human operator is required to learn, resulting in interactions that are unnatural in comparison to the way a human would normally express themselves in speech. In this paper, we present a novel architecture for conversational human-swarm interaction that addresses these issues, allowing swarm robotic systems to be engineered in such a way that a human operator can guide a swarm using spoken dialogue in a more natural manner.

This work proposes a control law for efficient area coverage and pop-up threat detection by a robot swarm inspired by the dynamical behavior of ant colonies foraging for food. In the first part, performance metrics that evaluate area coverage in terms of characteristics such as rate, completeness and frequency of coverage are developed. Next, the Keller–Segel model for chemotaxis is adapted to develop a virtual-pheromone-based method of area coverage. Sensitivity analyses with respect to the model parameters such as rate of pheromone diffusion, rate of pheromone evaporation, and white noise intensity then identify and establish noise intensity as the most influential parameter in the context of efficient area coverage and establish trends between these different parameters which can be generalized to other pheromone-based systems. In addition, the analyses yield optimal values for the model parameters with respect to the proposed performance metrics. A finite resolution of model parameter values were tested to determine the optimal one. In the second part of the work, the control framework is expanded to investigate the efficacy of non-Brownian search strategies characterized by Levy flight, a non-Brownian stochastic process which takes variable path lengths from a power-law distribution. It is shown that a control law that incorporates a combination of gradient following and Levy flight provides superior area coverage and pop-up threat detection by the swarm. The results highlight both the potential benefits of robot swarm design inspired by social insect behavior as well as the interesting possibilities suggested by considerations of non-Brownian noise.

This chapter mainly aims to introduce some widely used ACO algorithms and their origins, such as the AS, EAS, MMAS, and so on. It is found that all concerns are focused on the pheromone update strategy. Some uses the best-so-far-ant or the iteration-best ant independently/interactively to update the trail that ants travelled. Meanwhile, the update law may differ a bit for different ACO algorithms. Among the four ACO algorithms, two versions have received great popularities in various applications, i.e. AS and MMAS. Another contribution in this chapter is the extension of the general ACO algorithm to the system of ants of different tasks, and its behaviour is modelled and implemented in the track initiation problems. Simulation results are also presented to show the effectiveness of the novel ACO algorithm. According to the example presented in this chapter, we believe that the general framework of AS can be modified to solve various optimal or non-optimal problems.

Negotiation mechanism for self-organized scheduling system with collective intelligence

Swarm intelligence is a relatively new approach to problem solving that takes inspiration from the social behaviors of insects and other animals. Ants, in particular, have inspired a number of methods and techniques among which the most studied and successful is the general-purpose optimization technique, also known as ant colony optimization, In computer science and operations research, the ant colony optimization algorithm (ACO) is a probabilistic technique for solving computational problems which can be reduced to finding good paths through graphs. Ant Colony Optimization (ACO) algorithm is used to arrive at the best solution for TSP. In this article, the researcher has introduced ways to use a great deluge algorithm with the ACO algorithm to increase the ability of the ACO in finding the best tour (optimal tour). Results are given for different TSP problems by using ACO with great deluge and other local search algorithms.

Since introduced bio-inspired algorithms have proven be the superior algorithm in many optimization problems. Near optimum performance of these algorithms along with their very simple calculation rules has resulted in widespread utilization of biological computing in many fields of science like communications, robotics, software engineering, networks, etc. Swarm intelligence observed in social insects such as ants, resulting in a behavior beyond the scope of individual members of society, has been an important source of inspiration for these algorithms. Ant Colony Optimization, a particularly successful research direction in swarm intelligence based algorithms dedicated to discrete optimization problems, has been effectively used in a variety of combinatorial problems such as quadratic assignments, traveling salesman problems, and routing in telecommunication networks. In this paper we propose a new algorithm named Multi Resolution Ant Colony, which uses swarm intelligence in a continuous (non-discrete) environment, for finding extremes, i. e. minimums and maximums, of a function. Genetic Algorithm (GA), up to now, has been a candidate for solving these kinds of problems when analytical methods failed. The dependency of analytical methods on initial condition is one of the most important reasons to utilize Genetic Algorithms instead. The method we present has advances over GA in that it can either, find the extremes itself (simulation results show the out-performance of our algorithm to GA in this area), or be fed to analytical methods (in low resolutions steps, not possible in GA).