Fact-checked by Grok 2 weeks ago

Swarm intelligence

Swarm intelligence is defined as the of decentralized, self-organized systems, either natural or artificial, consisting of numerous simple agents that interact locally with each other and their to achieve complex global patterns without centralized control. This emergent behavior is inspired by natural phenomena observed in social insects, bird flocks, fish schools, and bacterial , where individual agents follow simple rules leading to robust, adaptive group outcomes. The field of swarm intelligence gained prominence in the mid-1990s through the development of computational algorithms mimicking these natural processes for problem-solving. Key examples include Ant Colony Optimization (ACO), originally developed by Marco Dorigo in the early 1990s and presented in a seminal 1996 paper with Vittorio Maniezzo and Alberto Colorni, which simulates ant foraging trails using pheromone-based mechanisms to solve problems like the traveling salesman problem. Another foundational algorithm is Particle Swarm Optimization (PSO), introduced by and Russell C. Eberhart in 1995, which models the social dynamics of bird flocking or fish schooling to iteratively search for optimal solutions in continuous spaces. These bio-inspired metaheuristics form the core of swarm intelligence, emphasizing population-based search strategies that balance exploration and exploitation. Swarm intelligence has broad applications across optimization, , , and engineering, enabling efficient solutions to complex, NP-hard problems where traditional methods falter. In , it facilitates multi-agent coordination for tasks like or , as seen in swarm robotic systems that exhibit and . In , algorithms like PSO and ACO enhance tasks such as , clustering, and training, improving predictive accuracy in large datasets. Ongoing research continues to refine these techniques, integrating them with other paradigms for real-world challenges in areas like IoT security and sustainable computing.

Fundamentals

Definition and Principles

Swarm intelligence (SI) is a branch of that emulates the of decentralized, self-organized systems found in , such as colonies, where numerous simple agents interact locally based on limited information to produce robust and adaptive global patterns without requiring central coordination. This approach contrasts with traditional AI paradigms, which typically depend on centralized and explicit rule-based programming, by emphasizing distributed and emergent intelligence arising from bottom-up interactions. In SI, unlike general multi-agent systems that may involve hierarchical or explicit communication protocols, the focus lies on bio-inspired mechanisms that foster and collective problem-solving through local rules alone. The foundational principles of swarm intelligence revolve around several core concepts that enable such emergent behaviors. ensures no single agent or leader controls the system, with coordination achieved solely through interactions. describes how complex, adaptive global structures—such as efficient paths in ant colonies—arise unpredictably from the application of straightforward local rules by individual agents. occurs as agents adapt dynamically to their environment via indirect communication methods like (where agents modify the environment to influence others) or direct mechanisms such as and repulsion forces, without external direction. Additionally, robustness stems from the system's , allowing it to maintain functionality even if individual agents fail, while permits improved performance as the number of agents increases, mirroring natural swarms. Mathematically, agent dynamics in a generic SI system can be represented by a simple iterative update rule for position, given by \mathbf{x}_{i}(t+1) = \mathbf{x}_{i}(t) + \mathbf{v}_{i}(t+1), where \mathbf{x}_{i}(t) is the position of agent i at time t, and the velocity \mathbf{v}_{i}(t+1) is computed based on local interactions with nearby agents, such as alignment, cohesion, or separation forces. This formulation captures the essence of how local rules propagate to drive collective motion and decision-making, as seen in natural examples like ant foraging trails.

Biological Foundations

Swarm intelligence draws its foundational principles from the collective behaviors observed in various animal groups, where decentralized interactions among individuals lead to emergent group-level adaptations without central control. In social and schooling animals, these behaviors have evolved to optimize survival in complex environments, relying on simple local rules such as signaling, sensory alignment, and response to environmental cues. Insect colonies exemplify decentralized coordination through chemical and behavioral signals. , for instance, employ pheromone-based , where foragers deposit trail pheromones to guide nestmates to sources, enhancing path efficiency through that reinforces successful routes and that diminishes unused trails. This system also supports division of labor, with pheromones signaling tasks like or , allowing colonies to allocate resources dynamically. Species such as the utilize multiple pheromones for various functions, including trail pheromones like dolichodial and iridomyrmecin, and alarm pheromones, to coordinate these activities, enabling rapid to changing availability. These loops that balance and drive success in ant colonies. Honeybees demonstrate sophisticated communication via the , a vibrational signal performed inside the to convey the location of resources. The dance encodes through the of the straight "waggle run" and direction relative to the sun's position, with an angular accuracy of approximately 15 degrees, allowing recruits to navigate effectively even over kilometers. This decentralized information sharing not only facilitates foraging but also contributes to , where bees collectively adjust wing fanning and water evaporation to maintain optimal temperatures, responding to local cues from nestmates. Termite colonies showcase , an indirect coordination mechanism where environmental modifications by individuals stimulate further actions. In nest building, deposit soil pellets that alter the substrate, prompting others to add adjacent material without direct interaction, resulting in complex, self-regulating structures like ventilated mounds that maintain internal climate. This process, first described in , relies on simple response rules to traces left by prior workers, enabling scalable construction over generations. Bird and fish flocks exhibit alignment and cohesion rules that promote group integrity. In fish schooling, individuals maintain position by aligning velocities and adjusting distances for cohesion, which confuses predators through the "confusion effect," reducing individual capture risk by up to 80% in dense groups. Similarly, starling murmurations involve rapid alignment to neighbors, creating fluid shapes that dilute predation threats, with topological interactions—focusing on a fixed number of nearest neighbors—ensuring robust group cohesion under attack. For energy efficiency, some bird flocks form V-shaped patterns during migration, where trailing individuals exploit wingtip vortices generated by leaders, potentially reducing energy costs by 20-30% compared to solitary flight. These biological swarms confer evolutionary advantages through decentralized , enabling efficient , robust , and optimal without hierarchical oversight. For example, and colonies achieve higher net energy gain from food collection than solitary individuals, as collective paths minimize redundancy and maximize discovery rates. In flocks, reduces per capita predation while facilitates about threats or resources, enhancing overall in dynamic ecosystems. Such systems promote , as the loss of individuals does not collapse the group, allowing adaptation via local interactions alone.

Historical Development

Early Inspirations

The earliest conceptual inspirations for swarm intelligence trace back to ancient observations of collective behaviors in social insects. In the 4th century BCE, Aristotle documented the coordinated activities of bee swarms in his History of Animals, noting how bees cluster and divide labor within the hive, exhibiting organized foraging and swarming patterns that suggested a form of communal decision-making without apparent central control. These accounts, while anthropomorphic at times, highlighted the emergent order in insect societies, influencing later naturalists' views on decentralized coordination. By the 18th and 19th centuries, entomological studies deepened these insights through empirical observations. Pierre Huber, in his 1810 work Recherches sur les mœurs des fourmis indigènes, described colonies' division of labor, trail formation, and nest-building, emphasizing how contribute to complex structures via simple interactions. Similarly, Auguste Forel, in his late-19th-century research culminating in publications like Les fourmis de la Suisse (1874) and subsequent works on , explored in , proposing that their behaviors arise from instinctive responses rather than , paving the way for understanding emergent . In the mid-20th century, biological research formalized these ideas, particularly through the study of eusocial insects. Edward O. Wilson's 1971 book The Insect Societies synthesized observations on eusociality in ants, bees, and termites, explaining how reproductive division and cooperative care emerge from genetic relatedness and simple rules, providing a theoretical foundation for collective behaviors in insect swarms. Concurrently, studies on bird flocking, such as W.D. Hamilton's 1971 "selfish herd" theory, modeled how individuals position themselves within groups to minimize predation risk, illustrating decentralized aggregation without leadership. A pivotal concept was stigmergy, introduced by Pierre-Paul Grassé in 1959 to describe termite nest-building, where indirect communication occurs through environmental modifications like pheromone trails, enabling coordinated construction without direct interactions. These biological insights transitioned toward computational paradigms in the mid-20th century, influenced by early and . Norbert Wiener's 1948 Cybernetics: Or Control and Communication in the Animal and the Machine introduced feedback mechanisms in decentralized systems, drawing parallels between biological coordination and machine control to explain self-regulating behaviors in groups. Complementing this, John von Neumann's work in the 1940s on cellular automata, later detailed in his 1966 Theory of Self-Reproducing Automata, modeled self-organizing systems through local rules on a , serving as a precursor to simulating emergent swarm-like patterns without central authority. Jean-Louis Deneubourg's 1977 model of termite mound building further bridged and computation by using probabilistic rules to simulate pillar formation via stigmergic traces, demonstrating how local actions yield global structures.

Key Milestones and Advances

The foundations of swarm intelligence emerged in the late 1980s with Craig Reynolds' development of the model in 1987, marking the first computational simulation of behavior through decentralized rules for separation, , and cohesion among virtual agents. This work laid the groundwork for modeling emergent collective behaviors without central control. Building on this, Tamás Vicsek introduced the in 1995, which explored dynamics in systems of , revealing phase transitions from to ordered motion under noise and density variations. The saw a surge in optimization applications, beginning with Marco Dorigo's introduction of Ant Colony Optimization (ACO) in his 1992 PhD thesis, inspired by pheromone-based foraging in ants to solve combinatorial problems like the traveling salesman. This was closely followed by and Eberhart's (PSO) in 1995, which simulated social foraging in bird flocks to optimize continuous nonlinear functions through updates based on personal and global best positions. Entering the 2000s, swarm intelligence expanded with Dervis Karaboga's Artificial Bee Colony (ABC) algorithm in 2005, modeling honeybee foraging roles—employed, onlooker, and scout bees—to enhance global search in numerical optimization. During this decade, integration with evolutionary computing gained traction, hybridizing swarm methods like PSO with genetic algorithms to improve convergence and diversity in dynamic environments. Robotics applications also rose, exemplified by iRobot's SwarmBots project in the early , deploying over 100 small, collaborative robots for tasks like perimeter surveillance without explicit programming. In the and , advancements shifted toward human-AI collaboration and real-world scalability. Louis Rosenberg's Artificial Swarm Intelligence platform, launched in 2015, enabled networked human groups to form real-time "swarms" for collective decision-making, outperforming individual averages in forecasting tasks. Drone swarm technologies advanced through DARPA's Offensive Swarm-Enabled Tactics () program, initiated in 2017, which developed tactics for to swarms of up to 250 unmanned air and ground systems in urban combat simulations. Hybrids with emerged, such as applied to train neural networks for tasks including and architecture optimization in . By 2020, swarm intelligence research had produced over 10,000 publications, reflecting its maturation as a field. Real-world deployments grew, including for disaster response since 2018, where autonomous flying robots used behavior-based search to locate over 90% of simulated survivors in cluttered environments within an hour. Post-2015 innovations included quantum-inspired swarm algorithms, incorporating principles into particle updates for enhanced exploration in optimization problems. Ethical considerations in human-AI swarms also gained prominence in 2025 discussions, emphasizing governance frameworks for , , and unintended collective biases in mixed systems.

Computational Models

Boids Model

The Boids model, developed by in 1987, represents a foundational approach to simulating flocking behavior in and . Designed as a distributed behavioral model, it simulates the coordinated motion of groups such as bird flocks, fish schools, or herds through simple, local rules applied to individual agents called "" (a portmanteau of "bird-oid"). Each boid is treated as an independent actor with position, velocity, and steering capabilities, enabling realistic aggregate patterns without centralized control. This model emerged as an alternative to labor-intensive keyframe , prioritizing for efficiency in . At its core, the Boids algorithm relies on three heuristic steering behaviors that each boid computes based on its nearby neighbors, typically within a fixed perception radius. Separation prevents collisions by steering away from overcrowded flockmates; alignment promotes synchronized movement by adjusting velocity to match the average direction of neighbors; cohesion fosters group unity by steering toward the average position of neighbors. These forces are combined into a resultant steering vector using tunable weights, then scaled to a desired speed and added to the current velocity, which is clipped to a maximum value before updating the position. A common implementation of these behaviors uses the following steering forces: \mathbf{F}_{sep} = \sum_{j \in N_i} \frac{\mathbf{p}_i - \mathbf{p}_j}{|\mathbf{p}_i - \mathbf{p}_j|}, \mathbf{F}_{ali} = \frac{1}{|N_i|} \sum_{j \in N_i} \mathbf{v}_j - \mathbf{v}_i, \mathbf{F}_{coh} = \frac{1}{|N_i|} \sum_{j \in N_i} \mathbf{p}_j - \mathbf{p}_i, and \mathbf{F} = w_1 \mathbf{F}_{sep} + w_2 \mathbf{F}_{ali} + w_3 \mathbf{F}_{coh}. Implementation of the model involves iterative updates for each boid in a simulated , often in a that processes , , and motion. A basic structure is as follows:
for each time step:
    for each boid b:
        perceive neighbors within radius r
        compute F_sep, F_ali, F_coh as above
        F = w1 * F_sep + w2 * F_ali + w3 * F_coh
        F = truncate(F, max_force)
        v = truncate(v + F, max_speed)
        p = p + v * delta_time
Extensions in the 1990s incorporated advanced features, such as explicit obstacle avoidance by treating environmental objects as additional "neighbors" in the separation rule, enhancing realism in complex scenes. When executed, the model produces emergent patterns, including cohesive groups, milling formations, and dynamic structures resembling tornadoes or vortices, arising solely from local interactions without global coordination. These behaviors have been applied in , notably in the 1992 movie , where simulated swarming bats for visual effects.

Self-Propelled Particles Model

The (SPP) model, also known as the , was introduced by Tamás Vicsek and colleagues in 1995 to investigate the emergence of collective motion resembling bird flocking in systems subject to environmental noise. This physics-inspired framework models agents as self-driven particles moving at a constant speed, focusing on how local interactions lead to global order despite perturbations. Unlike deterministic rule-based approaches such as the model, which emphasize separation to avoid collisions for visual realism, the SPP model incorporates probabilistic noise in alignment to capture realistic disorder in physical systems. At its core, the model defines discrete-time dynamics where each particle i updates its direction \theta_i(t+1) based on the average orientation of neighbors N_i within an interaction radius r, perturbed by random \eta: \theta_i(t+1) = \arg\left( \sum_{j \in N_i} e^{i\theta_j(t)} \right) + \eta Here, the argument of the sum provides the direction, and \eta is uniformly distributed in [-\eta_0/2, \eta_0/2], simulating errors or environmental fluctuations. Particles move with fixed speed v_0 in their updated direction, on a periodic torus to avoid . Key parameters include particle density \rho, strength \eta_0, and interaction radius r, which collectively determine the system's behavior. Simulations of the model reveal a delineating ordered (coherent) states, where particles align into flocks moving in the same direction, from disordered states resembling random motion. A critical exists, beyond which global order breaks down, marking a continuous analogous to nonequilibrium phenomena in statistical physics; for typical densities and radii, this threshold occurs around \eta_0 \approx 0.5 radians. Below the threshold, ordered phases exhibit straight-line , while specific parameter regimes produce milling patterns (circular vortices) and (clustered arrests), highlighting the model's capacity to generate diverse collective dynamics. Subsequent refinements in the extended the original -based interactions—where neighbors are all particles within radius r—to topological interactions, where each interacts with a fixed number of nearest neighbors regardless of distance, inspired by empirical observations in bird flocks. These topological variants, such as those analyzed by Ginelli et al. in , demonstrate enhanced robustness to and density variations, with phase transitions shifting to higher levels compared to rules, thus providing a more stable framework for modeling real-world cohesion.

Other Simulation Models

In addition to flocking and alignment models, swarm intelligence simulations have explored behaviors inspired by colonies, where agents follow probabilistic rules to form efficient trails. In the late , Jean-Louis Deneubourg and colleagues developed a model of based on local deposition and trail-following, in which individual lay scent marks and select paths with probability proportional to the local concentration, leading to emergent trail formation without central coordination. This probability-based mechanism amplifies small differences in trail strength, resulting in collective optimization of paths. Extensions of this model to double-bridge experiments, where two paths of differing lengths connect a nest to food, demonstrate how initial random choices evolve into preference for the shorter route through differential reinforcement and effects. Clustering simulations draw from behaviors in tasks, such as corpse piling, adapted for grouping using local interactions. In the 1990s, Bonabeau and collaborators proposed ant-based clustering algorithms where virtual agents move data items on a grid, picking up isolated objects and depositing them near similar neighbors based on a local similarity , fostering self-organized clusters without predefined categories. The similarity is typically computed as the average distance or feature overlap between an item and its k-nearest neighbors within a sensing radius, with pickup probability decreasing as similarity increases and drop probability rising accordingly. A generic clustering rule can be sketched as follows: for an agent encountering data point o_i with neighbors \{o_j\}, the drop probability P_{drop} is P_{drop}(o_i) = \begin{cases} \frac{f(o_i)}{k(1 - f(o_i)) + f(o_i)} & \text{if } f(o_i) < \alpha \\ 0 & \text{otherwise} \end{cases} where f(o_i) is the average similarity to neighbors (e.g., f(o_i) = \frac{1}{k} \sum \frac{1}{1 + d(o_i, o_j)}, with d as Euclidean distance), k is the neighborhood size, and \alpha is a drop threshold; agents may drop virtual pheromone proportional to f(o_i) to attract similar items. This approach, extended in later variants, enables robust grouping of multidimensional data by leveraging stigmergic-like feedback from deposited items. Epidemic spreading models within swarm intelligence incorporate infection rules into agent interactions to simulate disease propagation in decentralized groups. These models reveal how swarm density and mobility amplify outbreak thresholds, with recovery or immunity rules preventing total collapse, providing insights into resilience in mobile populations. Craig Reynolds extended his early flocking work in the 2000s to interactive group behaviors, simulating autonomous agents that respond to external stimuli while maintaining cohesion. In his 2000 model, agents use layered steering forces—combining separation, alignment, and attraction with user-defined goals—to generate realistic crowd dynamics in virtual environments, emphasizing scalability for hundreds of entities. Hybrid models integrating swarm intelligence with game theory emerged in the 2010s to study strategic interactions in collectives. These frameworks combine local agent rules with payoff-based decision-making, such as particle swarm updates influenced by Nash equilibria, to model resource allocation or cooperation in dynamic swarms, showing improved convergence in competitive scenarios over pure SI methods.

Optimization Algorithms

Ant Colony Optimization

Ant Colony Optimization (ACO) is a population-based metaheuristic for solving combinatorial optimization problems, drawing inspiration from the foraging behavior of real ants that deposit pheromones on paths to food sources, enabling collective path-finding through positive feedback mechanisms. Developed initially by in his 1992 PhD thesis at the , Italy, ACO was formalized as the "Ant System" in a 1996 paper co-authored with and . This approach models artificial ants as agents that construct candidate solutions incrementally while updating a shared pheromone matrix to bias future searches toward promising regions of the solution space. In the core mechanism of ACO, each artificial ant probabilistically selects solution components to build a complete candidate solution, guided by both pheromone levels and problem-specific heuristic information. The transition probability for ant k from node i to node j is given by p_{ij}^k = \frac{[\tau_{ij}]^\alpha [\eta_{ij}]^\beta}{\sum_{l \in \mathcal{N}_i^k} [\tau_{il}]^\alpha [\eta_{il}]^\beta}, where \tau_{ij} represents the pheromone trail on edge (i,j), \eta_{ij} is the heuristic desirability (e.g., \eta_{ij} = 1/d_{ij} for distance d_{ij} in the ), \mathcal{N}_i^k is the set of feasible next nodes, and parameters \alpha and \beta balance exploration (via pheromones) and exploitation (via heuristics). After all ants complete their solutions, the pheromone matrix is updated in two steps: global evaporation reduces existing trails by \tau_{ij} \leftarrow (1 - \rho) \tau_{ij} (where $0 < \rho < 1 is the evaporation rate), followed by reinforcement \tau_{ij} \leftarrow \tau_{ij} + \sum_{k=1}^m \Delta \tau_{ij}^k, with \Delta \tau_{ij}^k = Q / L_k if edge (i,j) is used in ant k's tour of length L_k (and 0 otherwise), and Q > 0 a constant. This update rule promotes convergence by amplifying pheromones on high-quality paths while preventing stagnation through evaporation. Several variants of ACO have enhanced its robustness and performance, particularly for the traveling salesman problem (TSP). The Ant Colony System (ACS), introduced by Dorigo and Maria Gambardella in 1997, modifies the original Ant System by adding local pheromone updates during solution construction to diversify searches and incorporating an elitist global update that reinforces only the best ant's edges, often combined with local search like . ACS differs from the base Ant System through these more targeted updates and pseudorandom proportional selection rules, achieving improvements of approximately 0.6% on Oliver30 and 1.6% on Eilon50 compared to the original. Another key variant, the MAX–MIN Ant System (MMAS), proposed by Thomas Stützle and Holger H. Hoos in 1997, imposes explicit upper and lower bounds on pheromone levels to avoid premature to suboptimal solutions and includes an iteration-best update strategy. MMAS has demonstrated superior performance over the Ant System on symmetric and asymmetric TSP benchmarks by maintaining greater solution diversity. ACO's effectiveness stems from its loop, where successful solutions reinforce trails, leading to rapid convergence on near-optimal configurations, while its nature allows adaptation to dynamic environments. In TSP applications, early ACO implementations and variants like ACS and MMAS have produced competitive results, often yielding tour lengths within a few percent of known optima on standard benchmarks, outperforming naive random searches and rivaling other metaheuristics of the era. This makes ACO particularly suitable for , path-based optimization challenges where -mediated cooperation enhances global search efficiency.

Particle Swarm Optimization

Particle Swarm Optimization (PSO) is a population-based stochastic optimization technique that simulates the social foraging behavior of birds or fish schools, where individuals adjust their movement based on personal and collective experiences to locate food sources. This draws brief inspiration from computational models of flocking, such as the model. Introduced by and C. Eberhart in 1995, PSO was originally developed for optimizing continuous nonlinear functions and applied to training artificial neural networks. In PSO, a swarm consists of multiple particles, each representing a solution with a position \mathbf{x}_i(t) and \mathbf{v}_i(t) in the multidimensional search space at t. The particles evaluate an function at their positions and update their velocities and positions iteratively to converge toward optimal solutions. The velocity update incorporates three components: the previous velocity (), a cognitive term pulling toward the particle's personal best position \mathbf{pbest}_i, and a social term pulling toward the global best position \mathbf{gbest} found by the swarm. The core equations for the updates are: \mathbf{v}_i(t+1) = w \mathbf{v}_i(t) + c_1 r_1 (\mathbf{pbest}_i - \mathbf{x}_i(t)) + c_2 r_2 (\mathbf{gbest} - \mathbf{x}_i(t)) \mathbf{x}_i(t+1) = \mathbf{x}_i(t) + \mathbf{v}_i(t+1) where w is the weight controlling , c_1 and c_2 are positive constants for cognitive and social influences, and r_1, r_2 are uniform random values in [0, 1]. Key parameters in PSO include the weight w, which is often damped linearly from an initial value near 0.9 to 0.4 over iterations to global in early stages and local for later. Typical values for c_1 and c_2 are both 2.0, promoting a blend of individual and group learning. A notable variant, the local-best PSO (LPSO), replaces \mathbf{gbest} with a local best \mathbf{lbest}_i from a particle's neighborhood , as proposed by P. N. Suganthan in , to enhance diversity and mitigate premature in complex landscapes. PSO exhibits strengths in its minimal parameter set—primarily w, c_1, c_2, swarm size, and iteration limits—enabling straightforward implementation and fast compared to other evolutionary algorithms. In benchmarks on functions, PSO often demonstrates superiority over genetic algorithms (), such as requiring 10-30% fewer function evaluations to reach near-optimal solutions in standard test problems like the Rastrigin or Griewank functions. During the 2000s, extensions included approaches combining PSO with , leveraging PSO's velocity-based momentum for rapid alongside 's crossover and for broader exploration, as in early hybrid genetic-PSO frameworks for multi-stage optimization. adaptations, such as the PSO introduced by and Eberhart in 1997, sigmoid-transform velocities into probabilities for binary decisions, enabling applications in combinatorial problems like scheduling.

Bee-Inspired and Other Algorithms

The algorithm, introduced by Dervis Karaboga in 2005, simulates the foraging behavior of colonies to solve numerical optimization problems. In this model, the population consists of artificial agents divided into three roles: employed bees, which search for around their assigned food sources; onlooker bees, which select promising food sources based on information shared by employed bees; and scout bees, which explore new random positions when a food source is abandoned after a predefined number of unsuccessful trials. Food sources represent potential solutions, with their quality evaluated by a fitness function, and an abandonment counter tracks exploitation limits to balance exploration and exploitation. The update mechanism for solution positions in ABC involves employed bees generating candidate solutions near their current position. For a food source at position \mathbf{x}_i, a new position v_{ij} in dimension j is produced as: v_{ij} = x_{ij} + \phi_{ij} (x_{ij} - x_{kj}), where k is a randomly selected index different from i, and \phi_{ij} is a uniformly distributed in [-1, 1]. If the new position yields better , it replaces the old one; otherwise, the counter increments. Onlookers choose food sources probabilistically via: p_i = \frac{fit_i}{\sum_{n=1}^{SN} fit_n}, where fit_i is the of source i and SN is the number of sources (equal to the number of employed bees). Scouts replace abandoned sources with random initializations. Artificial Swarm Intelligence (ASI), developed in 2015, extends swarm principles to hybrid human-AI systems for decision support. It employs virtual agents that mediate real-time interactions among networked human participants, simulating collective deliberation to amplify group intelligence without direct communication. This approach fosters emergent through moderated feedback loops, making it suitable for non-technical users in domains like and strategy. Other bee-inspired and biologically motivated algorithms include the (FA), proposed by Xin-She in 2008, which models fireflies' attraction based on brightness (objective function value) to converge on optima. Fireflies move toward brighter counterparts with a distance-dependent attractiveness, incorporating for exploration. (CS), introduced by and Suash Deb in 2009, draws from the brood parasitism of cuckoos, using Lévy flights for global random walks to generate new solutions and a discovery probability to replace host nests. Bacterial Foraging Optimization (BFO), developed by Kevin Passino in 2002, mimics E. coli , where virtual bacteria perform tumbles and runs toward nutrients, alongside reproduction and elimination-dispersal events to optimize distributed systems. Comparisons highlight ABC's strengths in dynamic environments, where variants like interleaved ABC outperform standard particle swarm optimization (PSO) by achieving faster convergence on moving peak benchmarks, often by 15-30% in iteration counts depending on problem scale. ASI, in contrast, excels in human-centric decision tasks, enabling non-expert groups to surpass individual accuracy by simulating swarm dynamics without requiring algorithmic expertise.

Applications

Engineering and Robotics

Swarm intelligence principles have been applied to network routing through ant colony optimization (ACO) algorithms, which mimic ant foraging behaviors to dynamically select paths for data packets. In AntNet, a seminal ACO-based system developed in the late 1990s, virtual ants deposit on promising routes, enabling adaptive routing that reduces congestion in simulated telecommunications networks compared to traditional protocols like OSPF. This approach has been extended to mobile ad-hoc networks (MANETs) with algorithms like ARA, which uses probabilistic pheromone updates to forward packets, achieving efficient routing in dynamic environments without central coordination. In swarm robotics, decentralized task allocation draws on SI to coordinate large groups of simple robots for complex objectives, such as and . The , introduced in the early , demonstrates with over 1,000 low-cost robots executing identical programs to form programmable shapes through local interactions, highlighting fault-tolerant behaviors where the system maintains functionality despite individual failures. Similarly, swarms for search-and-rescue operations leverage SI for autonomous navigation and victim detection; the EU's project (2012–2015) integrated ground and aerial robots using bio-inspired coordination to traverse hostile alpine terrains, improving mission efficiency in unstructured settings. Beyond routing and , SI algorithms optimize engineering systems like power grids and wireless sensor networks (WSNs). (PSO), applied to power grid load balancing since the early 2000s, adjusts generator outputs and transmission paths to minimize losses and ensure stability, as shown in optimal power flow solutions that reduce operational costs by balancing loads across distributed resources. In WSNs, artificial bee colony (ABC) algorithms perform clustering to select energy-efficient heads, improving by minimizing data transmission overhead in large-scale deployments. NASA has employed SI for satellite since the 2000s, using decentralized control inspired by behaviors to maintain precise relative positions among multiple , enabling missions like distributed sensing with enhanced . Recent advancements in drone regulations support swarm operations; in 2023, the FAA issued guidance and exemptions allowing multi- flights under waivers, facilitating scalable SI-based applications while addressing safety concerns. These applications underscore SI's strengths in scalability to thousands of agents and robustness, where systems tolerate significant agent loss with minimal performance degradation due to emergent from local rules.

Simulation and Social Modeling

Swarm intelligence (SI) principles have been extensively applied to crowd behaviors, particularly flows, by modeling collective dynamics through simple local rules. The model, introduced by Reynolds in 1986, simulates via rules of separation, , and , which have been adapted for simulations to capture emergent crowd patterns like lane formation and oscillations at bottlenecks. Similarly, the , which emphasizes velocity among self-propelled particles, has been integrated into flow simulations to replicate ordered motion in dense environments. These SI-based approaches are often hybridized with Helbing's social force model, originally proposed in 1995, where pedestrians are treated as particles influenced by attractive and repulsive forces; such hybrids effectively simulate realistic crowd interactions, including avoidance and herding, in non-panic scenarios like corridors or public spaces. In human swarming experiments, inspires platforms that enable collective decision-making among networked individuals, mimicking biological swarms to aggregate group wisdom. The UNU platform, developed in the , allows distributed users to form virtual swarms for tasks like event prediction, where participants influence a shared to converge on without hierarchical leadership. Studies using UNU demonstrate that these human swarms achieve predictive accuracy rivaling domain experts, such as in sports outcomes or awards, often outperforming individual judgments by leveraging parallel inputs and feedback loops. For instance, in 2015 trials, swarms reached high rates, with success levels around 73% in verifiable predictions, highlighting SI's potential to amplify beyond traditional polling. Specific applications include evacuation modeling and opinion dynamics. In evacuation simulations, SI algorithms like optimize paths and reduce computational demands compared to detailed agent-based models; for example, hybrid SI approaches can forecast clearance times more efficiently in large-scale scenarios through faster convergence on optimal routes. For opinion dynamics, SI introduces noise and alignment mechanisms akin to the DeGroot model, where agents iteratively update beliefs based on neighbors, but with interactions to model real-world and in networks. Tools like CrowdSim, developed in the as an agent-based framework, incorporate SI elements for dense crowd rendering, enabling realistic testing of social behaviors in virtual settings. Human trials further validate these models, showing effective consensus in decision tasks under controlled conditions. Recent advances integrate SI crowd simulations with () for immersive training, allowing users to experience and respond to dynamic group behaviors in simulated emergencies during the 2020s. These environments facilitate scenario-based drills, such as multi-exit evacuations, enhancing preparedness by visualizing SI-driven crowd flows in . Additionally, SI has been applied to pandemic modeling since 2020, using optimization techniques for simulating disease spread and supporting by predicting high-risk interactions in populations, thereby aiding and intervention strategies.

Creative and Emerging Fields

Swarm grammars represent a computational framework that integrates agent-based swarm behaviors with generative rewrite rules to produce emergent structures, originating from research in the late on and developmental models. Developed by researchers such as Hartmut von Mammen and Christian Jacob, these grammars enable decentralized agents to perceive, act, and evolve dynamic forms, such as growing trees or artistic designs, through bottom-up processes that mimic biological development. While primarily applied in visual and structural generation, swarm grammars have influenced explorations in during the , where SI rules facilitate the emergence of syntactic patterns in simulated systems by allowing agents to iteratively construct grammatical hierarchies from simple rules. In the realm of , swarm intelligence has inspired "swarmic" visuals and interactive installations that leverage collective behaviors for aesthetic expression. Reynolds' Steer Suite, introduced in the and extended through the , provides a foundational toolkit for simulating and dynamics, enabling artists to create lifelike, emergent animations used in films, games, and visual art. Notable examples include Ars Electronica's Swarm Arena project from the , where robotic swarms of drones and ground bots form volumetric point clouds and modular sculptures, blending swarm algorithms with real-time audience interaction to explore themes of in public installations. These works highlight SI's role in producing non-deterministic, organic visuals that evolve unpredictably, as seen in swarmOS software for coordinating heterogeneous robot ensembles in artistic performances. Emerging applications of swarm intelligence extend to creative domains like music composition and bio-inspired . The artificial bee colony () algorithm, a bio-inspired SI method, has been adapted for harmonic clustering in music generation, where foraging agents optimize note sequences to form coherent melodies and progressions, as demonstrated in systems that balance exploration of musical spaces with exploitation of harmonic constraints. In , MIT's in the 2010s on self-assembling modular robots utilized swarm principles to enable passive modules to form complex structures autonomously, paving the way for in dynamic, adaptive built environments. Similarly, in the 2020s, (PSO) has advanced by enhancing molecular docking simulations; for instance, hybrid PSO variants like PSOVina and multi-swarm competitive algorithms accelerate ligand-protein binding predictions, improving efficiency in identifying potential therapeutics. Forward-looking uses of SI address ethical challenges in and intersect with cutting-edge technologies. Recent work, including 2023 papers on multi-objective SI for bias mitigation, employs swarm algorithms to balance fairness in models by optimizing diverse datasets and decision boundaries, reducing discriminatory outcomes in human- collaborative systems. Trends in the include SI integration with for collective problem-solving in decentralized systems. Additionally, quantum-enhanced SI, such as quantum PSO variants post-2020, facilitates complex simulations by leveraging for faster exploration of high-dimensional spaces in and optimization tasks. As of 2025, ongoing research explores SI in edge for sustainable and climate modeling, enhancing adaptive responses in ecosystems. These developments underscore SI's potential to foster innovative, ethically aware creative practices.

Challenges and Future Directions

Current Limitations

Swarm intelligence (SI) systems often face significant challenges due to their , which can scale quadratically with the number of agents in fully connected topologies, resulting in O(n²) costs for interactions and updates among n agents. While techniques such as neighborhood-based limits mitigate this by restricting interactions to local subsets, they can compromise the realism of global emergent behaviors modeled after natural swarms. Convergence in SI algorithms remains problematic, with many exhibiting premature trapping in local optima, as seen in particle swarm optimization (PSO) where stagnation occurs due to loss of population diversity in multimodal landscapes. Similarly, Vicsek-like flocking models demonstrate high sensitivity to noise, where even moderate perturbations can disrupt alignment and lead to disordered states rather than coherent convergence. Theoretical foundations of SI are limited by the absence of rigorous convergence proofs for most metaheuristics, unlike exact optimization methods that guarantee under defined conditions. This gap contributes to the black-box nature of SI approaches, where the opaque decision processes hinder interpretability and trust, particularly in domains requiring explainable outcomes. In practical deployments, such as , communication delays introduce substantial hurdles, often causing drastic performance degradation due to desynchronization among agents. The reality gap between simulations and real-world environments exacerbates this, manifesting in notable drops in task efficiency, such as reduced coordination accuracy in missions. Additionally, the unpredictable of collective behaviors raises ethical concerns, as unintended patterns could lead to unreliable or hazardous outcomes in safety-critical applications. Benchmarks further highlight SI's underperformance in high-dimensional spaces; for instance, studies on 100-dimensional functions from the CEC suites show PSO and similar algorithms achieving suboptimal solutions compared to specialized high-dimensional optimizers, often failing to escape of dimensionality. Recent research in swarm intelligence (SI) has increasingly focused on hybrid approaches that integrate SI algorithms with (ML) techniques to address complex challenges in distributed systems. One prominent example is Swarm Learning, a decentralized ML paradigm introduced in a seminal 2021 study, which enables collaborative model training across devices without sharing raw data, thereby enhancing privacy and scalability in applications like healthcare diagnostics. This approach uses for coordination to aggregate updates securely. Complementing this, quantum-inspired particle swarm optimization (QPSO), originally developed in 2004, has seen variants such as enhanced weighted QPSO (EWQPSO) emerge since 2022, which improve convergence and accuracy in optimization tasks through mechanisms like weighted behavioral parameters, as demonstrated in applications like antenna design. Scaling to real-world environments has driven innovations in nano-scale and extraterrestrial applications. In , nano-swarms—autonomous micro- or nanorobots exhibiting swarming behavior—show promise for , where collectives of enzymatic nanomotors have been demonstrated using tracking in models for applications, with potential for navigating biological barriers to release therapeutics at targeted sites. These systems, under development in the , display collective migration for enhanced dispersion. In space , SI enables autonomous satellite and swarms; NASA's mission in 2024 successfully tested four CubeSats using distributed coordination for self-navigation and relative positioning, paving the way for resilient multi-agent operations in deep space. Theoretical advancements continue to formalize SI phenomena, providing rigorous foundations for predictability and design. Since the 2010s, models have yielded formal proofs of emergent behaviors in swarms, such as under limited visibility, where local interactions guarantee global through connectivity analyses. Similarly, multi-objective SI extensions, particularly in ant colony optimization (ACO) and PSO, incorporate Pareto fronts to balance conflicting goals like cost and reliability, generating non-dominated solution sets for engineering problems. Emerging trends emphasize interpretability and sustainability in SI deployments. Explainable SI methods, gaining traction since 2023, visualize agent decisions through analyses and decision trees, aiding and trust in black-box optimizations like PSO. In sustainable applications, SI optimizes energy distribution in smart cities, with algorithms like PSO scheduling renewable sources to minimize losses and support urban microgrids. These developments reflect surging interest, evidenced by over 15,000 publications on SI by 2025 and increased funding, such as NSF's $3 million grant in 2024 for bio-inspired emergent programs. As of 2025, conferences like the 16th International Conference on Swarm Intelligence (ICSI 2025) continue to highlight advances in multimodal optimization and defense applications.

Key Contributors

Pioneering Figures

Craig Reynolds, a pioneering figure in and , developed the model in 1986, published in 1987, which simulates flocking behaviors through simple local rules of separation, alignment, and cohesion among autonomous agents. This work, presented at the conference, earned recognition for advancing distributed behavioral simulation in animation. Reynolds' has profoundly influenced by enabling realistic crowd and group motion in films and games, and it has been adapted in for multi-agent coordination and tasks. Marco Dorigo, an Italian computer scientist, invented Ant Colony Optimization (ACO) during his 1992 PhD thesis at Politecnico di Milano, marking the first doctoral work explicitly on swarm intelligence algorithms inspired by ant foraging. As co-director and founder of the IRIDIA laboratory at , Dorigo has authored over 300 publications on and optimization, establishing foundational frameworks for decentralized problem-solving in multi-agent systems. James Kennedy, a social psychologist, and Russell Eberhart, an electrical engineer, co-developed Particle Swarm Optimization (PSO) in 1995, drawing from social behavior models to create an optimization algorithm where particles adjust positions based on personal and group experiences. Kennedy's broader contributions include applying social psychology principles to simulate emergent intelligence in swarms, as detailed in his co-authored book on the topic. Tamás Vicsek, a physicist, introduced the model in 1995, demonstrating phase transitions from disorder to collective motion in systems of interacting agents, which bridges statistical physics with biological and swarming phenomena. His work has provided analytical tools for understanding in both natural and artificial swarms, influencing interdisciplinary research in and complex systems.

Influential Modern Researchers

Dervis Karaboga has significantly advanced swarm intelligence through extensions of the algorithm, originally introduced in 2005, with key developments in the focusing on enhanced performance for and hybrid applications in problems. His 2012 comprehensive survey detailed ABC's adaptations for tasks like and numerical optimization. Subsequent works, including collaborations on improved scout bee mechanisms, have integrated ABC with other metaheuristics, improving its efficacy in real-world scenarios such as wireless sensor networks. Xin-She Yang contributed foundational algorithms to swarm intelligence, notably the in 2008 and in 2009, which mimic bioluminescent signaling and for . These methods have been widely adopted for their simplicity and effectiveness. Yang's ongoing extensions in the 2010s and 2020s, detailed in his 2014 book, emphasize hybrid variants for large-scale problems, influencing applications in image processing and structural design with reduced computational overhead. Radhika Nagpal pioneered scalable self-organizing robotic swarms through the Kilobot platform, introduced in 2012, enabling collective behaviors in large groups without centralized control. Her team's 2014 demonstration with 1,024 Kilobots showcased emergent , such as into shapes, despite individual robot limitations in sensing and actuation. This work at Harvard's Wyss Institute has advanced decentralized algorithms, inspiring bio-mimetic systems for . Vijay Kumar, leading the GRASP Lab at the University of Pennsylvania, has driven innovations in aerial since the 2010s, developing quadrotor fleets that coordinate via onboard sensing for tasks like 3D construction and search-and-rescue. His 2012 talk highlighted cooperative flight algorithms, where swarms of up to 20 drones form ad-hoc networks. Kumar's research extends to medical contexts, with swarm-based systems for precision delivery in healthcare environments, patented in the early 2020s for modular robotic platforms. Melanie Mitchell has enriched the theoretical foundations of swarm intelligence in the 2020s by exploring in and complex systems, linking collective behaviors to scalable intelligence without hierarchical control. Her analyses critique overhyped claims of emergence while advocating for analogy-based models inspired by natural swarms, as in her 2019 book updated with 2020s insights on ethical design. This has influenced interdisciplinary work on robust, interpretable swarm systems.

References

  1. [1]
    Swarm Intelligence - an overview | ScienceDirect Topics
    Swarm intelligence is defined as a collective behavior of a decentralized or self-organized system. These systems consist of numerous individuals with limited ...
  2. [2]
    (PDF) Swarm Intelligence : From Natural to Artificial Systems / E ...
    Swarm Intelligence (SI) represents a fascinating and powerful field of study that draws inspiration from the collective behaviour observed in decentralized, ...
  3. [3]
    Ant system: optimization by a colony of cooperating agents
    Feb 29, 1996 · Ant system: optimization by a colony of cooperating agents. Abstract: An analogy with the way ant colonies function has suggested the definition ...
  4. [4]
  5. [5]
    Swarm Intelligence-Based Multi-Robotics: A Comprehensive Review
    Oct 2, 2024 · Swarm Intelligence (SI) is a burgeoning field within artificial intelligence that draws inspiration from the collective behavior observed in ...2.1. Ant Colony Optimization... · 2.2. Particle Swarm... · 2.4. Cuckoo Search (cs)
  6. [6]
    Swarm Intelligence in Data Science: Applications, Opportunities and ...
    Swarm Intelligence is a group of nature-inspired searching and optimization techniques that studies collective intelligence in a population of low complexity ...Introduction · Swarm Intelligence... · Developments
  7. [7]
    A Systematic Literature Review on Swarm Intelligence Based ...
    Mar 1, 2024 · Swarm Intelligence (SI) has proven to be useful in solving issues that are difficult to solve using traditional mathematical methodologies ...
  8. [8]
    Swarm intelligence - Scholarpedia
    Jan 14, 2014 · Swarm intelligence is the discipline that deals with natural and artificial systems composed of many individuals that coordinate using decentralized control ...
  9. [9]
    [PDF] Swarm Intelligence - Scholarpedia - IRIDIA
    Oct 1, 2007 · Swarm intelligence is the discipline that deals with natural and artificial systems composed of many individuals that coordinate using.<|control11|><|separator|>
  10. [10]
    The biological principles of swarm intelligence
    Jul 17, 2007 · The roots of swarm intelligence are deeply embedded in the biological study of self-organized behaviors in social insects.Missing: definition | Show results with:definition
  11. [11]
    (PDF) The biological principles of swarm intelligence - ResearchGate
    Aug 10, 2025 · Abstract and Figures. The roots of swarm intelligence are deeply embedded in the biological study of self-organized behaviors in social insects.
  12. [12]
    [PDF] The biological principles of swarm intelligence - Harvard University
    Abstract The roots of swarm intelligence are deeply embedded in the biological study of self-organized behaviors in social insects. From the routing of ...
  13. [13]
    [PDF] Biological Foundations of Swarm Intelligence
    Many computer scientists are familiar with the double bridge experiment as an example of the means by which foraging is organized in ant colonies. In this ...
  14. [14]
    Biological Foundations of Swarm Intelligence - SpringerLink
    Sumpter, D. J. T. and Beekman, M. (2003) From non-linearity to optimality: pheromone trail foraging by ants. Animal Behaviour, 66:273–280. Article Google ...
  15. [15]
    Uncovering the complexity of ant foraging trails - PMC - NIH
    For example, Pharaoh's ant deposit two types of attractive trail pheromone: a short-lived pheromone that decays within 20 min and a longer lasting pheromone ...
  16. [16]
    Chaos–order transition in foraging behavior of ants - PNAS
    May 27, 2014 · We found that an effective foraging of ants mainly depends on their nest as well as their physical abilities and knowledge due to experience.
  17. [17]
    Automatic detection and decoding of honey bee waggle dances
    The proposed system performs with a detection accuracy of 90.07%. The decoded waggle orientation has an average error of -2.92° (± 7.37°), well within the range ...Missing: degrees | Show results with:degrees
  18. [18]
    Followers of honeybee waggle dancers change their behavior when ...
    Nov 2, 2018 · ... dance angles (representing precision of direction component of waggle dance) ... Bees occasionally dance with errors of 10-15° from the solar angle ...<|separator|>
  19. [19]
    Social signal learning of the waggle dance in honey bees - Science
    Mar 9, 2023 · Longer waggle runs communicate greater distances (more retinal optical flow), and the waggle direction angle communicates resource direction.
  20. [20]
    Self-organized biotectonics of termite nests - PNAS
    Jan 18, 2021 · This principle of stigmergy—defined as the spontaneous but indirect coordination of agents stimulated to action by the trace of previous actions ...
  21. [21]
    Excavation and aggregation as organizing factors in de novo ...
    Jun 14, 2017 · Grassé was the first to suggest that stigmergy plays a key role in the self-organized construction of termite mounds [8]. In his seminal ...
  22. [22]
    Revisiting stigmergy in light of multi-functional, biogenic, termite ...
    This review is focused on how termites design and build functional structures as nest, nursery and food storage; for thermoregulation and climatisation.
  23. [23]
    From behavioural analyses to models of collective motion in fish ...
    Oct 3, 2012 · This topological neighbourhood has proved to lead to robust cohesion of the school under predation [68], and it may be achieved either by ...
  24. [24]
    How predation shapes the social interaction rules of shoaling fish
    Aug 30, 2017 · Previous studies have suggested that both alignment and attraction responses could be shaped by predation, making group members more cohesive ...
  25. [25]
    It pays to follow the leader: Metabolic cost of flight is lower ... - PNAS
    Jun 17, 2024 · Thus, our results are consistent with energy savings for follower birds derived from beneficial aerodynamic interaction with the tip vortices of ...
  26. [26]
    Aerodynamic mechanisms behind energy efficiency in migratory bird ...
    Feb 20, 2025 · Studies have shown that birds flying in groups benefit from reduced energy expenditure by leveraging the vortices generated by the wings of the ...INTRODUCTION · Aerodynamic study of a... · Aerodynamic study of two...Missing: murmurations | Show results with:murmurations
  27. [27]
    Recherches sur les mœurs des fourmis indigènes : Huber, P. (Pierre ...
    Oct 9, 2020 · Recherches sur les mœurs des fourmis indigènes ; Publication date: 1810 ; Topics: Ants -- France ; Publisher: Paris ; Genève : Chez J.J. Paschoud.Missing: François | Show results with:François
  28. [28]
    Ants and some other insects; an inquiry into the psychic powers of ...
    Jan 18, 2007 · Ants and some other insects; an inquiry into the psychic powers of these animals, with an appendix on the peculiarities of their olfactory sense.
  29. [29]
    The Insect Societies - Harvard University Press
    Jan 1, 1971 · This first comprehensive study of social insects since the 1930s includes more than 250 illustrations and covers all aspects of classification, evolution, ...
  30. [30]
    Geometry for the selfish herd - ScienceDirect.com
    This paper presents an antithesis to the view that gregarious behaviour is evolved through benefits to the population or species.
  31. [31]
    La reconstruction du nid et les coordinations interindividuelles ...
    La reconstruction du nid et les coordinations interindividuelles chezBellicositermes natalensis etCubitermes sp. la théorie de la stigmergie: Essai d' ...Missing: Bellicositermes | Show results with:Bellicositermes
  32. [32]
    [PDF] Cybernetics: - or Control and Communication In the Animal - Uberty
    NORBERT WIENER second edition. THE M.I.T. PRESS. Cambridge, Massachusetts. Page 3. Copyright © 1948 and 1961 by The Massachusetts Institute of Technology. All ...Missing: decentralized | Show results with:decentralized
  33. [33]
    [PDF] Theory of Self-Reproducing Automata - CBA-MIT
    Von Neumann then estimated that the brain dissipates 25 watts, has 1010 neurons, and that on the average a neuron is activated about 10 times per second. Hence ...
  34. [34]
    Termite Mound Building Model | Request PDF - ResearchGate
    Aug 6, 2025 · In 1977, Deneubourg introduced a diffusion–advection model for describing the initial stage that termites build spontaneously their mound.
  35. [35]
    Flocks, herds and schools: A distributed behavioral model
    This paper explores an approach based on simulation as an alternative to scripting the paths of each bird individually.
  36. [36]
    Novel Type of Phase Transition in a System of Self-Driven Particles
    Aug 7, 1995 · A simple model with a novel type of dynamics is introduced in order to investigate the emergence of self-ordered motion in systems of particles.
  37. [37]
    artificial bee colony (ABC) algorithm | Journal of Global Optimization
    Apr 13, 2007 · A powerful and efficient algorithm for numerical function optimization: artificial bee colony (ABC) algorithm. Download PDF. Dervis Karaboga & ...
  38. [38]
    Swarm Intelligence | SpringerLink
    Dozier (2000): Adapting particle swarm optimization to dynamic environments. Proc. Int. Conf. Artificial Intelligence, 2000, 429–434, Las Vegas, NV, USA.
  39. [39]
    Photos: The robot designs of iRobot - CNET
    Apr 15, 2009 · iRobot Swarm. This robot from 1999 was designed, in the manner of an insect, to work in a swarm with other, similar machines. It was part of ...
  40. [40]
    [PDF] Human Swarming, a real-time method for Parallel Distributed ...
    This paper describes a novel platform called UNU that enables distributed populations of networked users to congregate online in real-time swarms and tackle ...
  41. [41]
    Swarm Characteristics Classification Using Neural Networks - arXiv
    Mar 28, 2024 · This article presents a study on using supervised neural network time series classification (NN TSC) to predict key attributes and tactics of swarming ...Missing: 2020s | Show results with:2020s
  42. [42]
    Search and rescue with autonomous flying robots through behavior ...
    Dec 5, 2018 · In computer simulations, the swarm is successful in locating over 90% of survivors in less than an hour. The swarm is controlled by new sets of ...
  43. [43]
    Quantum-Inspired gravitationally guided particle swarm optimization ...
    Oct 1, 2025 · A 2020 study presented a Quantum-Inspired Owl Search Algorithm (QIOSA) for feature subset selection, which used quantum principles to improve ...
  44. [44]
    On the ethical governance of swarm robotic systems in the real world
    Jan 30, 2025 · We argue that swarm robotic systems must be developed and operated within a framework of ethical governance.
  45. [45]
    Flocks, Herds, and Schools: A Distributed Behavioral Model
    A Distributed Behavioral Model. by Craig Reynolds. simulated boid flock avoiding obstacles (1986). Abstract: The aggregate motion of a flock of birds, a ...
  46. [46]
    Boids (Flocks, Herds, and Schools: a Distributed Behavioral Model)
    An attempt to replicate the main findings of Craig Reynolds's (1987) 'Boids' by Harry Brignull, reports on a project to implement boids using the POPBUGS ...
  47. [47]
    Interaction ruling animal collective behavior depends on topological ...
    The difference between topological and metric hypotheses is stark: In the topological scenario, the number of interacting individuals is fixed, whereas in the ...Abstract · Results · Discussion
  48. [48]
    Relevance of Metric-Free Interactions in Flocking Phenomena
    The transition to collective motion in the Vicsek topological model and its ordered phase at finite density are thus different from that of its metric ...
  49. [49]
    [PDF] Comparison of an Agent-based Model of Disease Propagation with ...
    This paper describes our recent experience in developing an agent-based disease propagation model to simulate an epidemic outbreak and comparing the results of ...
  50. [50]
    [PDF] Interaction with Groups of Autonomous Characters - red3d.com
    This paper presents a methodology for constructing large groups of autonomous characters which respond in real time to the user's interaction, ...Missing: later swarm
  51. [51]
    (PDF) A Swarm Intelligence method combined to Evolutionary Game ...
    Aug 6, 2025 · The main innovation of this study is to use a hybrid Discrete Particle Swarm Optimization (DPSO) method combined to Evolutionary Game Theory ( ...
  52. [52]
    Ant colony optimization
    The ant colony optimization algorithm (ACO), developed by Marco Dorigo ... PhD thesis, Politecnico di Milano, Italy, 1992. [BDT99] Swarm Intelligence: From ...
  53. [53]
    [PDF] The Ant System: Optimization by a colony of cooperating agents
    This procedure ensures the. Page 22. 22. Dorigo et al.: Ant System: Optimization by a Colony of Cooperating Agents possibility to always produce a feasible ...
  54. [54]
  55. [55]
    MAX-MIN Ant System and local search for the traveling salesman ...
    Ant System is a general purpose algorithm inspired by the study of the behavior of ant colonies. It is based on a cooperative search paradigm that is ...
  56. [56]
    Particle swarm optimization | IEEE Conference Publication
    Abstract: A concept for the optimization of nonlinear functions using particle swarm methodology is introduced. The evolution of several paradigms is ...
  57. [57]
    Particle swarm optimization | Swarm Intelligence
    Aug 1, 2007 · Eberhart, R. C., & Kennedy, J. (1995). A new optimizer using particle swarm theory. In Proceedings of the sixth international symposium on micro ...
  58. [58]
    A modified particle swarm optimizer | IEEE Conference Publication
    We introduce a new parameter, called inertia weight, into the original particle swarm optimizer. Simulations have been done to illustrate the significant ...
  59. [59]
    Particle swarm optimiser with neighbourhood operator - IEEE Xplore
    Although the PSO algorithm possesses some attractive properties, its solution quality has been somewhat inferior to other evolutionary optimisation algorithms ( ...
  60. [60]
    (PDF) Comparison between Genetic Algorithms and Particle Swarm ...
    Aug 7, 2025 · This paper compares the performance of two evolutionary computation paradigms, genetic algorithms (GAs) and particle swarm optimization (PSO), ...
  61. [61]
    A hybrid of genetic algorithm and particle swarm optimization for ...
    Apr 30, 2004 · This new evolutionary learning algorithm is based on a hybrid of genetic algorithm (GA) and particle swarm optimization (PSO), and is thus called HGAPSO.Missing: early | Show results with:early
  62. [62]
    A discrete binary version of the particle swarm algorithm - IEEE Xplore
    A discrete binary version of the particle swarm algorithm ... Examples, applications, and issues are discussed. Published in: 1997 IEEE International Conference ...
  63. [63]
    A powerful and efficient algorithm for numerical function optimization
    Aug 7, 2025 · A powerful and efficient algorithm for numerical function optimization: Artificial bee colony (ABC) algorithm · Abstract · Citations (8,126) ...
  64. [64]
    Artificial bee colony algorithm - Scholarpedia
    Mar 23, 2010 · The Artificial Bee Colony (ABC) algorithm is a swarm based meta-heuristic algorithm that was introduced by Karaboga in 2005.The Artificial Bee Colony Meta... · Applications of ABC
  65. [65]
    Human swarming, a real-time method for parallel distributed ...
    Human swarming uses the UNU platform to enable networked humans to work together in real-time, fostering a unified emergent intelligence.
  66. [66]
    [1003.1466] Firefly Algorithms for Multimodal Optimization - arXiv
    Mar 7, 2010 · This paper intends to provide a detailed description of a new Firefly Algorithm (FA) for multimodal optimization applications.Missing: 2008 original
  67. [67]
    [1005.2908] Engineering Optimisation by Cuckoo Search - arXiv
    May 17, 2010 · A new metaheuristic optimisation algorithm, called Cuckoo Search (CS), was developed recently by Yang and Deb (2009).Missing: original | Show results with:original
  68. [68]
    An Interleaved Artificial Bee Colony algorithm for dynamic ...
    The proposed algorithm was tested on the Moving Peak Benchmark. The experimental results indicated that the proposed algorithm achieved better results than the ...
  69. [69]
    [PDF] Artificial Swarm Intelligence | Unanimous AI
    In 2015, the first study was published demonstrating that networked teams can produce collaborative forecasts by working together as swarm- based systems, ...
  70. [70]
    [PDF] AntNet: Distributed Stigmergetic Control for Communications Networks
    The core ideas of these techniques (for a review see Dorigo, Di Caro, and. Gambardella, 1998) are (i) the use of repeated and concurrent simulations carried out ...
  71. [71]
    [PDF] ARA – The Ant-Colony Based Routing Algorithm for MANETs - LIX
    In this paper we present a new on-demand routing al- gorithm for mobile, multi-hop ad-hoc networks. The pro- tocol is based on swarm intelligence and especially ...
  72. [72]
    Smart collaboration between Humans and ground-aErial Robots for ...
    The goal of SHERPA is to develop a mixed ground and aerial robotic platform to support search and rescue activities in a real-world hostile environment like ...Missing: drone 2010s
  73. [73]
    Optimal power flow using particle swarm optimization - ScienceDirect
    This paper presents an efficient and reliable evolutionary-based approach to solve the optimal power flow (OPF) problem.
  74. [74]
    [PDF] Drone swarm technologies | GAO
    Operators must obtain a waiver to operate a drone swarm, as current regulations do not permit a person to operate more than one drone at the same time.
  75. [75]
    Multiagent Simulation Approach to Pedestrian Laminar Flow With ...
    Jan 5, 2021 · We propose a model that combines existing walking and crowd models (the social-force, following behavior, and Boids models) to simulate ...
  76. [76]
    An approach combining social force and Vicsek models | Phys. Rev. E
    Aug 12, 2020 · We study the pedestrian motion along a corridor in a nonpanic regime, as usually happens in evacuation scenarios in, eg, schools, hospitals, or airports.
  77. [77]
    Social force model for pedestrian dynamics | Phys. Rev. E
    May 1, 1995 · The social force model is capable of describing the self-organization of several observed collective effects of pedestrian behavior very realistically.
  78. [78]
    [PDF] Artificial Swarm Intelligence vs Human Experts - Unanimous AI
    Dec 7, 2016 · Abstract— Artificial Swarm Intelligence (ASI) strives to facilitate the emergence of a super-human intellect by connecting.
  79. [79]
    Forecasting pedestrian evacuation times by using swarm intelligence
    In this work, a model for evacuation simulation and for estimating evacuation times is proposed. It is inspired by the so-called Particle Swarm Optimization ( ...
  80. [80]
    [PDF] A Novel Swarm Intelligence Algorithm for the Evacuation Routing ...
    The simulation examples demonstrate that the proposed algorithm can greatly improve upon evacuation clear and congestion times. The experimental results ...
  81. [81]
    CrowdSim: A Model and a Simulation Framework for Dense Crowds
    We develop a novel agent-based model which ensures that both global navigation and local motion in a crowd are modeled close to reality. We design a simula tion ...<|separator|>
  82. [82]
    A Virtual Reality Simulation Method for Crowd Evacuation in ... - MDPI
    Dec 15, 2020 · In the paper, we propose a VR simulation method for crowd evacuation in a multiexit indoor fire environment.
  83. [83]
    (PDF) COVID-19 Outbreak Learning Prediction Based on Swarm ...
    Many researchers introduce a lot of methods to predict the outbreaks of a dangerous pandemic. This paper will introduce a new technique to predict the daily ...<|control11|><|separator|>
  84. [84]
    (PDF) Swarm-Based Computational Development - ResearchGate
    grammars. 18.3 Swarm Grammars. Our first swarm grammar systems were composed of two parts: (1) a set of rewrite. rules, which determined the composition of ...Missing: linguistics | Show results with:linguistics
  85. [85]
    Journal articles: 'Grammar structures' – Grafiati
    This paper presents artwork that was inspired by a computational model called Swarm Grammars. In this work, the “liveliness” of swarms is combined with the ...
  86. [86]
    Steering Behaviors For Autonomous Characters - red3d.com
    Jun 6, 2004 · This paper divides motion behavior into three levels. It will focus on the middle level of steering behaviors, briefly describe the lower level ...
  87. [87]
    Swarm Arena - Ars Electronica Futurelab
    Swarm Arena is a collaboration using drones and ground bots to enhance sports events with augmented and virtual arenas, creating a new audience experience.
  88. [88]
    swarmOS – swarms+art - Ars Electronica Center
    The core parts of SwarmOS are Ground Control, a cross-platform application to monitor and control swarms, and the Implant, a component that is attached to a ...
  89. [89]
    [PDF] MusicSwarm: Biologically Inspired Intelligence for Music Composition
    Sep 16, 2025 · This decentralized architecture mirrors biological swarms—ant colonies, bee hives, flocking birds—where sophisticated group intelligence ...
  90. [90]
  91. [91]
    A novel molecular docking program based on a multi-swarm ...
    The novel program uses a multi-swarm competitive algorithm (MSCA) with a multi-swarm framework, feedback, and gradient descent for molecular docking.
  92. [92]
    Multi-objective swarm intelligence approach for bias mitigation in ...
    MOSIBIM has been tested in several classification models, such as Logistic Regression and Decision Trees, which are widely used in decision-making software ...
  93. [93]
    Blockchain-Coordinated AI Swarm Intelligence and Collective ...
    Jul 19, 2025 · Explore how blockchain-coordinated AI swarms enable collective intelligence, tackling complex problems from logistics to scientific research ...Missing: NFTs art 2020s
  94. [94]
    Quantum Based Particle Swarm Optimization for Equivalent Circuit ...
    May 7, 2022 · In this paper, an improved quantum-behaved particle swarm optimization (QPSO) approach for modeling antenna impedance is illustrated.Missing: post- | Show results with:post-
  95. [95]
    Computational complexity of swarm-based algorithms - AIMS Press
    On the other hand, the literature on swarm-based algorithms does not usually include the analysis of computational complexity of the algorithms.
  96. [96]
    [PDF] Swarm Intelligence Algorithms for Optimization Problems a Survey ...
    In high-dimensional or large-scale optimization tasks, traditional SI algorithms, such as PSO, may incur high computational cost (Hsieh et al., 2012) this is ...
  97. [97]
    Potential-driven multi-learning particle swarm optimisation
    However, its search strategy may lead to issues such as getting trapped in local optima and premature convergence when solving complex multimodal problems. This ...
  98. [98]
    [PDF] arXiv:0801.0379v3 [physics.data-an] 23 Jan 2009
    Jan 23, 2009 · In the noise-free Vicsek model, given r and L, the convergence is faster with more agents (i.e., larger N) since they will have more frequent ...
  99. [99]
    Convergence Analysis of Metaheuristics - SpringerLink
    Sep 1, 2009 · In this tutorial, an overview on the basic techniques for proving convergence of metaheuristics to optimal (or sufficiently good) solutions is given.
  100. [100]
    [PDF] A Review of Swarm Intelligence in Problem Solving and Optimization
    May 10, 2024 · In this review paper, we provide an overview of swarm intelligence, covering its definition, principles, algorithms, applications, performance ...
  101. [101]
    (POSTER) Impact of Connectivity Degradation on Networked ...
    This paper studies how communication impairments can have a drastic impact on the performance of robotic swarms in critical missions such as exploration.Missing: drop | Show results with:drop<|separator|>
  102. [102]
    [PDF] Recent trends in robot learning and evolution for swarm robotics
    Apr 24, 2023 · The reality gap are the inescapable differences between the design and deployment environment, and often manifests in a performance drop when ...<|separator|>
  103. [103]
    Towards applied swarm robotics: current limitations and enablers
    In this paper, we have reviewed the key challenges that currently limit the adoption of swarm robotics in real-world applications (see Table 1). In ...
  104. [104]
    (PDF) Comparison of Swarm Intelligence Algorithms for High ...
    Aug 10, 2025 · On 1,000 dimensions, the algorithm obtains the optimal value on eight benchmark functions and is close to optimal on four others. We also ...
  105. [105]
    Swarm Learning for decentralized and confidential clinical machine ...
    May 26, 2021 · we introduce Swarm Learning—a decentralized machine-learning approach that unites edge computing, blockchain-based peer-to-peer networking and ...<|control11|><|separator|>
  106. [106]
    Swarming behavior and in vivo monitoring of enzymatic nanomotors ...
    Here, we report the swarming behavior of urease-powered nanomotors and its tracking using positron emission tomography (PET), both in vitro and in vivo.
  107. [107]
    Swarming for Success: Starling Completes Primary Mission - NASA
    May 29, 2024 · The four CubeSat spacecraft that make up the Starling swarm have demonstrated success in autonomous operations, completing all key mission objectives.
  108. [108]
    Pareto-Based Multiobjective Particle Swarm Optimization - IntechOpen
    Multiobjective PSO (MOPSO) with Pareto approach allows obtaining set of solutions including a joint optimal solution without weighting requirements.
  109. [109]
    A comprehensive survey of the application of swarm intelligent ...
    Aug 2, 2024 · This paper summarizes the application of swarm intelligence optimization algorithm in photovoltaic energy storage systems
  110. [110]
    BioInspired Wins NSF Grant to Develop Graduate Training Program ...
    Oct 19, 2024 · Syracuse University's BioInspired Institute has been awarded a $3 million grant from the US National Science Foundation (NSF) Research Traineeship Program.Missing: swarm 2020s
  111. [111]
    [PDF] Flocks, Herds, and Schools: A Distributed Behavioral Model 1
    This paper explores an approach based on simulation as an alternative to scripting the paths of each bird individually. The simulated flock is an elaboration of ...
  112. [112]
    Resume of Craig Reynolds - red3d.com
    Batman Returns, 1992, Warner Brothers. Short films: The Juggler, 1981 ... 2008: Birds, Bees, and Boids an introduction to swarm intelligence for a general ...<|control11|><|separator|>
  113. [113]
    Extending boids for safety-critical search and rescue - ScienceDirect
    We extend the Boids algorithm to include collision avoidance using barrier functions. Through simulations, we analyze performance trade-offs in a search and ...
  114. [114]
    Marco Dorigo Web Site - IRIDIA
    Special Issue on Swarm Robotics, Autonomous Robots, 17 (2-3), Special Section on Ant Colony Optimization, IEEE Transactions on Evolutionary Computation, 6 (4)
  115. [115]
    Collective motion in biological systems | Interface Focus - Journals
    Oct 10, 2012 · One of the simplest models exhibiting collective motion was introduced by Vicsek et al. [5]. In this model, self-propelled particles move at ...
  116. [116]
    (PDF) A comprehensive survey: Artificial bee colony (ABC) algorithm ...
    Mar 11, 2012 · ... Karaboga and Ozturk (2010) tested the performance of ABC. on fuzzy clustering and showed that ABC algorithm is also successful in fuzzy ...
  117. [117]
    Cuckoo Search and Firefly Algorithm: Theory and Applications
    Aug 9, 2025 · Firefly algorithm (FA) was developed by Xin-She Yang in 2008, while cuckoo search (CS) was developed by Xin-She Yang and Suash Deb in 2009.
  118. [118]
    A self-organizing thousand-robot swarm - Harvard SEAS
    Aug 14, 2014 · The Kilobot robot design and software, originally created in Nagpal's group at Harvard, are available open-source for non-commercial use.
  119. [119]
    Vijay Kumar: Robots that fly ... and cooperate | TED Talk
    Mar 1, 2012 · In his lab at Penn, Vijay Kumar and his team build flying quadrotors, small, agile robots that swarm, sense each other, and form ad hoc ...Missing: swarms GRASP medical patents 2020s
  120. [120]
  121. [121]
    Swarm intelligence techniques and their applications in fog/edge ...
    Aug 30, 2025 · Swarm intelligence techniques and their applications in fog/edge computing: an in-depth review. Open access; Published: 30 August 2025. Volume ...
  122. [122]
    Women make global gains as researchers, but gaps persist
    Jun 11, 2024 · The share of global STEM researchers who were women increased from 26 percent in 2000 to nearly 39 percent in 2022, according to the study. The ...