Explore the vast range of titles available.

The main focus of this paper is on the family of evolutionary algorithms and their real-life applications. We present the following algorithms: genetic algorithms, genetic programming, differential evolution, evolution strategies, and evolutionary programming. Each technique is presented in the pseudo-code form, which can be used for its easy implementation in any programming language. We present the main properties of each algorithm described in this paper. We also show many state-of-the-art practical applications and modifications of the early evolutionary methods. The open research issues are indicated for the family of evolutionary algorithms.

The aim of this paper is to extend recent reflection on the evolution of strategic management by analyzing the field's object of study: strategy. We show how the concept of strategy has formed the backbone of the development of strategic management as an academic field and how consensus regarding it has evolved in the academic community during the stages of its historical development. We also address changes in the structure of the definition as it evolved through the growth of internal consistency, the centrality degree of the key terms that have shaped it, and how this evolution fostered the emergence of new research topics during the development of the discipline.

Economic reform in China has attracted growing attention from around the world owing to its significance for theory and practice. What has been largely missing in the literature is the temporal dimension, i.e., the changes over time in key variables such as organizational environment, firm strategic adaptations, and the performance implications. In this study, we investigate environment and strategic adaptations 12 years after Tan and Litschert examined these issues in 1990. Following a staged model, the study found that (1) organizational environment and firm strategic adaptations have co-evolved over time, (2) a new configuration has emerged and is related to improved performance, and (3) such a relationship is moderated by the stage during transition in which firms were founded. Specifically, firms founded since 1990 are more proactive and innovative than firms that had existed in the previous stage.

Mobile robots play a pivotal role in advancing smart manufacturing technologies. However, existing Obstacle avoidance path Planning (OP) algorithms for mobile robots suffer from low stability and applicability. Therefore, this paper proposes an enhanced Secret Bird Optimization Algorithm (SBOA)-based OP algorithm for mobile robots to address these challenges, termed AGMSBOA. Firstly, an adaptive learning strategy is introduced, where individuals enhance the diversity of the algorithm’s population by summarizing relationships among candidates of varying quality, thereby strengthening the algorithm’s ability to locate globally optimal obstacle avoidance path regions. Secondly, a group learning strategy is incorporated by dividing the population into learning and teaching groups, enhancing the algorithm’s exploitation capabilities, improving the accuracy of obstacle avoidance path planning, and reducing actual runtime. Lastly, a multiple population evolution strategy is proposed, which balances the exploration/exploitation phases of the algorithm by analyzing the nature of different individuals, improving the algorithm’s ability to escape suboptimal obstacle avoidance path traps. Subsequently, AGMSBOA was used to solve the OP problem on five maps and two OP problems in real-world environments. The experiments illustrate that AGMSBOA achieves more than 5% performance improvement in path length and a 100–win rate in runtime metrics, as well as faster convergence and stability of the solution. Therefore, AGMSBOA proposed in this paper is an efficient, robust, and robust OP method for mobile robots.

Flow shop scheduling has garnered significant attention from researchers over the past ten years, establishing itself as a prominent area of study within the field of scheduling. Nevertheless, there exists a paucity of research dedicated to addressing Non-Permutation Flow Shop Scheduling Problems. In this study, a Hybrid Evolution Strategies (HES) is suggested by combining the exploitation ability of Nawaz, Enscore, and Ham (NEH) Heuristic, the exploration ability of Improved Evolution Strategies (IES), and a Local Search Technique to minimize the makespan of NPFSSP. The primary solution is produced through the NEH Heuristic, serving as a foundational solution for the IES. The IES is applied in two stages, in the first stage it improves the permutation sequence found from the NEH heuristic. In the second stage of the IES, the permutation sequence on the first 40% of machines is fixed as found in the first stage. The sequence on the last 60% of machines is altered only so that the makespan is minimized and a good non-permutation sequence is found. Recombination and mutation are the main genetic operators in IES. For recombination in IES, 16 offspring are generated randomly from a single parent. The Quad swap mutation operator is employed in the IES to optimize the utilization of the solution space while minimizing computational time. To prevent trapping in local minima, a Local Search Technique is integrated into the IES algorithm, which guides solutions to less explored areas. Computational analyses indicate that HES exhibits superior performance regarding solution quality, computational efficiency, and robustness.

The development of large-scale cluster intelligence will inevitably lead to new problems of adversarial game control. Aiming at the problem of high dimension and high dynamics in the process of unmanned aerial vehicle (UAV) cluster confrontation game, and the traditional optimal control algorithm cannot meet the requirements of timeliness, the evolution strategies (ESs) optimization method is proposed and applied to large-scale UAV cluster. It effectively avoids the problem that it is difficult to obtain accurate gradients when using reinforcement learning to deal with high-dimensional models, and promotes autonomous UAVs to find strategies with higher performance. First, the confrontation game models including UAV motion, cluster behavior patterns and interaction are established. Second, two UAV cluster game algorithms using the OpenAI evolution strategy (OpenAI ES) and integrated evolution strategy (IES) are presented. Finally, the large-scale UAV attack and defense confrontation scenarios have been established, and different sampling proportions and different numbers of UAVs are fully simulated. The results show that the two proposed algorithms can effectively solve large-scale UAV cluster confrontation game problems, especially the adaptive IES algorithm, which has better performance and shows more strategic behavior for the UAVs, which improves the effectiveness and robustness of confrontation strategies.

To realize autonomous ships in the near future, possibility of automatic berthing has been investigated. Automatic berthing is not an easy task because of some complexities that are included in the problem, such as the nonlinearity of the low-speed maneuvering model, danger of collision with berth, etc. In this research, as a first step, the authors solved the off-line automatic berthing problem. Here, the optimal control problem was modeled as minimum-time problem, and the collision risk with the berth was taken into account. The authors attempted to apply the covariance matrix adaption evolution strategy (CMA-ES), which is considered state-of-the-art in evolutionary computation approaches for optimization of real-valued variables. In the problem dealt with here, a propeller and a rudder were used only as control inputs; so, the degree of difficulty was significantly high. Nevertheless, optimal control method based on the CMA-ES successfully gave us the offline results for typical situations considered. It is noteworthy that preparation of a feasible initial control input was not required in the calculation process, which made the proposed procedure robust. The calculation method proposed here is offline, but the results could be applied as an initial guess in an online (real-time) control problem.

This research reports on the recent development of black-box optimization methods based on single-step deep reinforcement learning and their conceptual similarity to evolution strategy (ES) techniques. It formally introduces policy-based optimization (PBO), a policy-gradient-based optimization algorithm that relies on a policy network to describe the density function of its forthcoming evaluations, and uses covariance estimation to steer the policy improvement process in the right direction. The specifics of the PBO algorithm are detailed, and the connections to evolutionary strategies are discussed. Relevance is assessed by benchmarking PBO against classical ES techniques on analytic functions minimization problems, and by optimizing various parametric control laws intended for the Lorenz attractor and the classical cartpole problem. Given the scarce existing literature on the topic, this contribution definitely establishes PBO as a valid, versatile black-box optimization technique, and opens the way to multiple future improvements building on the inherent flexibility of the neural networks approach.

The Crested Porcupine Optimizer (CPO), an emerging intelligent optimization algorithm, exhibits considerable potential for addressing complex engineering problems, yet its capabilities remain insufficiently investigated. Nevertheless, the original CPO is susceptible to premature convergence and suffers from insufficient population diversity. To effectively address these limitations, this paper proposes a multi-mechanism enhanced Crested Porcupine Optimizer (SDHCPO). Its core innovation lies in the integration of four key strategies: a Sobol-Opposition-Based Learning (Sobol-OBL) initialization strategy, which combines the Sobol sequence with opposition-based learning to generate an initial population that is more uniformly distributed in the high-dimensional search space; a cosine-annealing-based dynamic adjustment strategy that replaces the original random weights and substantially enhances convergence stability; the incorporation of the DE/rand/1 strategy in the first defense phase to disrupt positional dependence and prevent premature convergence; and a horizontal-vertical crossover strategy employed in the second defense phase to eliminate dimensional stagnation. Experimental results on two authoritative benchmark suites, CEC2017 and CEC2022, demonstrate that the proposed algorithm outperforms seven representative metaheuristic algorithms in terms of global exploration capability, local exploitation accuracy, and convergence robustness. Furthermore, empirical studies on five representative engineering design optimization problems show that SDHCPO consistently attains either the best-known solutions or highly competitive results reported in the literature, thereby further confirming its effectiveness and broad application potential for complex real-world engineering optimization tasks.

Fuzzy neural networks, which combine the strengths of fuzzy logic systems and artificial neural networks, prove to be effective in modeling industrial processes. However, because of the nonlinearity and nonstationarity exhibited in complex industrial processes, constructing an accurate model and maintaining its performance in uncertain environments have remained challenging. Hence, a self-organizing fuzzy neural network with an adaptive evolution strategy (AE-SOFNN) is proposed for nonlinear and nonstationary process modeling. First, a self-organizing mechanism based on the network learning accuracy and the activity of rules is developed to achieve a compact structure. Meanwhile, by integrating the least squares method and an improved second-order algorithm, a hybrid learning algorithm is applied to adjust network parameters. Then, an adaptive evolution strategy is proposed to enable the AE-SOFNN to better adapt to changes, aiming to ensure the accuracy and robustness of the constructed network in nonstationary environments. Specifically, an adaptive activation threshold based on generalization ability is developed to determine how to update, namely by either local updating or global updating. The variation of linear parameters during local updating is taken as an indicator of concept drift, helping to improve the global updating performance via the selection of appropriate samples. Finally, the effectiveness of the AE-SOFNN is evaluated by a chaotic time-series prediction problem and an industrial application, demonstrating the superiority of AE-SOFNN in modeling nonlinear and nonstationary processes.