Collaborative Hunting Research Articles

CGJO: a novel complex-valued encoding golden jackal optimization

Golden jackal optimization (GJO) is inspired by mundane characteristics and collaborative hunting behaviour, which mimics foraging, trespassing and encompassing, and capturing prey to refresh a jackal’s position. However, the GJO has several limitations, such as a slow convergence rate, low computational accuracy, premature convergence, poor solution efficiency, and weak exploration and exploitation. To enhance the global detection ability and solution accuracy, this paper proposes a novel complex-valued encoding golden jackal optimization (CGJO) to achieve function optimization and engineering design. The complex-valued encoding strategy deploys a dual-diploid organization to encode the real and imaginary portions of the golden jackal and converts the dual-dimensional encoding region to the single-dimensional manifestation region, which increases population diversity, restricts search stagnation, expands the exploration area, promotes information exchange, fosters collaboration efficiency and improves convergence accuracy. CGJO not only exhibits strong adaptability and robustness to achieve supplementary advantages and enhance optimization efficiency but also balances global exploration and local exploitation to promote computational precision and determine the best solution. The CEC 2022 test suite and six real-world engineering designs are utilized to evaluate the effectiveness and feasibility of CGJO. CGJO is compared with three categories of existing optimization algorithms: (1) WO, HO, NRBO and BKA are recently published algorithms; (2) SCSO, GJO, RGJO and SGJO are highly cited algorithms; and (3) L-SHADE, LSHADE-EpsSin and CMA-ES are highly performing algorithms. The experimental results reveal that the effectiveness and feasibility of CGJO are superior to those of other algorithms. The CGJO has strong superiority and reliability to achieve a quicker convergence rate, greater computation precision, and greater stability and robustness.

Multi-Robot Collaborative Hunting in Cluttered Environments With Obstacle-Avoiding Voronoi Cells

Multi-Robot Collaborative Hunting in Cluttered Environments With Obstacle-Avoiding Voronoi Cells

A survey on collaborative hunting with robotic swarm: Key technologies and application scenarios

Compared with a single robot, robotic swarm realizes multi-agent cooperative operations through information interaction, and has such characteristics of wide combat monitoring range, flexible combat organization and strong reconfiguration. As the intelligence of robotic swarm, collaborative hunting tasks have been used in the fields of intrusion countermeasures, target elimination, scientific research, target rescue and etc. A comprehensive overview of current state of researches on collaborative hunting tasks with robotic swarm would be beneficial to researchers. Therefore, we provide an overview of research progress related to collaborative hunting tasks of robotic swarm in this paper. Specifically, we analyze key technologies in the collaborative hunting tasks from the perspectives of target searching, hunting task allocation and tracking path planning. Moreover, we summarize the differences of hunting strategies in different scenarios (i.e., air scenario, sea scenario and ground scenario), so it has important guiding significance for future researches. Finally, we discuss future research directions for collaborative hunting tasks of robotic swarm.

Temporary division of roles in group hunting for fish eggs by a coral reef fish

Division of roles was observed during group hunting by the false cleanerfish, Aspidontus taeniatus (Blenniidae), when they raid the nests of the damselfish (Pomacentridae) and eat their guarded eggs. In this paper, we provide the first description of the collaborative group egg-eating behavior by the false cleanerfish. When raiding the nests of the three-spot dascyllus, Dascyllus trimaculatus, whose eggs are guarded by parents, the false cleanerfish divided roles as follows: “decoy” or “watcher” to draw attention and attract attacks from the parents, and “hider” or “intruder” to avoid detection by the parents and invade the nest. The potential differential costs associated with each role are unique among examples of group hunting strategies in fishes. However, once any individual in the group successfully invaded the nest, all individuals quickly achieved successful predation of the eggs and gained immediate shared benefit. We propose that the group egg-eating behavior of the false cleanerfish not only reinforces the evidence that fish can collaborate with other individuals but also suggests the hypothesis that collaborative hunting can evolve through mutualism even in fishes. Digital video images related to the article are available at http://www.momo-p.com/showdetail-e.php?movieid=momo240411at01a, and http://www.momo-p.com/showdetail-e.php?movieid=momo240411at02a.

Collaborative hunting in artificial agents with deep reinforcement learning.

Collaborative hunting, in which predators play different and complementary roles to capture prey, has been traditionally believed to be an advanced hunting strategy requiring large brains that involve high-level cognition. However, recent findings that collaborative hunting has also been documented in smaller-brained vertebrates have placed this previous belief under strain. Here, using computational multi-agent simulations based on deep reinforcement learning, we demonstrate that decisions underlying collaborative hunts do not necessarily rely on sophisticated cognitive processes. We found that apparently elaborate coordination can be achieved through a relatively simple decision process of mapping between states and actions related to distance-dependent internal representations formed by prior experience. Furthermore, we confirmed that this decision rule of predators is robust against unknown prey controlled by humans. Our computational ecological results emphasize that collaborative hunting can emerge in various intra- and inter-specific interactions in nature, and provide insights into the evolution of sociality.

Solving Equations Systems Using the Penguins Search Optimization

Abstract The Penguin Search Optimization (PeSOA) is an optimization method based on collaborative hunting strategy of penguins. In this work, a solving linear equation systems method based on PeSOA is proposed. A dual population for PeSOA part was also tested. Experimental results obtained with our proposed method compared with those obtained with classical math methods, showed positive perspectives regarding possible extensions of the proposed method for systems of equations of larger dimensions. Conclusions as well as future research directions are also included.

An Improved Golden Jackal Optimization Algorithm Using Opposition-Based Learning for Global Optimization and Engineering Problems

Golden Jackal Optimization (GJO) is a recently developed nature-inspired algorithm that is motivated by the collaborative hunting behaviours of the golden jackals in nature. However, the GJO has the disadvantage of poor exploitation ability and is easy to get stuck in an optimal local region. To overcome these disadvantages, in this paper, an enhanced variant of the golden jackal optimization algorithm that incorporates the opposition-based learning (OBL) technique (OGJO) is proposed. The OBL technique is implemented into GJO with a probability rate, which can assist the algorithm in escaping from the local optima. To validate the efficiency of OGJO, several experiments have been performed. The experimental outcomes revealed that the proposed OGJO has more efficiency than GJO and other compared algorithms.

A Cooperative Hunting Method for Multi-USV Based on the A* Algorithm in an Environment with Obstacles.

A single unmanned surface combatant (USV) has poor mission execution capability, so the cooperation of multiple unmanned surface ships is widely used. Cooperative hunting is an important aspect of multi USV collaborative research. Therefore, this paper proposed a cooperative hunting method for multi-USV based on the A* algorithm in an environment with obstacles. First, based on the traditional A* algorithm, a path smoothing method based on USV minimum turning radius is proposed. At the same time, the post order traversal recursive algorithm in the binary tree method is used to replace the enumeration algorithm to obtain the optimal path, which improves the efficiency of the A* algorithm. Second, a biomimetic multi USV swarm collaborative hunting method is proposed. Multiple USV clusters simulate the hunting strategy of lions to pre-form on the target's path, so multiple USV clusters do not require manual formation. During the hunting process, the formation of multiple USV groups is adjusted to limit the movement and turning of the target, thereby reducing the range of activity of the target and improving the effectiveness of the algorithm. To verify the effectiveness of the algorithm, two sets of simulation experiments were conducted. The results show that the algorithm has good performance in path planning and target search.

Fast random opposition-based learning Golden Jackal Optimization algorithm

Nowadays, optimization techniques are required in various engineering domains in order to find optimal solutions for complex problems. As a result, there is a growing tendency among scientists to enhance existing nature-inspired algorithms using various evolutionary strategies and to develop new nature-inspired optimization methods that can properly explore the feature space. The recently designed nature-inspired metaheuristic, named the Golden Jackal Optimization​ (GJO) algorithm, was inspired by the collaborative hunting actions of the golden jackal in nature to solve various challenging problems. However, like other approaches, the GJO has the limitations of poor exploitation ability, ease to get stuck in a local optimal region, and an improper balancing of exploration and exploitation. To overcome these limitations, this paper proposes a novel contribution to GJO based on a new technique, namely the fast random opposition-based learning Golden Jackal Optimization algorithm (FROBL-GJO). The FROBL technique is mainly inspired by opposition-based learning (OBL) and random opposition-based learning (ROBL) techniques to enhance the optimization precision and convergence speed of the GJO algorithm. Furthermore, two other models, such as OBL-GJO and ROBL-GJO, are also proposed for comparison purposes. To examine the proficiency of the newly proposed FROBL-GJO algorithm, it has been examined with several well-known existing meta-heuristic algorithms while solving the CEC-2005 and CEC-2019 benchmark test functions and real-life engineering problems. The experimental outcomes and statistical tests reveal the superior performance of the proposed FROBL-GJO in solving both global optimization and engineering design problems. Hence, the findings of benchmark functions and engineering problems endorse that the proposed FROBL-GJO algorithm can be considered a promising method for solving complex optimization problems.

Collaborative planning algorithm for incomplete navigation graphs

In a complex environment, in order to improve the efficiency of multi-AUV collaborative work, this paper proposes a new collaborative hunting algorithm based on the Bionic Neural Wave Network (BNWN) algorithm. This algorithm integrates search, tracking and capture of targets by multi-AUV under the incomplete navigation graphs. A search mechanism with memory tabu that to avoid redundant search and improve global search efficiency is designed. Then a real-time redistribution method is embedded into this algorithm to ensure the optimal matching state during the tracking and capture process. Further, multi-AUV track and capture prey based on energy consumption models and self-learning models, and recast time-varying navigation maps through the recognition mechanisms, under the whole collaborative operations. Simulation results have proved that the number of multi-AUV path turns is reduced and the execution time is shortened by an average of 81%. In this way, the optimal matching state is maintained, the repeated search and partial self-locking problems are overcome, and the efficient capture of intelligent prey is realized.

Pneumothorax prediction using a foraging and hunting based ant colony optimizer assisted support vector machine

Although PNLB is generally considered safe, it is still invasive and risky. Pneumothorax, the most common complication of lung puncture, can cause shortness of breath, chest pain, and even life-threatening. Therefore, the auxiliary diagnosis for pneumothorax is of great clinical interest. This paper proposes an ant colony optimizer with slime mould foraging behavior and collaborative hunting, called SCACO, in which slime mould foraging behavior is combined to improve the convergence accuracy and solution quality of ACOR. Then the ability of ACO to jump out of the local optimum is optimized by an adaptive collaborative hunting strategy when trapped in the local optimum. As a first step toward Pneumothorax diagnostic prediction, we suggested an SVM classifier based on bSCACO (bSCACO-SVM), which uses the proposed SCACO's binary version as the basis for its feature selection algorithms. To demonstrate the SCACO performance, we first used the slime mould foraging behavior and adaptive cooperative hunting strategy, then compared SCACO with nine basic algorithms and nine variants, respectively. Finally, we verified bSCACO-SVM on various widely used public datasets and applied it to the Pneumothorax prediction issue, showing that it has robust classification prediction capacity and can be successfully employed for tuberculous pleural effusion diagnostic prediction.

Qualitative analysis for a diffusive predator-prey model with hunting cooperation and holling type III functional response

The Spatio-temporal pattern induced by self-diffusion of a predator-prey model with Boiling type III functional response that incorporates the hunting cooperation between predators has been investigated in this paper. For the local model without structure, the stability of non-negative equilibria with or without collaborative hunting in predators is studied. For the Spatio-temporal model, we analyze the effect of hunting cooperation term on diffusion-driven Turing instability of the homogeneous positive equilibria. To get an idea about patterns formation near the Turing bifurcation, we derive and give a detailed study of the amplitude equation using the multiple-scale analysis. Our result shows that hunting cooperation plays a crucial role in determining the stability and the Turing bifurcation of the model, which is in sharp contrast to the case without cooperation in hunting. Furthermore, some numerical simulations are illustrated to visualize the complex dynamic behavior of the model.

Metaheuristic Optimization for Enhancing Cyber Security Index Prediction: A DTO+FGW Approach with MLP Integration

In the realm of cybersecurity, the evaluation and enhancement of cyber resilience are paramount to safeguarding nations and organizations against evolving digital threats. This paper introduces a novel approach that integrates the Dipper Throated Algorithm (DTO) and the Grey Wolf Optimizer (GWO) to fortify the analysis of Cyber Security Indexes. These indexes encompass vital metrics, including the Cybersecurity Exposure Index (CEI), Global Cyber Security Index (GCI), National Cyber Security Index (NCSI), and Digital Development Level (DDL). Leveraging the adaptive nature of DTO and the collaborative hunting strategies of GWO, the proposed DTO+GWO algorithm aims to optimize the evaluation of cyber readiness, exposure levels, and global commitments to cybersecurity. The Cyber Security Indexes dataset, featuring indicators from 193 countries, serves as the testing ground. This study contributes to advancing cyber threat assessment methodologies, fostering a proactive stance in the face of cyber risks globally. Through rigorous optimization, the DTO+GWO algorithm exhibits promising potential to elevate the precision and efficacy of cybersecurity evaluations. The optimization results demonstrate a notable achievement, with an RMSE of 0.0090, reflecting the algorithm's enhanced performance in fine-tuning the assessment of cybersecurity indexes.

Golden jackal optimization: A novel nature-inspired optimizer for engineering applications

A new nature-inspired optimization method, named the Golden Jackal Optimization (GJO) algorithm is proposed, which aims to provide an alternative optimization method for solving real-world engineering problems. GJO is inspired by the collaborative hunting behaviour of thegolden jackals(Canis aureus). The three elementary steps of algorithm are prey searching, enclosing, and pouncing, which are mathematically modelled and applied. The ability of proposed algorithm is assessed, by comparing with different state of the art metaheuristics, on benchmark functions. The proposed algorithm is further tested for solving seven different engineering design problems and introduces a real implementation of the proposed method in the field of electrical engineering. The results of the classical engineering design problems and real implementation verify that the proposed algorithm is appropriate for tackling challenging problems with unidentified search spaces.

Self-organized search-attack mission planning for UAV swarm based on wolf pack hunting behavior

Cooperative search-attack is an important application of unmanned aerial vehicle (UAV) swarm in military field. The coupling between path planning and task allocation, the heterogeneity of UAVs, and the dynamic nature of task environment greatly increase the complexity and difficulty of the UAV swarm cooperative search-attack mission planning problem. Inspired by the collaborative hunting behavior of wolf pack, a distributed self-organizing method for UAV swarm search-attack mission planning is proposed. First, to solve the multi-target search problem in unknown environments, a wolf scouting behavior-inspired cooperative search algorithm for UAV swarm is designed. Second, a distributed self-organizing task allocation algorithm for UAV swarm cooperative attacking of targets is proposed by analyzing the flexible labor division behavior of wolves. By abstracting the UAV as a simple artificial wolf agent, the flexible motion planning and group task coordinating for UAV swarm can be realized by self-organizing. The effectiveness of the proposed method is verified by a set of simulation experiments, the stability and scalability are evaluated, and the integrated solution for the coupled path planning and task allocation problems for the UAV swarm cooperative search-attack task can be well performed.

Task dynamics define the contextual emergence of human corralling behaviors.

Social animals have the remarkable ability to organize into collectives to achieve goals unobtainable to individual members. Equally striking is the observation that despite differences in perceptual-motor capabilities, different animals often exhibit qualitatively similar collective states of organization and coordination. Such qualitative similarities can be seen in corralling behaviors involving the encirclement of prey that are observed, for example, during collaborative hunting amongst several apex predator species living in disparate environments. Similar encirclement behaviors are also displayed by human participants in a collaborative problem-solving task involving the herding and containment of evasive artificial agents. Inspired by the functional similarities in this behavior across humans and non-human systems, this paper investigated whether the containment strategies displayed by humans emerge as a function of the task's underlying dynamics, which shape patterns of goal-directed corralling more generally. This hypothesis was tested by comparing the strategies naïve human dyads adopt during the containment of a set of evasive artificial agents across two disparate task contexts. Despite the different movement types (manual manipulation or locomotion) required in the different task contexts, the behaviors that humans display can be predicted as emergent properties of the same underlying task-dynamic model.

Identification of Chua’s chaotic circuit parameters using penguins search optimisation algorithm

ABSTRACT In this paper, the Penguins Search optimisation (PeSOA) Algorithm is used to identify optimal control parameters of the Chua circuit. The PeSOA algorithm, which is one of the nature-inspired algorithms, is mainly based on the collaborative hunting concept of penguins. In this algorithm, each penguin individually starts its search process, then communicates its position and the number of fish found to his group. The main objective of this strategy is to synchronise dives among the group in order to achieve a global solution. In this paper, a PeSOA algorithm is adopted to explore the search space for locating the optimum intervals and identify the unknown Chua’s system parameters without any partial knowledge of the internal structure. The identified parameters, obtained by minimising the objective function between the estimated and the output values of the system, are used to obtain stable oscillations. The obtained results show that the PeSOA algorithm gives accurate results and the identified parameters produce a stable oscillation of Chua’s chaotic circuit.

Group hunting in harbour porpoises (Phocoena phocoena)

Cooperative hunting involves individual predators relating in time and space to each other’s actions to more efficiently track down and catch prey. The evolution of advanced cognitive abilities and sociality in animals are strongly associated with cooperative hunting abilities as has been shown in lions, chimpanzees, and dolphins. Much less is known about cooperative hunting in seemingly unsocial animals, such as the harbour porpoise (Phocoena phocoena (Linnaeus, 1758)). Using drones, we were able to record 159 hunting sequences of porpoises, out of which 95 sequences involved more than one porpoise. To better understand if the harbour porpoises were individually attracted by the fish school or formed an organized hunting strategy, the behaviour of each individual porpoise in relation to the targeted fish school was analysed. The results indicate role specialization, which is considered the most sophisticated form of collaborative hunting and only rarely seen in animals. Our study challenges previous knowledge about harbour porpoises and opens up for the possibility of other seemingly non-social species employing sophisticated collaborative hunting methods.

Hypercarnivorous teeth and healed injuries to Canis chihliensis from Early Pleistocene Nihewan beds, China, support social hunting for ancestral wolves.

Collaborative hunting by complex social groups is a hallmark of large dogs (Mammalia: Carnivora: Canidae), whose teeth also tend to be hypercarnivorous, specialized toward increased cutting edges for meat consumption and robust p4-m1 complex for cracking bone. The deep history of canid pack hunting is, however, obscure because behavioral evidence is rarely preserved in fossils. Dated to the Early Pleistocene (>1.2 Ma), Canis chihliensis from the Nihewan Basin of northern China is one of the earliest canines to feature a large body size and hypercarnivorous dentition. We present the first known record of dental infection in C. chihliensis, likely inflicted by processing hard food, such as bone. Another individual also suffered a displaced fracture of its tibia and, despite such an incapacitating injury, survived the trauma to heal. The long period required for healing the compound fracture is consistent with social hunting and family care (food-sharing) although alternative explanations exist. Comparison with abundant paleopathological records of the putatively pack-hunting Late Pleistocene dire wolf, Canis dirus, at the Rancho La Brea asphalt seeps in southern California, U.S.A., suggests similarity in feeding behavior and sociality between Chinese and American Canis across space and time. Pack hunting in Canis may be traced back to the Early Pleistocene, well before the appearance of modern wolves, but additional evidence is needed for confirmation.

Multiautonomous underwater vehicle consistent collaborative hunting method based on generative adversarial network

The time-varying ocean currents and the delay of underwater acoustic communication have caused the uncertainty of single autonomous underwater vehicle (AUV) tracking target and the inconsistency of multi-AUV coordination, which make it difficult for multiple AUVs to form a hunting alliance. To solve the above problems, this article proposes the multi-AUV consistent collaborative hunting method based on generative adversarial network (GAN). Firstly, the three-dimensional (3D) kinematic model of AUV is established for the underwater 3D environment. Secondly, combined with the Laplacian matrix, the topology of the hunting alliance in the ideal environment is established, and the control rate of AUV is calculated. Finally, using the GAN network model, the control relationship after environmental interference is used as the input of the generative model. The control rate in the ideal environment is used as the comparison object of the discriminative model. Using the iterative training of GAN to generate a control rate that adapts to the current interference environment and combining multi-AUV topological hunting model to achieve successful hunting of noncooperative target, the experimental results show that the algorithm reduces the average hunting time to 62.53 s and the success rate of hunting is increased to 84.69%, which is 1.17% higher than the particle swarm optimization-constant modulus algorithm (PSO-CMA) algorithm.