For multiple unmanned aerial vehicles (UAVs) performing aerial search-attack tasks, there is a tradeoff between maximizing total benefit and minimizing consumption under the validity of constraints. This article proposes a dynamic discrete pigeon-inspired optimization algorithm to handle cooperative search-attack mission planning for UAVs, which integrates the centralized task assignment and distributed path generation aspects of the problem. Besides, a solution acceptance strategy is proposed to avoid frequent task switching. To design a reasonable objective function, the probability map is constructed and updated by Bayes formula to guide the following search motion, and a response threshold sigmoid model is adopted for target allocation during executing attack. Moreover, the flyable trajectories are generated by B-spline curves based on the simplified waypoints. Finally, numerical experiments prove that the proposed methods can provide feasible solutions for multiple UAVs considering different scenarios, such as the absence or presence of threats and insufficient resources. The results also show that the solution acceptance strategy is effective to improve performance. Moreover, the extensible mission planning system also integrates with an interactive 3D visualization simulation module, where the multi-UAV coordinated flight processes are demonstrated dynamically.

Foundation models are used to train a broad system of general data to build adaptations to new bottlenecks. Typically, they contain hundreds of billions of hyperparameters that have been trained with hundreds of gigabytes of data. However, this type of black-box vulnerability places foundation models at risk of data poisoning attacks that are designed to pass on misinformation or purposely introduce machine bias. Moreover, ordinary researchers have not been able to completely participate due to the rise in deployment standards. This study introduces the theoretical framework of scenarios engineering (SE) for building accessible and reliable foundation models in metaverse, namely, “SE-enabled foundation models in metaverse.” Particularly, the research framework comprises a six-layer architecture (infrastructure layer, operation layer, knowledge layer, intelligence layer, management layer, and interaction layer), which can provide controllability, trustworthiness, and interactivity for the foundation models in metaverse. This creates closed-loop, virtual–real, and human–machine environments that provides the best indices and goals for the foundation models, which allows us to fully validate and calibrate the corresponding models. Then, examples of use cases from the automotive industry are listed to provide transparency on the possible use and benefits of our approach. Finally, the open research topics of related frameworks are discussed.

The collective behaviors of animals, from schooling fish to packing wolves and flocking birds, display plenty of fascinating phenomena that result from simple interaction rules among individuals. The emergent intelligent properties of the animal collective behaviors, such as self-organization, robustness, adaptability and expansibility, have inspired the design of autonomous unmanned swarm systems. This article reviews several typical natural collective behaviors, introduces the origin and connotation of swarm intelligence, and gives the application case of animal collective behaviors. On this basis, the article focuses on the forefront of progress and bionic achievements of aerial, ground and marine robotics swarms, illustrating the mapping relationship from biological cooperative mechanisms to cooperative unmanned cluster systems. Finally, considering the significance of the coexisting-cooperative-cognitive human-machine system, the key technologies to be solved are given as the reference directions for the subsequent exploration.