Quantum collapse mutation-based Salp Swarm Algorithm (QCM-SSA) for spatial alliance of point clouds

The consistency of the metaphor approaches is crucial in attaining reliable and optimal solutions in multifaceted computational engineering and optimization processes. Although the Salp Swarm Algorithm (SSA) has earned recognition owing to its simplicity and efficiency, it often incurs from premature convergence in complicated and multi-modal settings. This constraint becomes especially crucial for tasks needing precision, such as 3D point cloud registration (PCR), where the confined minima may impede the fine spatial alignment of the point clouds. To address this, we present a hybrid approach (HA) referred to as Quantum Collapse Mutation-inspired SSA (QCM-SSA), which incorporates quantum-driven likelihood collapse and Gaussian-based mutation dynamics into the standard SSA framework. The quantum collapse operator provides regulated randomness, enabling the salp to avoid deceptive local optima, and the mutation framework offers a diversified search procedure through adaptable Gaussian perturbations. The suggested QCM-SSA is employed to transform the source point cloud to their target cloud, by optimizing the six transformation components - three rotational and three translational. This registration procedure is validated utilizing the standard real-world Bildstein Station1 dataset and evaluated across the registration metrics. The findings outline that the QCM-SSA is a reliable and trustworthy approach in regards to the greater accuracy and reduced registration error.