Optimized Intelligent Localization Through Mathematical Modeling and Crow Search Algorithms

Area of Science:

• Robotics
• Artificial Intelligence
• Optimization Algorithms

Background:

• Localization is crucial for robots and mobile systems, but current methods lack precision for high-demand applications.
• Existing localization techniques face limitations in achieving the required accuracy across diverse operational domains.

Purpose of the Study:

• To enhance localization accuracy by integrating mathematical modeling with the Crow Search Algorithm (CSA).
• To identify the most probable position within a defined search space for improved robotic navigation.

Main Methods:

• Defined an initial search area using a network of fixed anchor points.
• Reduced the search area via mathematical calculation of circle intersections from anchor points.
• Employed a modified Crow Search Algorithm (CSA) to iteratively refine candidate point centroids for optimal position estimation.

Main Results:

• The proposed algorithm demonstrated superior localization accuracy compared to existing methods in both real and simulated datasets.
• Achieved a significant accuracy improvement, reaching 98% precision.
• Validated the effectiveness for applications demanding high accuracy with minimal infrastructure.

Conclusions:

• The integrated mathematical modeling and CSA approach significantly enhances localization accuracy.
• The methodology offers a computationally efficient solution for high-precision localization needs.
• Confirms the algorithm's viability for applications requiring minimal infrastructure and low computational complexity.