# Trajectory Planning of Spraying Robot Based on Multi Strategy Improved Beluga Optimization Algorithm

## TL;DR

This paper introduces an improved beluga whale optimization algorithm for planning smooth and efficient trajectories for plasma-spraying robots on complex surfaces.

## Contribution

The novel contribution is the integration of tent chaotic mapping and sine-cosine algorithms to enhance the beluga whale optimization algorithm's performance.

## Key findings

- The improved beluga whale optimization (IBWO) algorithm outperforms original and other comparative algorithms in convergence accuracy and stability.
- The IBWO-generated joint trajectories are smooth and meet constraints well for complex surface spraying tasks.

## Abstract

In this paper, a trajectory planning method based on an improved beluga whale optimization algorithm is proposed for the trajectory planning of plasma-spraying robot with complex surfaces. Firstly, the system architecture, kinematics model and trajectory planning constraints of the 6-DOF mobile plasma robot are analyzed, including kinematics, dynamics and environmental constraints, and a constrained-objective optimization function with time optimization, energy consumption and smoothness as objectives is established. Secondly, aiming at the shortage of the balance between global search and local development of the original beluga optimization algorithm, the tent chaotic mapping strategy is introduced to enhance the population diversity, and the sine and cosine algorithm is integrated to optimize the search process, so as to improve the convergence accuracy and stability. The experimental part is verified by the standard test function and the special index of trajectory planning. The results show that the IBWO algorithm is significantly better than the original beluga optimization, particle swarm optimization and other comparative algorithms in convergence accuracy, stability and comprehensive performance. In addition, the trajectory planning example shows that the joint trajectory generated by improved beluga whale optimization is smooth and has high constraint satisfaction, which is suitable for complex surface spraying tasks.