# Robotic Arm Trajectory Planning for Tunnel Lighting Cleaning Based on the CAW-PSO Algorithm

## TL;DR

A new algorithm improves robotic arm efficiency for tunnel lighting cleaning, reducing motion time significantly.

## Contribution

The CAW-PSO algorithm introduces chaotic maps, dynamic learning factors, and hybrid optimization to enhance trajectory planning.

## Key findings

- The CAW-PSO algorithm reduced simulation time by 69.94%.
- The mean relative error between simulation and experiment was 1.16%.
- The algorithm improves convergence and avoids local optima in trajectory planning.

## Abstract

Tunnel lighting cleaning is of significant practical importance for improving driving safety. To address the low operational efficiency of tunnel lighting cleaning tasks, a trajectory planning method based on the chaotic adaptive whale–particle swarm optimization (CAW-PSO) algorithm is proposed. Taking the SIASUN GCR16-2000 robotic arm as the research object, the trajectory is constructed using a 3-5-3 polynomial interpolation, with the objective of achieving time-optimal trajectory planning. In the CAW-PSO algorithm, a tent chaotic map is introduced to improve the quality of the population; a linearly decreasing inertia weight is designed to strike a balance between local and global search; dynamic learning factors are defined to strengthen the individual learning ability and global cognitive capability of particles; finally, the exploitation mechanism of the whale optimization algorithm is employed to avoid getting trapped in local optima and improve convergence accuracy. The simulation time is 3.661 s, a reduction of 69.94%. The experimental results yielded a mean relative error of 1.16%, indicating good agreement with the simulation results. The results of the simulation and experiment indicate that the CAW-PSO effectively reduces the motion time of the robotic arm, exhibiting superior applicability in trajectory planning for tunnel lighting cleaning robotic arms.