Research on Trajectory Planning of Six-Degree-of-Freedom Robotic Arm Based on Improved Genetic Algorithm

Integrating intelligent sensor technologies with robotic manipulators is central to advancing smart manufacturing systems. This study presents a comprehensive trajectory planning and optimization framework for a six-degree-of-freedom (6-DOF) robotic arm equipped with sensor-driven control to enhance task precision and reduce execution time. Five interpolation methods were evaluated in both Cartesian and joint spaces, with an improved cubic B-spline fitting method selected for its superior trajectory smoothness and adaptability. A novel genetic algorithm (GA) was developed to optimize time-based trajectory execution, incorporating a penalty-based constraint handling mechanism and a sinusoidal function for adaptive variation in crossover and mutation rates. Simulation results demonstrated a 30–33% reduction in total motion time compared to the unoptimized baseline, lowering the execution time from 20.00 s to 13.38 s across five trajectory segments. The algorithm ensured compliance with mechanical constraints on angular velocity, acceleration, and jerk. Validation was performed using a co-simulation platform integrating MATLAB Simscape, SolidWorks CAD models, and the Robotics Toolbox. Simulated joint angles, velocities, and accelerations exhibited < 2% mean absolute percentage error (MAPE) against theoretical predictions, confirming the accuracy of the inverse kinematics and optimization process. This work demonstrates the viability of sensor-integrated, optimization-driven robotic arms for time-sensitive, high-precision operations in Industry 4.0 environments.