Application of an improved whale optimization algorithm in time-optimal trajectory planning for manipulators.

Area of Science:

• Robotics
• Artificial Intelligence
• Optimization Algorithms

Background:

• Traditional manipulator systems often exhibit unstable, non-uniform, and inefficient motion trajectories.
• Existing trajectory planning methods struggle to achieve optimal performance and smooth motion.

Purpose of the Study:

• To propose an improved whale optimization algorithm (WOA) for time-optimal trajectory planning in manipulator systems.
• To enhance the global and local search capabilities of the WOA for superior optimization performance.

Main Methods:

• Incorporated an inertia weight factor into the WOA's core formulas, controlled via reinforcement learning.
• Integrated the variable neighborhood search (VNS) algorithm to bolster local optimization.
• Compared the enhanced WOA against several standard optimization algorithms.

Main Results:

• The improved WOA demonstrated superior performance compared to other commonly used optimization algorithms.
• The algorithm successfully generated smooth and continuous manipulation trajectories.
• Achieved significantly higher work efficiency in trajectory planning tasks.

Conclusions:

• The enhanced whale optimization algorithm effectively addresses the limitations of traditional manipulator trajectory planning.
• The proposed method offers a robust solution for achieving time-optimal, smooth, and efficient robot motion.
• Reinforcement learning and VNS integration significantly boost the WOA's optimization capabilities.