Trajectory optimization for wall-building robots in accordance with nonlinear viscoelastic cement mortar environment

Area of Science:

• Robotics
• Construction Engineering
• Artificial Intelligence

Background:

• Suboptimal masonry quality is a challenge for wall-building robots in viscoelastic cement mortar environments.
• Developing accurate viscoelastic mechanical models for cement mortar is complex.
• Existing trajectory planning methods may not optimize multiple performance metrics simultaneously.

Purpose of the Study:

• To propose a multi-objective trajectory optimization method for wall-building robots.
• To enhance masonry quality and robot operational efficiency.
• To provide a robust framework for intelligent construction robots.

Main Methods:

• Utilized orthogonal experimental design to gather data.
• Developed a Kriging surrogate model to link experimental data and design variables.
• Implemented the Fractal Evolutionary Particle Swarm Optimization (FEPSO) algorithm for multi-objective optimization.
• Employed the TOPSIS algorithm to select an optimal masonry scheme from the Pareto set.

Main Results:

• The FEPSO algorithm outperformed NSGA-II and MOPSO.
• Optimized trajectory planning increased robot efficiency by 23.66% and reduced energy consumption by 29.33%.
• Masonry error was significantly reduced from 2.57 mm to 0.14 mm, with improved trajectory smoothness (90.47%) and decreased contact force (7.03%).

Conclusions:

• The proposed Kriging-FEPSO method effectively optimizes wall-building robot trajectories for enhanced masonry quality.
• The method offers significant improvements in efficiency, energy consumption, and accuracy.
• Provides valuable theoretical and practical insights for trajectory planning and quality control in intelligent construction.