Multi-objective path planning for mobile robot with an improved artificial bee colony algorithm.

Area of Science:

• Robotics
• Artificial Intelligence
• Optimization Algorithms

Background:

• Path planning (PP) is crucial for autonomous mobile robot navigation.
• The multi-objective PP problem is computationally complex and often treated as an NP-hard problem.
• Intelligent optimization algorithms, like the artificial bee colony (ABC) algorithm, are increasingly used to address PP challenges.

Purpose of the Study:

• To propose an improved artificial bee colony (ABC) algorithm, termed IMO-ABC, for multi-objective path planning in mobile robots.
• To optimize path length and path safety simultaneously as two key objectives.
• To enhance the efficiency and effectiveness of PP solutions for autonomous navigation.

Main Methods:

• A well-environment model and path encoding method were developed to ensure feasible solutions.
• A hybrid initialization strategy was employed for generating efficient initial feasible solutions.
• Path-shortening and path-crossing operators were integrated into the IMO-ABC algorithm.
• Variable neighborhood local search and global search strategies were incorporated to improve exploitation and exploration.

Main Results:

• The proposed IMO-ABC algorithm was tested on various maps, including a real-world environment.
• Simulation results demonstrated the effectiveness of the integrated strategies through comparisons and statistical analyses.
• The IMO-ABC algorithm achieved superior solutions, as indicated by hypervolume and set coverage metrics.

Conclusions:

• The developed IMO-ABC algorithm offers an effective approach for multi-objective path planning in mobile robots.
• The proposed strategies enhance the quality of navigation solutions, balancing path length and safety.
• IMO-ABC provides a valuable tool for decision-makers in autonomous navigation systems.