Operation Path Planning for Rail-Type Rebar Binding Robots Based on Improved Ant Colony Algorithm

In recent years, the engineering construction industry has faced challenges such as aging and labor shortages. Various intelligent construction robots have been researched and applied to bridge and building construction sites. Complete coverage path planning (CCPP) is crucial for rebar binding robots to achieve autonomous operation based on scene information, significantly enhancing operational efficiency and reducing energy consumption. The traditional CCPP method, mainly employing the cell decomposition method, often results in redundant paths and excessive turning operations in scenarios with numerous and complex obstacles. This paper proposes an improved ant colony algorithm to address the deadlock issue encountered by traditional ant colony algorithms when solving complete traversal problems. Taking into account the unique operational mode of the binding robot on the rebar mesh, this method introduces a distance adaptive coefficient to adjust the probability of transitioning in different directions during the search process and enhances the convergence speed and overall optimization capability of the algorithm by improving the information pheromone update method. This study uses actual data from the construction site and simulation experiments to test the performance of the algorithm. Compared with the results of the traditional CCPP method, the length of the path is reduced by about 15%, and the path repetition rate is reduced by more than 30%. Experimental results demonstrate its applicability and superiority in adapting to various sizes and distributions of obstacles in work environments for rebar binding robot path planning.