Research on Robot Path Planning Integrating Multiple Algorithm Concepts

Path planning is a core technology for mobile robots to achieve autonomous navigation and obstacle avoidance. To address the shortcomings of traditional path planning algorithms in terms of adaptability to complex environments, global convergence speed, and path optimality, this paper proposes an improved ant colony optimization algorithm (ADRACO) that integrates the ideas of A*, Dynamic-Window Approach (DWA), and Rapidly-exploring Random Tree (RRT). The algorithm enhances adaptability to complex environments and balances exploration and convergence by introducing A* hybrid heuristics and dynamic weight adjustment. It incorporates DWA's direction prioritization and RRT's randomness to construct a multi-strategy node selection mechanism, improving global optimization capabilities. Additionally, a multi-level pheromone update and adaptive early-stopping strategy are employed to strengthen optimal path retention and enhance convergence efficiency. Experimental results demonstrate that ADRACO outperforms A*, RRT, traditional ACO, and IACO algorithms regarding path length, node count, convergence speed, and stability, exhibiting strong robustness and efficiency across varying obstacle densities and map scales. This algorithm provides an effective solution for path planning in complex scenarios for mobile robots, offering significant engineering application value.