Optimized Path Planning for Indoor Environments with Ant Colony and Curve Smoothing Algorithm

In this technological-world of high speed, where every operation needs to be performed instantaneously and more efficiently, scientists and engineers have started focus on the meta-heuristic methods, which are more strong and adaptable, and their use to solve the autonomous problems of the mobile robots to navigate on any environment, the Ant Colony Optimization (ACO) algorithm is one of such solution assists in solving the problem of robot path planning (PP). Thus, in order to migrate its shortcomings and enhance the robustness and quick execution, this paper proposes a new way of using the Ant Colony (AC) concept, which ensures to solve the limitations of traditional ACO, such as computational execution time. The modified algorithm built on the condition-based rules, named the Condition-Based Ant Colony Concept (CB-ACC). The algorithm was tested on three different maps to examine the output efficiency and the computational execution time, as well as the path distance. The results show that the proposed algorithm is completely efficient in small-scale environments and remarkably better in large-scale environments. Moreover, we update the CB-ACC to improve the path distance. We then simulate the algorithm in the same environments and discover its efficiency in achieving an optimal smooth path using the Bezier curve. Simulation results show the efficiency of CB-ACC, as well as how effective it is for static-complex environments. Moreover, this paper presents the efficiency of the algorithm on different types of maps.