Targeted Path Optimization Using RRT-MWOAII: A Hybrid Approach to Enhanced Smoothness in Robotic Path Planning

Abstract

Path planning in robotics and automation often demands solutions that effectively balance efficiency and path smoothness, particularly in diverse and large-scale environments. To address this, this paper presents the Rapidly Exploring Random Tree-Modified Whale Optimization Algorithm II (RRT-MWOAII), an enhanced version of the previous Rapidly Exploring Random Tree-Modified Whale Optimization Algorithm (RRT-MWOA) approach. The RRT-MWOAII is a hybrid technique that combines the strengths of the RRT path planning method and the MWOAII. It utilizes the RRT path as the initial solution and then applies the MWOAII to improve the smoothness of the RRT path. The key advancement in the RRT-MWOAII algorithm is the incorporation of a targeted global search, where the weakest solution is targeted instead of a random one during the global search phase. This targeted approach helps to efficiently identify and refine the weakest link in the solution, leading to improved overall path optimization. Additionally, the algorithm further refines its local solution by employing a neighborhood search, which allows for fine-tuning of the path. Simulations were conducted and evaluated on seven benchmarks, including RRT, RRT*, Bidirectional RRT (BiRRT), and state-of-the-art optimization methods such as the original Whale Optimization Algorithm (WOA), Improved Whale Optimization Algorithm (IWOA) and Sparrow Search Algorithm (SpSA). Experimental results show that MWOAII consistently produced shorter and smoother paths, outperforming its predecessor with a 31.6% improvement in the initial RRT path smoothness and a 21.05% better average smooth cost across all nine maps. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i>—Path planning in robotics and automation often requires solutions that balance efficiency and path smoothness across diverse and sometimes large-scale environments. This work introduces the Rapidly Exploring Random Tree-Modified Whale Optimization Algorithm II (RRT-MWOAII), an advanced path planning technique that addresses these challenges by combining the Rapidly Exploring Random Tree (RRT) method with the Modified Whale Optimization Algorithm II (MWOAII). The algorithm first uses RRT to identify a feasible initial path, then employs MWOA to improve path smoothness in a targeted manner. The RRT-MWOAII brings two significant enhancements over prior approaches: 1) a targeted global search that refines the weakest segment of the current path, reducing redundant computations, and 2) a neighborhood search for local fine-tuning, improving path smoothness and continuity. These improvements result in a substantial gain in path quality, with a 31.6% improvement in the initial RRT path smoothness and a 21.05% better average smooth cost across nine test environments compared to its predecessor.