Jiaxi Lu ^1* Ryota Takamido ² Yusheng Wang ² Jun Ota ²

• ¹ Faculty of Engineering, The University of Tokyo, Bunkyo, Japan
• ² Research into Artifacts, Center for Engineering, The University of Tokyo, Bunkyo, Tokyo, Japan

This study presents an experience-based hierarchical-structure optimization algorithm to address the robotic system environment design problem which combines motion planning and environment arrangement problems together. Motion planning problem which could be defined as a multiple-Degree-of-Freedom (m-DOF) problem, together with the environment arrangement problem which could be defined as a free DOF problem, is a high-dimensional optimization problem.Therefore, the hierarchical structure, at first environment arrangement problem solved in the higher layer, and motion planning problem solved in the lower layer, was introduced. Previously planned trajectories and past results for this design problem were first constructed as datasets, however, they cannot be seen as optimal. Therefore, this study proposed an experience-reuse manner, which selected the most "useful" experience from the datasets and reused it to query new problems, optimize the results in the datasets, and provide better environment arrangement with shorter path lengths within the same time. Therefore, a hierarchical structural caseGA-ERTC algorithm was proposed. In the higher layer, a novel approach employing case-injected genetic algorithm (GA) was implemented to tackle optimization challenges in robot environment design, leveraging experiential insights. Performance indices in the arrangement of the robot system's environment were determined by the robotic arm's motion and path length calculated using experience-driven random tree (ERT) algorithm. Moreover, the effectiveness of the proposed method is illustrated with the 12.59% decrease of path lengths by solving different settings of hard problems and 5.05% decrease in easy problems compared with other state-of-the-art methods in three small robots.