الفهرس 
صفحة العنوانOnly 14 pages are availabe for public view
 |  | from | 95 |  |  |
| | | from | 95 | | |
Abstract
Abstract
Motion planning is a task of finding a feasible and optimal path that satisfies a set of constraints and reaches a predefined goal; such function is essential for any autonomous robots and has received considerable amount of attention from the control and artificial intelligence (AI) communities. Since motion planning algorithms ignore experience when solving new motion planning problems, experience-based algorithms have emerged to overcome this information reuse-ability limitation and help reducing computation time by engaging experience for solving similar motion planning problems. This thesis aims to extended traditional motion planning algorithms by employing powerful AI techniques like case-based reasoning (CRB) for computational reduction. Then, it will introduce two approaches for solving the motion planning problem using experience without any traditional planner involvement. Finally, an experience-based scheme extension will be demonstrated for improving path quality while maintaining response time.