Mobile robot path planning algorithm research

• Main Author: Duan,Yibing
• Other Authors: Luo Yu
• Format: Thesis-Master by Coursework
• Language: English
• Published: Nanyang Technological University 2022
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence; Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics
• Online Access: https://hdl.handle.net/10356/161700
• Institution: Nanyang Technological University

Path planning that does not collide with obstacles in the surrounding environment is important to enable moving objects to autonomously find an efficient path from a specified starting point to a goal point in different environments. To achieve this goal, more and more path planning algorithms have been proposed. In recent years, the autonomous driving field and UAV technology have developed fast, path planning algorithms have become a popular research topic. The special features of various path planning algorithms are different, thus they are often used in different situations and environments. Consequently, it is important for the development of the technology to study path planning intelligence algorithms in terms of their own characteristics and applications. In this project, we start from the review of existing path planning algorithms, outline the basic principles and research progress of the commonly used algorithms under different categories, and summarize and review the results of various scholars in recent years. At the same time, an environment is designed, and several commonly used classical algorithms are simulated in this environment. Then we analyze the advantages and disadvantages of different algorithms from the experimental point of view. Through the analysis of various kinds of path planning algorithms, the D* algorithm is chosen as the major research focus in this project, which has some benefits that other heuristic algorithms do not have, but also has shortcomings. On this basis, an improved D* algorithm is proposed by revising the heuristic function. Finally, the effectiveness of the method is evaluated by experimental simulation.