A Dynamic Programming-Based Path Planning Method for Mobile Robots in an Indoor Intelligent Environment

• Main Authors: CheWang, 王晢
• Other Authors: Chin-Tien Huang
• Format: Others
• Language: en_US
• Published: 2014
• Online Access: http://ndltd.ncl.edu.tw/handle/26569970589165028171

碩士 === 國立成功大學 === 機械工程學系 === 102 === Intelligent living space have gained much attention due to its potential application over the past few years. Promoted by the governments around the globe, applications of intelligent environments are becoming more accessible to the public. One of the key enabling technologies is Robotics. With the arrival of domestic robots, technologies such as robot navigation and localization urgent in indoor environments. In this thesis, a structure of intelligent environment with a working robot system is proposed. The structure is composed of a Wiimote Localization System monitoring robot positions and a Mobile Robot System that works as a moving platform, which other robots can be built on. To navigate the robot, a DP-based path planning method is proposed to find an obstacle-free path. The method is tested in a designed simulated environments, where static and dynamic obstacles are simulated using potential functions. In addition, the path-planning method is optimized for finding distance-efficient path, which is inspired by problem of busy commute for indoor robots. The method is compared to other path-planning methods such as Potential Field and Bug Algorithm, and as suggested by simulation and experiment results, it has better performance than both methods in the proposed environment structure. With the integration of navigation methods, the system has the potential to be used in extensive applications. Cloud robotics, a cloud technology-based network can be adopted to make the system more robust and flexible in the future.