RBPF and ICP based SLAM and Q-learning based Obstacle Avoidance Strategy for Home Service Robots

• Main Authors: Hsiang-TingChen, 陳湘婷
• Other Authors: Tzuu-Hseng S. Li
• Format: Others
• Language: en_US
• Published: 2014
• Online Access: http://ndltd.ncl.edu.tw/handle/9fetn3

碩士 === 國立成功大學 === 電機工程學系 === 102 === This thesis mainly discusses the design and implementation of simultaneous localization and mapping (SLAM) and obstacle avoidance strategies for home service robots. The SLAM system is first built using the Rao-Blackwellized Particle Filter (RBPF) method and Iterative Closest Point (ICP) algorithm. The robot learns the map for an unknown environment through information on the distance received by a laser range finder. The ICP algorithm estimates the pose of the robot by iteratively revising the transformation from the prior map to the posterior observation. The RBPF method is a robust way to solve the SLAM problem, which can deal with both the nonlinear and non-Gaussian state space model. Secondly, Q-learning is applied to the four wheel independent steering and four wheel independent driven (4WIS4WID) platform for obstacle avoidance during navigation. After the learning step, the robot navigates smoothly through the environment away from dangers. In the end, the methods mentioned above are implemented in the experimental results in the laboratory and in the competition, Restaurant Mission, in robot@home league at RoboCup Japan Open 2014. The validity and efficiency of the SLAM system and strategy system for the home service robot are demonstrated.