Title :
An Adaptive UKF-Based Particle Filter for Mobile Robot SLAM
Author_Institution :
Electron. Inf. Instn., Shanghai Dianji Univ., Shanghai, China
Abstract :
The mobile robot simultaneous localization and mapping (SLAM) in unknown environments has been considered to be an important and fundamental problem in the mobile robotics research domain. Nowadays most methods for SLAM are focused on probabilistic Bayesian estimation, this paper propose an unscented Kalman filter (UKF) assistant-proposal distribution (UKF-APD) particle algorithm,compute the Euclidean distance of particle approximate distribution to the UKF-APD, and take it as an adaptive particle-resampling criterion, the proposed algorithm can avoid particlespsila impoverishment and deviation to the real robot posterior distribution. Experimental results demonstrate the effectiveness of the proposed algorithm.
Keywords :
Bayes methods; Kalman filters; SLAM (robots); mobile robots; particle filtering (numerical methods); Euclidean distance; SLAM; assistant-proposal distribution particle algorithm; mobile robot; particle filter; probabilistic Bayesian estimation; simultaneous localization and mapping; unscented Kalman filter; Adaptive filters; Artificial intelligence; Bayesian methods; Intelligent robots; Jacobian matrices; Mobile robots; Orbital robotics; Particle filters; Simultaneous localization and mapping; State estimation; Extended Kalman Filter; Unscented Kalman Filter; particle-resampling; robot SLAM;
Conference_Titel :
Artificial Intelligence, 2009. JCAI '09. International Joint Conference on
Conference_Location :
Hainan Island
Print_ISBN :
978-0-7695-3615-6
DOI :
10.1109/JCAI.2009.115
