摘要：AbstractThis work presents a probabilistic localization algorithm for the autonomous navigation system of a rail-guided robot, named DORIS, aimed at performing inspection and monitoring tasks in offshore facilities. A particle filter, which integrates odometry with inertial measurements, laser scans and image data, is used to estimate the robot localization on the rail. A novel technique, based on the recent history of events observed by the robot, is proposed to enhance the standard Monte Carlo localization algorithm, improving the robustness and convergence of the estimation and reducing its computational complexity. Simulations with experimental data acquired in field tests show that the proposed algorithm estimates the robot position with an absolute error smaller than 25cm (0.2% of the total rail length). The algorithm is able to deal with important localization issues of autonomous robots, which are the global localization and the kidnapped robot problems, proving to be better than odometry or a standard particle filter.
关键词：KeywordsLocalizationParticle FilterAutonomous Mobile RobotsRail-Guided Robots
