In this paper, we propose a LiDAR-based robot localization method in a complex oil and gas environment. Localization is achieved in six Degrees of Freedom (DoF) thanks to a particle filter framework. A new time-efficient likelihood function, based on a pre-calculated 3D likelihood field, is introduced. Experiments are carried out in real environments and their digitized point clouds. Six DoF realtime localization is achieved with spatial and angular errors of less than 2.5cm and 1°respectively in a real environment of 350m 3 . The proposed approach focuses on real-time performance on embedded platforms. It enabled the Vikings team to win the first two ARGOS Challenge contests.