SIMD and OpenMP optimization of EKF-SLAM

Abstract

SLAM algorithms are widely used by autonomous robots operating in unknown environments. Several works have presented optimizations mainly focused on the algorithm complexity. New computing technologies (SIMD coprocessors, multicore architecture) can greatly accelerate the processing time but require rethinking the algorithm implementation. This paper presents an efficient implementation of the EKF-SLAM algorithm on an embedded system implementing OMAP multi-core architecture and SIMD optimizations. The aim is to optimize the algorithm implementation to improve the localization quality. Results demonstrate that an optimized implementation is always needed to achieve efficient performances and can help to design embedded systems implementing a low-cost multi-core architecture operating under real time constraints.