SLAM Hardware & Software optimization for mobile platform integration

Abstract: This thesis work will focus on the optimization of a state-of-the-art monocular Visual-Inertial Odometry (VIO) algorithm for real-time application with limited resources on an embedded system. We will be using a multi-processor unit equipped with a Digital Signal Processor (DSP) to accelerate and offload tasks from the CPU. The goal is to reduce resource consumption without damaging the algorithm performance in speed and accuracy. To this end, we will first identify OpenVINS [1] as a suitable algorithm for this work and find the functions to optimize. When comparing the version of the optimized algorithm with the DSP and its original version, we achieved a similar performance accuracy with more than x1.5 power consumption saving on the CPU and more than x2 memory saving. This work finds its importance in every embedded system which requires a vision-based localization system running along with other CPU heavy tasks.