Motion estimation hardware for autonomous vehicle guidance

The goal of this work is to extend the navigational capabilities of an existing autonomous vehicle so that it can reliably traverse a real-time dynamic environment. The primary facility such a vehicle requires is the ability to estimate the motion of objects in its environment. We show how a multisensor motion estimation system can be built to give real time results while fusing data from a number of sensor modalities in order to increase accuracy. Unlike other motion estimation systems, ours will be a compact, low power, single board solution appropriate for use in current autonomous vehicles.