New Algorithm Shrinks AI Control System Memory by 90 Percent
Researchers have developed a technique that dramatically reduces the computer memory needed to run a widespread type of AI control system used in robotics, autonomous vehicles, and industrial automation. The method exploits mathematical shortcuts to cut storage requirements by up to tenfold, potentially enabling these systems to run on cheaper, smaller devices.
Originaltitel: Reduced Memory Footprint in Multiparametric Quadratic Programming by Exploiting Low Rank Structure
<p>In multiparametric programming an optimization problem which is dependent on a parameter vector is solved parametrically. In control, multiparametric quadratic programming (mp-QP) problems have become increasingly important since the optimization problem arising in Model Predictive Control (MPC) can be cast as an mp-QP problem, which is referred to as explicit MPC. One of the main limitations with mp-QP and explicit MPC is the amount of memory required to store the parametric solution and the critical regions. In this paper, a method for exploiting low rank structure in the parametric solution of an mp-QP problem in order to reduce the required memory is introduced. The method is based on ideas similar to what is done to exploit low rank modifications in generic QP solvers, but is here applied to mp-QP problems to save memory. The proposed method has been evaluated experimentally, and for some examples of relevant problems the relative memory reduction is an order of magnitude compared to storing the full parametric solution and critical regions.</p>