Data-Driven Multi-Modal Learning Model Predictive Control

TL;DR

This paper introduces a data-driven LMPC approach for multi-modal systems with unknown modes, utilizing historical data to construct models and safe sets, demonstrated through automated driving simulations.

Contribution

It proposes a novel method for selecting local data and constructing ATV models for multi-modal LMPC using historical data.

Findings

Effective control policy derived from historical data

Successful application to automated driving on friction-varying tracks

Demonstrated improved safety and performance in simulations

Abstract

We present a Learning Model Predictive Controller (LMPC) for multi-modal systems performing iterative control tasks. Assuming availability of historical data, our goal is to design a data-driven control policy for the multi-modal system where the current mode is unknown. First, we propose a novel method to select local data for constructing affine time-varying (ATV) models of a multi-modal system in the context of LMPC. Then we present how to build a sampled safe set from multi-modal historical data. We demonstrate the effectiveness of our method through simulation results of automated driving on a friction-varying track.