Learning Model Predictive Control for Competitive Autonomous Racing

TL;DR

This paper develops a learning model predictive control approach enabling multiple autonomous agents to race competitively in real-time, addressing exploration and obstacle avoidance limitations of previous single-agent methods.

Contribution

It introduces a multi-agent LMPC that explores the state space more effectively and maintains convexity in obstacle avoidance, improving racing performance.

Findings

Enhanced exploration of the state space for overtaking.

Convex safe set for obstacle avoidance.

Real-time multi-agent racing demonstrated.

Abstract

The goal of this thesis is to design a learning model predictive controller (LMPC) that allows multiple agents to race competitively on a predefined race track in real-time. This thesis addresses two major shortcomings in the already existing single-agent formulation. Previously, the agent determines a locally optimal trajectory but does not explore the state space, which may be necessary for overtaking maneuvers. Additionally, obstacle avoidance for LMPC has been achieved in the past by using a non-convex terminal set, which increases the complexity for determining a solution to the optimization problem. The proposed algorithm for multi-agent racing explores the state space by executing the LMPC for multiple different initializations, which yields a richer terminal safe set. Furthermore, a new method for selecting states in the terminal set is developed, which keeps the convexity for the terminal safe set and allows for taking suboptimal states.