Hierarchical Control for Head-to-Head Autonomous Racing

TL;DR

This paper introduces a hierarchical control framework for autonomous head-to-head racing, combining high-level game planning with low-level control strategies, including reinforcement learning and Nash game approaches, to outperform baselines in race success and rule adherence.

Contribution

The paper presents a novel hierarchical control architecture that integrates game-theoretic planning with reinforcement learning and Nash equilibrium methods for autonomous racing.

Findings

Hierarchical controllers outperform baselines in race wins and rule compliance.

MARL-based low-level control achieves over 90% win rate in head-to-head races.

Controllers mimic expert human driving behaviors like overtaking and blocking.

Abstract

We develop a hierarchical controller for head-to-head autonomous racing. We first introduce a formulation of a racing game with realistic safety and fairness rules. A high-level planner approximates the original formulation as a discrete game with simplified state, control, and dynamics to easily encode the complex safety and fairness rules and calculates a series of target waypoints. The low-level controller takes the resulting waypoints as a reference trajectory and computes high-resolution control inputs by solving an alternative formulation approximation with simplified objectives and constraints. We consider two approaches for the low-level planner, constructing two hierarchical controllers. One approach uses multi-agent reinforcement learning (MARL), and the other solves a linear-quadratic Nash game (LQNG) to produce control inputs. The controllers are compared against three baselines: an end-to-end MARL controller, a MARL controller tracking a fixed racing line, and an LQNG controller tracking a fixed racing line. Quantitative results show that the proposed hierarchical methods outperform their respective baseline methods in terms of head-to-head race wins and abiding by the rules. The hierarchical controller using MARL for low-level control consistently outperformed all other methods by winning over 90% of head-to-head races and more consistently adhered to the complex racing rules. Qualitatively, we observe the proposed controllers mimicking actions performed by expert human drivers such as shielding/blocking, overtaking, and long-term planning for delayed advantages. We show that hierarchical planning for game-theoretic reasoning produces competitive behavior even when challenged with complex rules and constraints.