Competitor-aware Race Management for Electric Endurance Racing

TL;DR

This paper introduces a bi-level, competitor-aware race management framework for electric endurance racing, combining game-theoretic control and reinforcement learning to optimize energy use and race strategies.

Contribution

It presents a novel integration of game-theoretic optimal control with reinforcement learning for multi-agent race strategy optimization under aerodynamic and energy constraints.

Findings

Aerodynamic interactions significantly influence race outcomes.

Strategies prioritizing finishing position differ from minimum-time approaches.

The framework successfully manages energy and pit stops in a simulated race.

Abstract

Electric endurance racing is characterized by severe energy constraints and strong aerodynamic interactions. Determining race-winning policies therefore becomes a fundamentally multi-agent, game-theoretic problem. These policies must jointly govern low-level driver inputs as well as high-level strategic decisions, including energy management and charging. This paper proposes a bi-level framework for competitor-aware race management that combines game-theoretic optimal control with reinforcement learning. At the lower level, a multi-agent game-theoretic optimal control problem is solved to capture aerodynamic effects and asymmetric collision-avoidance constraints inspired by motorsport rules. Using this single-lap problem as the environment, reinforcement learning agents are trained to allocate battery energy and schedule pit stops over an entire race. The framework is demonstrated in a two-agent, 45-lap simulated race. The results show that effective exploitation of aerodynamic interactions is decisive for race outcome, with strategies that prioritize finishing position differing fundamentally from single-agent, minimum-time approaches.