Multi-Objective Reinforcement Learning for Adaptable Personalized Autonomous Driving

TL;DR

This paper introduces a multi-objective reinforcement learning approach for autonomous driving that dynamically adapts to individual user preferences in real-time without retraining, improving user satisfaction and safety.

Contribution

It presents a novel preference-driven MORL method enabling real-time adaptation of autonomous driving behavior along multiple style objectives without policy retraining.

Findings

The agent successfully adapts to changing preferences in urban scenarios.

Maintains safety and efficiency while adjusting driving style.

Operates effectively in complex mixed-traffic environments.

Abstract

Human drivers exhibit individual preferences regarding driving style. Adapting autonomous vehicles to these preferences is essential for user trust and satisfaction. However, existing end-to-end driving approaches often rely on predefined driving styles or require continuous user feedback for adaptation, limiting their ability to support dynamic, context-dependent preferences. We propose a novel approach using multi-objective reinforcement learning (MORL) with preference-driven optimization for end-to-end autonomous driving that enables runtime adaptation to driving style preferences. Preferences are encoded as continuous weight vectors to modulate behavior along interpretable style objectives$\unicode{x2013}$including efficiency, comfort, speed, and aggressiveness$\unicode{x2013}$without requiring policy retraining. Our single-policy agent integrates vision-based perception in complex mixed-traffic scenarios and is evaluated in diverse urban environments using the CARLA simulator. Experimental results demonstrate that the agent dynamically adapts its driving behavior according to changing preferences while maintaining performance in terms of collision avoidance and route completion.