Continual Adaptation for Autonomous Driving with the Mixture of Progressive Experts Network

TL;DR

This paper introduces the Mixture of Progressive Experts network, a continual learning framework for autonomous driving that dynamically adapts to evolving environments by selectively activating expert models, improving performance in complex urban scenarios.

Contribution

The paper proposes the MoPE network, a novel continual learning approach that combines reinforcement and supervised learning to enhance autonomous driving adaptability.

Findings

MoPE outperforms behavior cloning by up to 7.8% in urban environments.

The framework enables dynamic task-specific expert activation.

Progressive refinement improves adaptation to new driving scenarios.

Abstract

Learning-based autonomous driving requires continuous integration of diverse knowledge in complex traffic , yet existing methods exhibit significant limitations in adaptive capabilities. Addressing this gap demands autonomous driving systems that enable continual adaptation through dynamic adjustments to evolving environmental interactions. This underscores the necessity for enhanced continual learning capabilities to improve system adaptability. To address these challenges, the paper introduces a dynamic progressive optimization framework that facilitates adaptation to variations in dynamic environments, achieved by integrating reinforcement learning and supervised learning for data aggregation. Building on this framework, we propose the Mixture of Progressive Experts (MoPE) network. The proposed method selectively activates multiple expert models based on the distinct characteristics of each task and progressively refines the network architecture to facilitate adaptation to new tasks. Simulation results show that the MoPE model outperforms behavior cloning methods, achieving up to a 7.8% performance improvement in intricate urban road environments.