CoMoCAVs: Cohesive Decision-Guided Motion Planning for Connected and Autonomous Vehicles with Multi-Policy Reinforcement Learning

TL;DR

This paper introduces CDGMP, a novel framework for connected autonomous vehicles that integrates decision-making and motion planning using a multi-policy reinforcement learning approach with a Mixture of Experts architecture, enhancing safety and adaptability.

Contribution

The paper presents a new cohesive framework combining decision-making and motion planning through a Mixture of Experts and multi-policy reinforcement learning, improving modularity and safety in autonomous driving.

Findings

Demonstrates reliable lane selection and trajectory control in simulations.

Enhances modularity and safety through specialized sub-networks.

Improves adaptability across diverse traffic scenarios.

Abstract

Autonomous driving demands reliable and efficient solutions to closely related problems such as decision-making and motion planning. In this work, decision-making refers specifically to highway lane selection, while motion planning involves generating control commands (such as speed and steering) to reach the chosen lane. In the context of Connected Autonomous Vehicles (CAVs), achieving both flexible and safe lane selection alongside precise trajectory execution remains a significant challenge. This paper proposes a framework called Cohesive Decision-Guided Motion Planning (CDGMP), which tightly integrates decision-making and motion planning using a Mixture of Experts (MoE) inspired architecture combined with multi-policy reinforcement learning. By coordinating multiple specialized sub-networks through a gating mechanism, the method decomposes the complex driving task into modular components. Each sub-network focuses on a specific aspect of driving, improving efficiency by activating only the most relevant modules during inference. This design also enhances safety through modular specialization. CDGMP improves the adaptability and robustness of CAVs across diverse traffic scenarios, offering a scalable solution to real-world autonomy challenges. The architectural principles behind CDGMP, especially the use of MoE, also provide a strong foundation for other high-dimensional decision and control tasks. Simulation results (available at https://youtu.be/_-4OXNHV0UY) demonstrate reliable performance in both lane selection and motion planning.