Towards Safe and Robust Autonomous Vehicle Platooning: A Self-Organizing Cooperative Control Framework

TL;DR

This framework integrates deep reinforcement learning (DRL) with model-driven approaches, enabling dynamic formation dissolution and reconfiguration through a safety-prioritized twin-world deduction mechanism, thereby optimizing decision-making ability and adaptability.

Abstract

In hybrid traffic environments where human-driven vehicles (HDVs) and autonomous vehicles (AVs) coexist, achieving safe and robust decision-making for AV platooning remains a complex challenge. Existing platooning systems often struggle with dynamic formation management and adaptability, especially in unpredictable, mixed-traffic conditions. To enhance autonomous vehicle platooning within these hybrid environments, this paper presents TriCoD, a twin-world safety-enhanced Data-Model-Knowledge Triple-Driven Cooperative Decision-making Framework. This framework integrates deep reinforcement learning (DRL) with model-driven approaches, enabling dynamic formation dissolution and reconfiguration through a safety-prioritized twin-world deduction mechanism. The DRL component augments traditional model-driven methods, enhancing both safety and operational efficiency, especially under emergency conditions. Additionally, an adaptive switching mechanism allows the system to seamlessly shift between data-driven and model-driven strategies based on real-time traffic demands, thereby optimizing decision-making ability and adaptability. Simulation experiments and hardware-in-the-loop tests demonstrate that the proposed framework significantly improves safety, robustness, and flexibility. A detailed account of the validation results for the model can be found in \href{https://perfectxu88.github.io/towardssafeandrobust.github.io/}{Our Website}.

Figures (10)

• Figure 1: Illustration of challenging traffic conditions and our framework's adaptive responses: formation maintenance, dissolution, and reorganization.CAVs (red) and HDVs (green) are represented with corresponding behaviors under each scenario.
• Figure 2: Illustration of the system and the simulation setup. All high-level actions are verified through a security mask before being processed by the bottom-level controller, which will be finally converted into control signals.
• Figure 3: Overview of the TriCoD framework for self-organizing autonomous vehicle platooning, which combines a data-driven upper layer and a model-driven lower layer to manage platoon adaptively. The upper layer uses DRL with a twin-world safety verification model for safe, real-time decision-making, while the lower layer employs a LQR for precise control in predictable conditions, ensuring stable and efficient vehicle spacing. Together, these layers provide robust, adaptive platooning in complex traffic environments.
• Figure 4: Illustration of the designed headway maintaining reward, which considers both the single-vehicle rewards and the multi-vehicle rewards.
• Figure 5: Illustration of the TRPO-based formation configuration algorithm schematic model.