A Cascaded Multi-Agent Reinforcement Learning-Based Resource Allocation for Cellular-V2X Vehicular Platooning Networks.

The platooning of cars and trucks is a pertinent approach for autonomous driving due to the effective utilization of roadways. The decreased gas consumption levels are an added merit owing to sustainability. Conventional platooning depended on Dedicated Short-Range Communication (DSRC)-based vehicle-to-vehicle communications. The computations were executed by the platoon members with their constrained capabilities. The advent of 5G has favored Intelligent Transportation Systems (ITS) to adopt Multi-access Edge Computing (MEC) in platooning paradigms by offloading the computational tasks to the edge server. In this research, vital parameters in vehicular platooning systems, viz. latency-sensitive radio resource management schemes, and Age of Information (AoI) are investigated. In addition, the delivery rates of Cooperative Awareness Messages (CAM) that ensure expeditious reception of safety-critical messages at the roadside units (RSU) are also examined. However, for latency-sensitive applications like vehicular networks, it is essential to address multiple and correlated objectives. To solve such objectives effectively and simultaneously, the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) framework necessitates a better and more sophisticated model to enhance its ability. In this paper, a novel Cascaded MADDPG framework, CMADDPG, is proposed to train cascaded target critics, which aims at achieving expected rewards through the collaborative conduct of agents. The estimation bias phenomenon, which hinders a system's overall performance, is vividly circumvented in this cascaded algorithm. Eventually, experimental analysis also demonstrates the potential of the proposed algorithm by evaluating the convergence factor, which stabilizes quickly with minimum distortions, and reliable CAM message dissemination with 99% probability. The average AoI quantity is maintained within the 5-10 ms range, guaranteeing better QoS. This technique has proven its robustness in decentralized resource allocation against channel uncertainties caused by higher mobility in the environment. Most importantly, the performance of the proposed algorithm remains unaffected by increasing platoon size and leading channel uncertainties.

Coalitional Distributed Model Predictive Control Strategy for Vehicle Platooning Applications.

This work aims at developing and testing a novel Coalitional Distributed Model Predictive Control (C-DMPC) strategy suitable for vehicle platooning applications. The stability of the algorithm is ensured via the terminal constraint region formulation, with robust positively invariant sets. To ensure a greater flexibility, in the initialization part of the method, an invariant table set is created containing several invariant sets computed for different constraints values. The algorithm was tested in simulation, using both homogeneous and heterogeneous initial conditions for a platoon with four homogeneous vehicles, using a predecessor-following, uni-directionally communication topology. The simulation results show that the coalitions between vehicles are formed in the beginning of the experiment, when the local feasibility of each vehicle is lost. These findings successfully prove the usefulness of the proposed coalitional DMPC method in a vehicle platooning application, and illustrate the robustness of the algorithm, when tested in different initial conditions.

PL-TOON: A Low-Cost Experimental Platform for Teaching and Research on Decentralized Cooperative Control.

In this paper, we present the development of a low-cost multi-agent system experimental platform for teaching, and research purposes. The platform consists of train-like autonomous agents equipped with local speed estimation, distance sensing to their nearest predecessor, and wireless communications with other agents and a central coordinator. The individual agents can be used for simple PID experiments in a classroom or laboratory setting, while a collection of agents are capable of performing decentralized platooning with cooperative adaptive cruise control in a variety of settings, the latter being the main goal of the platform. The agents are built from low cost components and programmed with open source software, enabling teaching experiences and experimental work with a larger number of agents that would otherwise be possible with other existing solutions. Additionally, we illustrate with experimental results some of the teaching activities that the platform is capable of performing.

Multi-Task End-to-End Self-Driving Architecture for CAV Platoons.

Connected and autonomous vehicles (CAVs) could reduce emissions, increase road safety, and enhance ride comfort. Multiple CAVs can form a CAV platoon with a close inter-vehicle distance, which can further improve energy efficiency, save space, and reduce travel time. To date, there have been few detailed studies of self-driving algorithms for CAV platoons in urban areas. In this paper, we therefore propose a self-driving architecture combining the sensing, planning, and control for CAV platoons in an end-to-end fashion. Our multi-task model can switch between two tasks to drive either the leading or following vehicle in the platoon. The architecture is based on an end-to-end deep learning approach and predicts the control commands, i.e., steering and throttle/brake, with a single neural network. The inputs for this network are images from a front-facing camera, enhanced by information transmitted via vehicle-to-vehicle (V2V) communication. The model is trained with data captured in a simulated urban environment with dynamic traffic. We compare our approach with different concepts used in the state-of-the-art end-to-end self-driving research, such as the implementation of recurrent neural networks or transfer learning. Experiments in the simulation were conducted to test the model in different urban environments. A CAV platoon consisting of two vehicles, each controlled by an instance of the network, completed on average 67% of the predefined point-to-point routes in the training environment and 40% in a never-seen-before environment. Using V2V communication, our approach eliminates casual confusion for the following vehicle, which is a known limitation of end-to-end self-driving.

Secure platooning control of automated vehicles under cyber attacks.

This paper studies the problem of secure control of automated vehicles in a platoon-based driving pattern over a vehicular ad-hoc network (VANET) subject to various cyber attacks. The platoon under consideration is a convoy of a leader vehicle whose control input is unknown to its following vehicles and some follower vehicles with uncertain heterogeneous engine time constants, bounded disturbance and noise. First, a local estimator is developed for each follower vehicle so as to construct some confidence ellipsoidal estimation region always enclosing vehicular true state regardless of uncertain heterogenous engine time constants, bounded disturbance and noise. A convex optimization algorithm is proposed to find some optimal ellipsoidal sets and recursively solve out gain matrices of the local estimators. Then, a scalable control protocol employing the state estimates from its local and underlying neighboring estimators is designed to accomplish secure platooning control. Under the derived design technique, the resulting closed-loop platooning tracking errors are proven to remain in the vicinity of zero. Comparative studies are conducted to validate the efficacy of the proposed control method on achieving the satisfactory platooning performance by handling different attack strategies.