AIM5LA: A Latency-Aware Deep Reinforcement Learning-Based Autonomous Intersection Management System for 5G Communication Networks

Intersections are a major source of traffic delays and accidents within modern transportation systems. Compared to signalized intersection management, autonomous intersection management (AIM) coordinates the intersection crossing at an individual vehicle level, which provides additional flexibility. AIM can potentially eliminate stopping in intersection crossings due to traffic lights while maintaining a safe separation among conflicting movements. In this article, the state-of-the-art AIM research among various disciplines (e.g., traffic engineering and control engineering) is surveyed from the perspective of three hierarchical layers: corridor coordination layer, intersection management layer, and vehicle control layer. The key aspects of AIM designs are discussed in detail, including conflict detection schemes, priority rules, control centralization, computation complexity, and so on. Potential improvements for AIM evaluation with the emphasis on realistic scenarios are provided. This article serves as a comprehensive review of AIM design and provides promising directions for future research.

Intersections are at the core of congestion in urban areas. After the end of the Second World War, the problem of intersection management has benefited from a growing body of advances to address the optimization of the traffic lights' phase splits, timing, and offset. These contributions have significantly improved traffic safety and efficiency in urban areas. However, with the growth of transportation demand and motorization, traffic lights show their limits. At the end of the 1990s, the perspective of autonomous and connected driving systems motivated researchers to introduce a paradigm shift for controlling intersections. This new paradigm is well known today as autonomous intersection management (AIM). It harnesses the self-organization ability of future vehicles to provide more accurate control approaches that use the smallest available time window to reach unprecedented traffic performances. This is achieved by optimizing two main points of the interaction of connected and autonomous vehicles at intersections: the motion control of vehicles and the schedule of their accesses. Considering the great potential of AIM and the complexity of the problem, the proposed approaches are very different, starting from various assumptions. With the increasing popularity of AIM, this paper provides readers with a comprehensive vision of noticeable advances toward enhancing traffic efficiency. It shows that it is possible to tailor vehicles' speed and schedule according to the traffic demand by using distributed particle swarm optimization. Moreover, it brings the most relevant contributions in the light of traffic engineering, where flow-speed diagrams are used to measure the impact of the proposed optimizations. Finally, this paper presents the current challenging issues to be addressed.

Fail-safe Priority-based Approach for Autonomous Intersection Management

Advances in autonomous vehicles and intelligent transportation systems indicate a rapidly approaching future in which intelligent vehicles will automatically handle the process of driving. However, increasing the efficiency of today's transportation infrastructure will require intelligent traffic control mechanisms that work hand in hand with intelligent vehicles. To this end, Dresner and Stone proposed a new intersection control mechanism called Autonomous Intersection Management (AIM) and showed in simulation that by studying the problem from a multiagent perspective, intersection control can be made more efficient than existing control mechanisms such as traffic signals and stop signs. We extend their study beyond the case of an individual intersection and examine the unique implications and abilities afforded by using AIM-based agents to control a network of interconnected intersections. We examine different navigation policies by which autonomous vehicles can dynamically alter their planned paths, observe an instance of Braess' paradox, and explore the new possibility of dynamically reversing the flow of traffic along lanes in response to minute-by-minute traffic conditions. Studying this multiagent system in simulation, we quantify the substantial improvements in efficiency imparted by these agent-based traffic control methods.

Autonomous Intersection Management (AIM) controllers develop a distributed cooperative control logic to determine conflict-free trajectories for Connected Autonomous Vehicles (CAVs) in signal-free intersections. The work in this paper aims to allow AIM systems to work within narrow margins of error resulting in increased traffic throughput and reducing traffic congestion. The cooperative trajectory planning problem is formulated as vehicle-level mixed-integer non-linear programs that aim to minimize travel time of each vehicle and their speed variations while avoiding near-crash conditions. This paper implements and tests various dynamic velocity control strategies for vehicles within an intersection. Moreover, Model Predictive Controller (MPC), Fuzzy Logic and Proportional-Integral-Differential (PID) controllers were used and compared in terms of controller effort and velocity tracking. A Comparison is formulated based on different control parameters i.e., time response characteristics and control effort. The simulations have been implemented using unreal engine and RoadRunner. The simulation results have shown an acceptable performance for all controllers under test with varying features that has been discussed throughout this study.

The vehicle platoon controller to be presented here plays an important part in the latest generation of the decentralised, autonomous intersection management. It is the executing instance in the intersection management and combines the results from different optimisations done by the vehicles on their way into the intersection in order to ensure optimum crossing of the intersection. To do so it must not only be platoon-stable but also have an enlarged functionality in comparison to a conventional platoon controller. In the following we present all relevant aspects for the design of the platoon controller and its use in simulations of the intersection management.

The deployment of Cooperative Intelligent Transportation Systems (C-ITS) raises the question of future traffic management systems, which will be operating with an increasing amount of information and control over the infrastructure and the vehicles. This topic of research shares some similarities with robot coordination problems, inspiring our research on autonomous intersection management. In this article, we use a mixed-integer linear programming formulation for time-optimal robots coordination along specified paths and apply it to intersection management for autonomous vehicles. Our formulation allows to simultaneously solve a discrete optimal vehicle ordering problem, and a (discretized) continuous optimal velocity planning problem taking into account kinodynamics constraints. This allows faster pruning of the decision tree for the discrete problem, thus reducing computation time. A possible application for ITS is to evaluate the efficiency loss from a given vehicle ordering policy, or dynamically adapt policies to improve their efficiency. Moreover, any intermediary solution found by the solver can be used as a heuristically good policy, with proved bounds on sub-optimality.

Autonomous Intersection Management (AIM) is of high importance to avoid traffic jams. Intelligent Vehicles (IVs) and cooperative navigation have received recently much attention in this context. More importantly, the local motion planning approaches for IVs may become impracticable due to traffic disturbances. To face this problem, this paper presents a two-layer Decision-Making and Motion Planning (DMMP) framework to perform trajectory-based IVs hierarchical control in multiple intersections. It includes a microscopic car-following model while taking into account the decisions made by the intersection management layer. This layer is ensured via a local supervisor that detects the vehicle flow rate of traffic downstream. Accordingly, the “road-weight” of each lane is designated to alleviate the traffic congestion. Simultaneously, an aggregated velocity is assigned for approaching IVs in the low-level motion planner layer. Hence, lane's priorities are specified by the local supervisor based on a predefined strategy to manage the distributed IVs system. The Probability Collectives (PC) algorithm is also adopted to ensure an optimal collision-free trajectory regarding the aggregated velocity. Simulations including two adjacent unsignalized intersections are presented to validate the DMMP coordination framework. The overall navigation performances and the traffic flow density are remarkably improved by the supervised AIM.

This paper focuses on Cooperative Adaptive Cruise Control (CACC) in autonomous vehicles. In CACC, vehicles regulate their speed according to a preceding “leader” vehicle in the lane, forming a platoon. In a benign environment, CACC reduces fuel consumption, maximizes road capacity, and ensures traffic safety. However, CACC is vulnerable to various security threats. In this paper, we consider one of the critical threats, where the platoon leader is compromised, and forges acceleration information sent to platoon members. Such attack would lead to traffic instability and potential collisions. First, we propose information sharing in CACC model to allow vehicles and fixed infrastructure to sense and share information about platoon leaders, hence improves the reliability and supports the detection of anomalous behavior. Then, we propose a real-time anomaly detection mechanism that combines statistical learning with the physics laws of kinematics. Specifically, we propose Generalized Extreme Studentized Deviate with Sliding Chunks (GESD-SC) approach, which is applied at each vehicle in the platoon to detect anomalies in real-time based on the vehicle's own speeding decisions. Kinematic model is also utilized to detect unexpected deviations using the leader's information, communicated directly and observed by the leader's neighboring vehicle(s) and/or supporting infrastructure. Combining kinematic model with GESD-SC has shown to be effective in detecting falsification attacks in CACC. Furthermore, we analyze the time performance, and show that the proposed technique outperforms existing method in detection accuracy and processing time.

Current research on autonomous intersection management makes a set of assumptions including active Vehicle-to-Vehicle (V2V) or Vehicle-to-Infrastructure (V2I) communications, and/or centralized control. While they enhance the efficiency of the solution, such assumptions have inherent security and privacy drawbacks and require high infrastructure costs. This paper sets to investigate an alternative solution to autonomous intersection management that is decentralized (no centralized controller) and passive (no vehicle communications). The authors’ scheme permits autonomous vehicles approaching an intersection to make localized collision-free access decisions based purely on sensing and beacon information. Besides demonstrating the feasibility of a fully autonomous and decentralized approach, the authors show that this scheme operationally outperforms a standard actuated signal and all-way stop control. The decentralized approach trades off optimality for low cost, and enhanced security, privacy, and practicality..

Connected autonomous vehicles can significantly improve the safety and mobility of urban transportation systems. However, these systems are vulnerable to model uncertainties, wireless communication impairments, and external disturbances. In this article, we propose a new autonomous intersection management (AIM) system, called hierarchical model predictive control (HMPC). In HMPC, the intersection coordination unit (ICU) in a global centralized layer is responsible for assigning a safe speed to each vehicle while minimizing the system's cost. In the Local decentralized layer, each vehicle is responsible for tracking the reference speed assigned by the ICU, while avoiding collisions. In our method, each vehicle can use its own sensors to monitor its close surroundings, and take its own decisions on its movements, independent on the control decisions sent from the ICU. We investigate the safety, scalability and robustness of HMPC compared with two well-known AIM methods based on centralized and decentralized control strategies. For the evaluation, we use simulation of urban mobility (SUMO). Further, we study the scalability and performance of the algorithms in the presence of communication impairments associated with wireless channels. Our simulation results show that HMPC can safely handle high traffic flow rates. Also, HMPC is robust to uncertainties caused by the wireless communication.

Autonomous Intersection Management (AIM) is a typical problem in the field of Intelligent Transportation Systems (ITS), and has attracted much attention in both academia and industry in recent decades. With the development of vehicular networks, it becomes more and more possible to coordinate more effectively the traveling behaviors of vehicles approaching intersections by the deployment of novel Autonomous Intersection Controllers (AIC). Taking into consideration various traveling requirements of different types of vehicles (such as ambulances, shuttle buses, and taxis), a novel Service-oriented Cloud-cooperative AIC (SoC-AIC) is studied and designed for the application scene of future ITS, i.e. Service-oriented Cooperative ITS (SoC-ITS). In this study, vehicular behaviors and reservation-based passing-through procedures are analyzed firstly. After mapping service properties of vehicles to vehicular priorities, a service quality oriented scheduling mechanism is proposed, which can guaranttee emergency vehicles to pass through preferentially via priority-based policies. Finally, all these designs are implemented within a new AIC controller, and verified via a hardware-in-the-loop environment where a traffic simulator is also included.

An accurate cooperative positioning system for vehicular safety applications

The rapid growth of connected medical devices generates massive volumes of heterogeneous health data that must be processed and transmitted in real time. In such environments, minimizing latency and energy consumption remains a critical challenge for next-generation health monitoring systems. Existing reinforcement learning and optimization methods for intelligent communication networks face several challenges, including slow convergence, high computational overhead, and inefficiency in handling task prioritization. To resolve these issues, this work develops a chaotic dung beetle optimization-boosted multi-agent deep reinforcement learning that jointly optimizes communication reliability, computational efficiency, and task prioritization. A reward function is designed to jointly minimize delay, energy usage, and system cost while preserving information freshness. Specifically, the dung beetle optimization process is combined with a piecewise linear chaotic map to enhance population diversity, which significantly improves search space exploration and leads to faster convergence and higher solution quality. The proposed algorithm enhances the exploration capability of multi-agent deep reinforcement learning through the integration of chaotic dung beetle optimization, enabling more accurate and reliable decision-making in real-world applications. Extensive experiments demonstrate that the proposed chaotic dung beetle optimization-boosted multi-agent deep reinforcement learning model achieves superior performance compared to baseline algorithms. Specifically, it reaches an accuracy of over 97.00% with rapid convergence, reduces system cost under varying health data sizes and Medical Internet of Things devices, and maintains robust scalability across diverse workloads. Moreover, the model achieves significant reductions in communication latency and energy consumption as central processing unit cycles and bandwidth increase, while effectively prioritizing high-criticality tasks.

The development of autonomous vehicle or self-driving car integrates with the wireless communication technology which would be a forward step for road transportation in the near future. The autonomous crossing of an intersection with an autonomous vehicle will play a crucial role in the future of intelligent transportation system (ITS). The fundamental objectives of this work are to manage autonomous vehicles crossing an intersection with no collisions, maintaining that a vehicle drives continuously, and to decrease the waiting time at an intersection. In this paper, a discrete model of the one-way single intersection is designed. The vehicle-to-infrastructure (V2I) communication is implemented to exchange information between a vehicle and an intersection manager which is the roadside infrastructure. The safe trajectory of autonomous vehicles for the autonomous intersection management is determined and presented by using discrete mathematics.