Keywords: Multi-Vehicle Systems, Control Systems and Technology, Advanced Driver Assistance Systems
Abstract: The paper proposes an adaptive cruise control method for connected and automated vehicles (CAVs) with safety considerations against cyber attacks. A high-level layer is responsible for the computation of energy optimal speed profiles for the CAVs, considering oncoming road information such as terrain characteristics and speed limits. Due to the computationally cumbersome optimization method of the speed profile design, this step is performed in a cloud. Next, a feasibility analysis is carried out on the vehicle layer regarding safety of the CAVs, overwriting high-level speed references in case of a collision risk is detected. The aim of the present paper is to validate the above multi-layer control method with the design of an intelligent cyber attack using reinforcement learning techniques. Evaluating a multi-agent training with real data velocity profiles, each automated vehicle has been simulated to be attacked by an agent aiming to generate collisions in the vehicle string.

Keywords: Communication Control Application and Systems, Multi-Vehicle Systems, Vehicle to Vehicle Communication
Abstract: Connected autonomous vehicles (CAVs) can share raw data directly about traffic, and road conditions to support real-time decision-making. Despite the potential for optimizing the flow of traffic, data sharing also raises privacy concerns as the location and timeliness of the reported events might reveal the routes of the vehicles. Therefore, a vehicle shall be careful when sharing even a part of its measurement data. In this paper, several data selection methods are proposed to decide how much data to share. The selection methods are also evaluated in terms of the utility and privacy sensitivity of the shared data.

Simulations based on a Markov chain model indicate that a greedy method may provide the most information while it does not reveal more than other feasible approaches.

Keywords: Intelligent Transportation Systems, Intelligent Control, Traffic Control
Abstract: This paper proposes a novel driving strategy for Connected and Automated Vehicles (CAVs) in a lane-free traffic environment. To this end, a combination of artificial forces and a reinforcement learning approach are used. To ensure the safe driving behavior of vehicles, an artificial ellipsoid border is assumed around each vehicle by which the lateral and longitudinal forces are obtained and applied. Furthermore, a longitudinal repulsive force based on a Deep Deterministic Policy Gradient (DDPG) network is exerted on the vehicles to avoid longitudinal collisions. Using this approach, the reaction of vehicles is improved, and vehicles may experience closer longitudinal space gaps allowing higher network throughput. The proposed lane-free driving methodology is implemented in the SUMO traffic simulator to showcase its benefits. Additionally, by implementing typical lane-based scenarios in SUMO with the same road condition and traffic demand as lane-free scenarios, a comparison in terms of average speed and time delay has been drawn between the proposed innovative approach and its conventional counterpart, proving the developed approach’s functionality.

Keywords: Controller Design, Traffic Control, Multi-Vehicle Systems
Abstract: This paper presents an approach for designing correct-by-construction Autonomous Intersection Management (AIM) algorithms for autonomous vehicles using formal methods. The task of the AIM is to establish the right-of-way (priorities) for the incoming autonomous vehicles. Based on the assumption that the vehicles communicate their planned paths, namely the entering and the exiting points of the intersection, e.g., over V2I protocol, the AIM makes sure that the trajectories of the incoming vehicles do not overlap. We argue that traffic efficiency and flow can be increased with an intelligent algorithm; however, the safety of this algorithm should be verified formally and then tested in a simulation environment. In this paper, we use formal methods for synthesizing a control protocol with safety guarantees. The intersection and the incoming vehicles are modeled as transition systems; their composition constitutes the overall concurrent system. The control protocol is synthesized using a set of specifications (safety properties) written in Linear Temporal Logic (LTL). These LTL specifications are then converted to Büchi automata, and the product automaton with the concurrent system results in a new transition system verified by model-checking. Formal verification is complemented by simulation-based tests conducted in MOBATSim (Model-based Autonomous Traffic Simulation Framework). This approach increases the validation envelope for the correct behavior of the system and the validity of the assumptions made for modeling. The synthesis algorithms developed for MATLAB implementation are also published as an open-source library with documentation and case studies.

Keywords: Centralized Control, Obstacle Detection and Avoidance, Path Planning
Abstract: Unlike conventional cars, connected and autonomous vehicles (CAVs) can cross intersections in a lane-free order and utilise the whole area of intersections. This paper presents a minimum-time optimal control problem to centrally control the CAVs to simultaneously cross an intersection in the shortest possible time. Dual problem theory is employed to convexify the constraints of CAVs to avoid collision with each other and with road boundaries. The developed formulation is smooth and solvable by gradient-based algorithms. Simulation results show that the proposed strategy reduces the crossing time of intersections by an average of 52% and 54% as compared to, respectively, the state-of-the-art reservation-based and lane-free methods. Furthermore, the crossing time by the proposed strategy is fixed to a constant value for an intersection regardless of the number of CAVs.