Vehicle-to-Everything (V2X) communication promises improvements in road safety and efficiency by enabling low-latency and reliable communication services for vehicles. Besides using Mobile Broadband (MBB), there is a need to develop Ultra Reliable Low Latency Communications (URLLC) applications with cellular networks especially when safety-related driving applications are concerned. Future cellular networks are expected to support novel latencysensitive use cases. Many applications of V2X communication, like collaborative autonomous driving requires very low latency and high reliability in order to support real-time communication between vehicles and other network elements. In this paper, we classify V2X use-cases and their requirements in order to identify cellular network technologies able to support them. The bottleneck problem of the medium access in 4G Long Term Evolution(LTE) networks is random access procedure. It is evaluated through simulations to further detail the future limitations and requirements. Limitations and improvement possibilities for next generation of cellular networks are finally detailed. Moreover, the results presented in this paper provide the limits of different parameter sets with regard to the requirements of V2X-based applications. In doing this, a starting point to migrate to Narrowband IoT (NB-IoT) or 5G - solutions is given.

Obstacle avoidance and overtaking are important manoeuvres for autonomous driving. The collision avoidance with a vehicle, a pedestrian or any obstacle and the generation of a feasible continuous curvature trajectory represent the major problems faced by researchers to provide a safe path planning solution. This paper presents an algorithm able to avoid vehicles or obstacles by proposing a smooth local modified trajectory of a global path. The proposed method is based on the combination of a parameterized sigmoid function and a rolling horizon. The major advantage of this method is the reactivity to the obstacle motion and the generation of a smooth trajectory in a low execution time. The lateral and the longitudinal safety distances are easily parameterized when generating the avoidance trajectory. Simulation results show that the algorithm performs collision avoidance manoeuvres for static and dynamic obstacles in an effective way. The method is validated by applying the avoidance approach on real measured trajectory.

The location of objects is a growing research topic due, for instance, to the expansion of civil drones or intelligent vehicles. This expansion was made possible through the development of microelectromechanical systems (MEMS), inexpensive and miniaturized inertial sensors. In this context, this article describes the development of a new simulator which generates sensor measurements, giving a specific input trajectory. This will allow the comparison of pose estimation algorithms. To develop this simulator, the measurement equations of every type of sensor have to be analytically determined. To achieve this objective, classical kinematic equations are used for the more common sensors, i.e., accelerometers and rate gyroscopes. As nowadays, the MEMS inertial measurement units (IMUs) are generally magnetometer-augmented, an absolute world magnetic model is implemented. After the determination of the perfect measurement (through the error-free sensor models), realistic error models are developed to simulate real IMU behavior. Finally, the developed simulator is subjected to different validation tests.

This paper presents a deep learning approach to estimate a projectile trajectory in a GNSS-denied environment. For this purpose, Long-Short-Term-Memories (LSTMs) are trained on projectile fire simulations. The network inputs are the embedded Inertial Measurement Unit (IMU) data, the magnetic field reference, flight parameters specific to the projectile and a time vector. This paper focuses on the influence of LSTM input data pre-processing, i.e., normalization and navigation frame rotation, leading to rescale 3D projectile data over similar variation ranges. In addition, the effect of the sensor error model on the estimation accuracy is analyzed. LSTM estimates are compared to a classical Dead-Reckoning algorithm, and the estimation accuracy is evaluated via multiple error criteria and the position errors at the impact point. Results, presented for a finned projectile, clearly show the Artificial Intelligence (AI) contribution, especially for the projectile position and velocity estimations. Indeed, the LSTM estimation errors are reduced compared to a classical navigation algorithm as well as to GNSS-guided finned projectiles.