Deep reinforcement learning based control for Autonomous Vehicles in CARLA

Nowadays, Artificial Intelligence (AI) is growing by leaps and bounds in almost all fields of technology, and Autonomous Vehicles (AV) research is one more of them. This paper proposes the using of algorithms based on Deep Learning (DL) in the control layer of an autonomous vehicle. More specifically, Deep Reinforcement Learning (DRL) algorithms such as Deep Q-Network (DQN) and Deep Deterministic Policy Gradient (DDPG) are implemented in order to compare results between them. The aim of this work is to obtain a trained model, applying a DRL algorithm, able of sending control commands to the vehicle to navigate properly and efficiently following a determined route. In addition, for each of the algorithms, several agents are presented as a solution, so that each of these agents uses different data sources to achieve the vehicle control commands. For this purpose, an open-source simulator such as CARLA is used, providing to the system with the ability to perform a multitude of tests without any risk into an hyper-realistic urban simulation environment, something that is unthinkable in the real world. The results obtained show that both DQN and DDPG reach the goal, but DDPG obtains a better performance. DDPG perfoms trajectories very similar to classic controller as LQR. In both cases RMSE is lower than 0.1m following trajectories with a range 180-700m. To conclude, some conclusions and future works are commented.

Gauss process regression for real-time ionospheric delay estimation from GNSS observations

The number of devices equipped with global satellite positioning has exceeded seven billion recently. There are a wide variety of receivers regarding their accuracy and reliability. Low cost, multi-frequency units have been released on the market latterly; however, the number of single-frequency receivers is still significant. Since their measurements are influenced by ionospheric delay, accurate ionosphere models are of utmost importance to reduce the effect. This paper summarizes how Gauss process regression (GPR) can be applied to derive near real-time regional ionosphere models using raw Global Navigation Satellite System (GNSS) observations of permanent stations. While Gauss process is widely used in machine learning, GPR is a nonparametric, Bayesian approach to regression. GPR has several benefits for ionosphere monitoring since it is quite robust and efficient to derive a grid model from data available in irregular set of ionospheric pierce points. The corresponding instrumental delays are estimated by a parallel Kalman filter. The presented algorithm can be applied near real-time, however the results are offline calculated and are compared to two high quality TEC map products. Based on the analysis, the accuracy of the GPR modell is in 2 TECu range. The developed methods could be efficiently applied in the field of autonomous vehicle navigation with meeting both accuracy and integrity requirements.

Evaluating the Impacts of Optimization Horizon on the Shared Autonomous Vehicle Reservation Request System

With the development of technology, shared autonomous vehicles may become one of the main traffic modes in the future. Especially, shared autonomous vehicle reservation system, commuting, and other trips with fixed departure time mostly submit their travel requests in advance. Therefore, it is important to reasonably match shared autonomous vehicles and reservation demands. In this paper, reservation requests are divided into short-term and long-term requests by inputting requests in a more realistic way. An integer linear programming model considering operator scheduling cost and system service level is established. A detailed scheme considering rolling horizon continuity and ridesharing is used to improve the dispatching result. Based on traffic data in Delft, the Netherlands, 164 scenarios are tested in which the parking cost, fuel cost, ridesharing effect, service level, and network size are analyzed. The results show that a better relocation and ridesharing matching scheme can be obtained when the rolling horizon is small, while the overall effect is better when the rolling horizon is large. Moreover, the buffer time, distance, and travel time limit for vehicle relocation should be selected according to the request quantity and the calculation time requirement. The result can provide a suggestion for the dispatching of shared autonomous vehicle reservation system with ridesharing.