Browsing by Keyword "Autonomous driving"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
Item A Control Testing Framework for automated driving functionalities using modular architecture with ROS/CARLA environment(Institute of Electrical and Electronics Engineers Inc., 2021) Arizala, Asier; Lattarulo, Ray; Zubizarreta, Asier; Perez, Joshue; Ferariu, Lavinia; Matcovschi, Mihaela-Hanako; Ungureanu, Florina; CCAMInterest in Automated Vehicles (AV) has increased in the last years due to the need of providing more efficient and safe transportation systems. However, the development of AV functionalities is a complex task, as multiple technologies have to be tested and integrated to fulfill the required automation level. Moreover, the number of different scenarios that have to be dealt with Cooperative and Connected Automated Mobility (CCAM) solutions makes traditional track testing a non-optimal approach. Due to this, in recent years interest in the development of simulation-based testing frameworks has arisen, with open-source and commercial solutions trying to fulfill the requirements of AV development. This work introduces an automated vehicle testing framework that combines the widely used open-source simulation environment CARLA with a self-developed modular control framework AUDRIC. The communication between both is made using the ROS environment. The proposed approach provides the advantages of both environments in terms of flexibility and modularity, allowing the development of automated functionalities for the different modules of AV architecture. The validity of the approach is demonstrated by presenting two use cases: a lane following application and an obstacle avoidance scenario.Item An Efficient and Scalable Simulation Model for Autonomous Vehicles with Economical Hardware(2021-03) Sajjad, Muhammad; Irfan, Muhammad; Muhammad, Khan; Ser, Javier Del; Sanchez-Medina, Javier; Andreev, Sergey; Ding, Weiping; Lee, Jong Weon; IAAutonomous vehicles rely on sophisticated hardware and software technologies for acquiring holistic awareness of their immediate surroundings. Deep learning methods have effectively equipped modern self-driving cars with high levels of such awareness. However, their application requires high-end computational hardware, which makes utilization infeasible for the legacy vehicles that constitute most of today's automotive industry. Hence, it becomes inherently challenging to achieve high performance while at the same time maintaining adequate computational complexity. In this paper, a monocular vision and scalar sensor-based model car is designed and implemented to accomplish autonomous driving on a specified track by employing a lightweight deep learning model. It can identify various traffic signs based on a vision sensor as well as avoid obstacles by using an ultrasonic sensor. The developed car utilizes a single Raspberry Pi as its computational unit. In addition, our work investigates the behavior of economical hardware used to deploy deep learning models. In particular, we herein propose a novel, computationally efficient, and cost-effective approach. The designed system can serve as a platform to facilitate the development of economical technologies for autonomous vehicles that can be used as part of intelligent transportation or advanced driver assistance systems. The experimental results indicate that this model can achieve real-time response on a resource-constrained device without significant overheads, thus making it a suitable candidate for autonomous driving in current intelligent transportation systems.Item Safe adaptation for reliable and energy-efficient E/E architectures(Springer Verlag, 2018) Weiss, Gereon; Schleiss, Philipp; Drabek, Christian; Ruiz, Alejandra; Radermacher, Ansgar; QuantumThe upcoming changing mobility paradigms request more and more services and features to be included in future cars. Electric mobility and highly automated driving lead to new requirements and demands on vehicle information and communication (ICT) architectures. For example, in the case of highly-automated driving, future drivers no longer need to monitor and control the vehicle all the time. This calls for new fault-tolerant approaches of automotive E/E architectures. In addition, the electrification of vehicles requires a flexible underlying E/E architecture which facilitates enhanced energy management. Within the EU-funded SafeAdapt project, a new E/E architecture for future vehicles has been developed in which adaptive systems ensure safe, reliable, and cost-effective mobility. The holistic approach provides the necessary foundation for future in-vehicle systems and its evaluation shows the great potential of such reliable and energy-efficient E/E architectures.Item Trajectory planning for automated buses in parking areas(Institute of Electrical and Electronics Engineers Inc., 2021) Martin, Asier; Lattarulo, Ray; Zubizarreta, Asier; Perez, Joshue; Lopez-Garcia, Pedro; Ferariu, Lavinia; Matcovschi, Mihaela-Hanako; Ungureanu, Florina; Tecnalia Research & InnovationAutomated Vehicles (AVs) are complex, and they require solutions in different areas such as perception, communications, decision, and control. In urban environments, path planning for parking maneuvers is a relevant feature. There is a good amount of research on this topic considering passenger cars. However, there are some gaps considering automated buses. This work proposes a path planning approach for parking an automated bus that targets the fewer possible trajectories to complete the parking maneuver. The algorithm considers the vehicle geometry, its kinematics, and the blockage or availability of the surrounding parking spaces, to create a set of trajectories to complete the parking maneuver. The approach was tested in simulation environments considering an electric Gulliver minibus in the framework of the European project SHOW.Item Vision-Based Semantic Segmentation in Scene Understanding for Autonomous Driving: Recent Achievements, Challenges, and Outlooks(2022-12-01) Muhammad, Khan; Hussain, Tanveer; Ullah, Hayat; Ser, Javier Del; Rezaei, Mahdi; Kumar, Neeraj; Hijji, Mohammad; Bellavista, Paolo; De Albuquerque, Victor Hugo C.; IAScene understanding plays a crucial role in autonomous driving by utilizing sensory data for contextual information extraction and decision making. Beyond modeling advances, the enabler for vehicles to become aware of their surroundings is the availability of visual sensory data, which expand the vehicular perception and realizes vehicular contextual awareness in real-world environments. Research directions for scene understanding pursued by related studies include person/vehicle detection and segmentation, their transition analysis, lane change, and turns detection, among many others. Unfortunately, these tasks seem insufficient to completely develop fully-autonomous vehicles i.e., achieving level-5 autonomy, travelling just like human-controlled cars. This latter statement is among the conclusions drawn from this review paper: scene understanding for autonomous driving cars using vision sensors still requires significant improvements. With this motivation, this survey defines, analyzes, and reviews the current achievements of the scene understanding research area that mostly rely on computationally complex deep learning models. Furthermore, it covers the generic scene understanding pipeline, investigates the performance reported by the state-of-the-art, informs about the time complexity analysis of avant garde modeling choices, and highlights major triumphs and noted limitations encountered by current research efforts. The survey also includes a comprehensive discussion on the available datasets, and the challenges that, even if lately confronted by researchers, still remain open to date. Finally, our work outlines future research directions to welcome researchers and practitioners to this exciting domain.