Drive-By-Wire Development Process Based on ROS for an Autonomous Electric Vehicle

Arango, J. Felipe; Bergasa, Luis M.; Revenga, P.; Barea, Rafael; López-Guillén, Elena; Gómez-Huélamo, Carlos; Araluce, Javier; Gutiérrez, Raquel Lázaro

doi:10.3390/s20216121

Cited by 15 publications

(7 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the near future, we plan to extend this research by obtaining the state vector from real sensor data instead of obtaining them directly from the ground truth. The main advantage of the proposed architecture is that it is ROS based, which allows a fast and easy integration in our real vehicle [ 43 ]. We have already conducted some experiments in a real environment on our university campus, using a Petri nets-based decision-making module.…”

Section: Discussionmentioning

confidence: 99%

Reinforcement Learning-Based Autonomous Driving at Intersections in CARLA Simulator

Gutiérrez-Moreno

Barea

López-Guillén

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Intersections are considered one of the most complex scenarios in a self-driving framework due to the uncertainty in the behaviors of surrounding vehicles and the different types of scenarios that can be found. To deal with this problem, we provide a Deep Reinforcement Learning approach for intersection handling, which is combined with Curriculum Learning to improve the training process. The state space is defined by two vectors, containing adversaries and ego vehicle information. We define a features extractor module and an actor–critic approach combined with Curriculum Learning techniques, adding complexity to the environment by increasing the number of vehicles. In order to address a complete autonomous driving system, a hybrid architecture is proposed. The operative level generates the driving commands, the strategy level defines the trajectory and the tactical level executes the high-level decisions. This high-level decision system is the main goal of this research. To address realistic experiments, we set up three scenarios: intersections with traffic lights, intersections with traffic signs and uncontrolled intersections. The results of this paper show that a Proximal Policy Optimization algorithm can infer ego vehicle-desired behavior for different intersection scenarios based only on the behavior of adversarial vehicles.

show abstract

Section: Discussionmentioning

confidence: 99%

Reinforcement Learning-Based Autonomous Driving at Intersections in CARLA Simulator

Gutiérrez-Moreno

Barea

López-Guillén

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…The first by-wire system to be integrated into a commercial car was the throttle-by-wire or electronic throttle control (ETC), which appeared in the 1988 BMW 7 Series [ 12 ]. Since then, the use of the electronic throttle has become widespread, and the traditional throttle, operated by a Bowden cable, is now practically considered obsolete [ 1 ]. This system uses sensors to measure pedal travel; the electronic control unit (ECU) receives the data, which manage the required fuel and optimal air intake, sending commands to actuators.…”

Section: State Of the Artmentioning

confidence: 99%

“…Drive-by-wire is an automotive technology that uses electrical or electro-mechanical systems to perform vehicle functions, avoiding mechanical linkages. New trends in the automotive industry are accelerating the adoption of X-by-wire technology, such as electrification and the use of autonomous vehicles [ 1 , 2 ]. This approach offers several advantages, including minimizing the number of mechanical parts and connections, reducing the overall weight, and providing a faster response time than traditional systems [ 3 ].…”

Section: Introductionmentioning

confidence: 99%

Next-Generation Pedal: Integration of Sensors in a Braking Pedal for a Full Brake-by-Wire System

Gumiel

Mabe

Burguera³

et al. 2023

Sensors

View full text Add to dashboard Cite

This article presents a novel approach to designing and validating a fully electronic braking pedal, addressing the growing integration of electronics in vehicles. With the imminent rise of brake-by-wire (BBW) technology, the brake pedal requires electronification to keep pace with industry advancements. This research explores technologies and features for the next-generation pedal, including low-power consumption electronics, cost-effective sensors, active adjustable pedals, and a retractable pedal for autonomous vehicles. Furthermore, this research brings the benefits of the water injection technique (WIT) as the base for manufacturing plastic pedal brakes towards reducing cost and weight while enhancing torsional stiffness. Communication with original equipment manufacturers (OEMs) has provided valuable insights and feedback, facilitating a productive exchange of ideas. The findings include two sensor prototypes utilizing inductive technology and printed-ink gauges. Significantly, reduced power consumption was achieved in a Hall-effect sensor already in production. Additionally, a functional BBW prototype was developed and validated. This research presents an innovative approach to pedal design that aligns with current electrification trends and autonomous vehicles. It positions the braking pedal as an advanced component that has the potential to redefine industry standards. In summary, this research significantly contributes to the electronic braking pedal technology presenting the critical industry needs that have driven technical studies and progress in the field of sensors, electronics, and materials, highlighting the challenges that component manufacturers will inevitably face in the forthcoming years.

show abstract

“…Considering the better performance of DDPG we will focus on this strategy, having in mind that our final goal is the implementation of the navigation architecture in the real vehicle [1]. Therefore, in the following section, architecture based in DDPG algorithm, which is more stable and reliable, is testing in some new routes.…”

Section: Validation Stagementioning

confidence: 99%

Deep reinforcement learning based control for Autonomous Vehicles in CARLA

Pérez-Gil

Barea

López-Guillén

et al. 2022

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Drive-By-Wire Development Process Based on ROS for an Autonomous Electric Vehicle

Cited by 15 publications

References 32 publications

Reinforcement Learning-Based Autonomous Driving at Intersections in CARLA Simulator

Reinforcement Learning-Based Autonomous Driving at Intersections in CARLA Simulator

Next-Generation Pedal: Integration of Sensors in a Braking Pedal for a Full Brake-by-Wire System

Deep reinforcement learning based control for Autonomous Vehicles in CARLA

Contact Info

Product

Resources

About