scholarly journals Autonomous Drifting Using Reinforcement Learning

2021 ◽  
Author(s):  
László Orgován ◽  
Tamás Bécsi ◽  
Szilárd Aradi
Keyword(s):  
Reinforcement Learning ◽  
Autonomous Vehicles ◽  
Learning Algorithm ◽  
Autonomous Vehicle ◽  
Autonomous Driving ◽  
The Road ◽  
Model Free ◽  
On The Road ◽  
Self Driving Cars ◽  
Planning Problems

Autonomous vehicles or self-driving cars are prevalent nowadays, many vehicle manufacturers, and other tech companies are trying to develop autonomous vehicles. One major goal of the self-driving algorithms is to perform manoeuvres safely, even when some anomaly arises. To solve these kinds of complex issues, Artificial Intelligence and Machine Learning methods are used. One of these motion planning problems is when the tires lose their grip on the road, an autonomous vehicle should handle this situation. Thus the paper provides an Autonomous Drifting algorithm using Reinforcement Learning. The algorithm is based on a model-free learning algorithm, Twin Delayed Deep Deterministic Policy Gradients (TD3). The model is trained on six different tracks in a simulator, which is developed specifically for autonomous driving systems; namely CARLA.

scholarly journals Autonomous Vehicle Fuel Economy Optimization with Deep Reinforcement Learning

Electronics ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1911
Author(s):  
Hyunkun Kim ◽  
Hyeongoo Pyeon ◽  
Jong Sool Park ◽  
Jin Young Hwang ◽  
Sejoon Lim
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Reinforcement Learning ◽  
Velocity Profile ◽  
Fuel Economy ◽  
Autonomous Vehicles ◽  
Learning Algorithm ◽  
Autonomous Vehicle ◽  
Simulation Program ◽  
On The Road

The ever-increasing number of vehicles on the road puts pressure on car manufacturers to make their car fuel-efficient. With autonomous vehicles, we can find new strategies to optimize fuels. We propose a reinforcement learning algorithm that trains deep neural networks to generate a fuel-efficient velocity profile for autonomous vehicles given road altitude information for the planned trip. Using a highly accurate industry-accepted fuel economy simulation program, we train our deep neural network model. We developed a technique for adapting the heterogeneous simulation program on top of an open-source deep learning framework, and reduced dimension of the problem output with suitable parameterization to train the neural network much faster. The learned model combined with reinforcement learning-based strategy generation effectively generated the velocity profile so that autonomous vehicles can follow to control itself in a fuel efficient way. We evaluate our algorithm’s performance using the fuel economy simulation program for various altitude profiles. We also demonstrate that our method can teach neural networks to generate useful strategies to increase fuel economy even on unseen roads. Our method improved fuel economy by 8% compared to a simple grid search approach.

scholarly journals Autonomous Driving in Roundabout Maneuvers Using Reinforcement Learning with Q-Learning

Electronics ◽  
2019 ◽  
Vol 8 (12) ◽  
pp. 1536 ◽  
Author(s):  
Laura García Cuenca ◽  
Enrique Puertas ◽  
Javier Fernandez Andrés ◽  
Nourdine Aliane
Keyword(s):  
Reinforcement Learning ◽  
Autonomous Vehicles ◽  
Learning Algorithm ◽  
Autonomous Vehicle ◽  
Autonomous Driving ◽  
Simulation Environment ◽  
Q Learning ◽  
Driving Scenario

Navigating roundabouts is a complex driving scenario for both manual and autonomous vehicles. This paper proposes an approach based on the use of the Q-learning algorithm to train an autonomous vehicle agent to learn how to appropriately navigate roundabouts. The proposed learning algorithm is implemented using the CARLA simulation environment. Several simulations are performed to train the algorithm in two scenarios: navigating a roundabout with and without surrounding traffic. The results illustrate that the Q-learning-algorithm-based vehicle agent is able to learn smooth and efficient driving to perform maneuvers within roundabouts.

Analysis of Preference for Autonomous Driving Under Different Traffic Conditions Using a Driving Simulator

2015 ◽  
Vol 27 (6) ◽  
pp. 660-670 ◽  
Author(s):  
Udara Eshan Manawadu ◽  
◽  
Masaaki Ishikawa ◽  
Mitsuhiro Kamezaki ◽  
Shigeki Sugano ◽  
...  
Keyword(s):  
Autonomous Vehicles ◽  
Driving Simulator ◽  
Autonomous Driving ◽  
Driving Experience ◽  
The Road ◽  
Traffic Conditions ◽  
Passenger Vehicles ◽  
New Type ◽  
On The Road ◽  
Near Future

<div class=""abs_img""><img src=""[disp_template_path]/JRM/abst-image/00270006/08.jpg"" width=""300"" /> Driving simulator</div>Intelligent passenger vehicles with autonomous capabilities will be commonplace on our roads in the near future. These vehicles will reshape the existing relationship between the driver and vehicle. Therefore, to create a new type of rewarding relationship, it is important to analyze when drivers prefer autonomous vehicles to manually-driven (conventional) vehicles. This paper documents a driving simulator-based study conducted to identify the preferences and individual driving experiences of novice and experienced drivers of autonomous and conventional vehicles under different traffic and road conditions. We first developed a simplified driving simulator that could connect to different driver-vehicle interfaces (DVI). We then created virtual environments consisting of scenarios and events that drivers encounter in real-world driving, and we implemented fully autonomous driving. We then conducted experiments to clarify how the autonomous driving experience differed for the two groups. The results showed that experienced drivers opt for conventional driving overall, mainly due to the flexibility and driving pleasure it offers, while novices tend to prefer autonomous driving due to its inherent ease and safety. A further analysis indicated that drivers preferred to use both autonomous and conventional driving methods interchangeably, depending on the road and traffic conditions.

scholarly journals A PRELIMINARY STUDY ON UPDATING HIGH DEFINITION MAPS: DETECTING AND POSITIONING A TRAFFIC CONE BY USING A STEREO CAMERA

2019 ◽  
Vol XLII-4/W19 ◽  
pp. 271-274
Author(s):  
M. L. R. Lagahit ◽  
Y. H. Tseng
Keyword(s):  
Real Time ◽  
Data Storage ◽  
Autonomous Vehicles ◽  
Detection System ◽  
Time Data ◽  
High Definition ◽  
Stereo Camera ◽  
The Road ◽  
On The Road ◽  
Self Driving Cars

Abstract. The concept of Autonomous Vehicles (AV) or self-driving cars has been increasingly popular these past few years. As such, research and development of AVs have also escalated around the world. One of those researches is about High-Definition (HD) maps. HD Maps are basically very detailed maps that provide all the geometric and semantic information on the road, which helps the AV in positioning itself on the lanes as well as mapping objects and markings on the road. This research will focus on the early stages of updating said HD maps. The methodology mainly consists of (1) running YOLOv3, a real-time object detection system, on a photo taken from a stereo camera to detect the object of interest, in this case a traffic cone, (2) applying the theories of stereo-photogrammetry to determine the 3D coordinates of the traffic cone, and (3) executing all of it at the same time on a Python-based platform. Results have shown centimeter-level accuracy in terms of obtained distance and height of the detected traffic cone from the camera setup. In future works, observed coordinates can be uploaded to a database and then connected to an application for real-time data storage/management and interactive visualization.

Self-Driving Cars

2020 ◽  
pp. 490-507
Author(s):  
Pooja Jha ◽  
K. Sridhar Patnaik
Keyword(s):  
Traffic Safety ◽  
Autonomous Vehicle ◽  
Technological Advancement ◽  
Social Environments ◽  
Highway Traffic ◽  
National Highway Traffic Safety ◽  
Human Errors ◽  
The Road ◽  
On The Road ◽  
Self Driving Cars

Human errors are the main cause of vehicle crashes. Self-driving cars bear the promise to significantly reduce accidents by taking the human factor out of the equation, while in parallel monitor the surroundings, detect and react immediately to potentially dangerous situations and driving behaviors. Artificial intelligence tool trains the computers to do things like detect lane lines and identify cyclists by showing them millions of examples of the subject at hand. The chapter in this book discusses the technological advancement in transportation. It also covers the autonomy used according to The National Highway Traffic Safety Administration (NHTSA). The functional architecture of self-driving cars is further discussed. The chapter also talks about two algorithms for detection of lanes as well as detection of vehicles on the road for self-driving cars. Next, the ethical discussions surrounding the autonomous vehicle involving stakeholders, technologies, social environments, and costs vs. quality have been discussed.

Pedestrians’ understanding of fully autonomous vehicles (FAV) intent to stop

2020 ◽  
Vol 64 (1) ◽  
pp. 1931-1932
Author(s):  
Michal Hochman ◽  
Tal Oron-Gilad
Keyword(s):  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Background Color ◽  
Urban Road ◽  
The Road ◽  
Message Type ◽  
On The Road ◽  
Future Work ◽  
Road Crossing ◽  
Distance Conditions

This study explored pedestrians’ understanding of Fully Autonomous Vehicle (FAV) intention and what influences their decision to cross. Twenty participants saw fixed simulated urban road crossing scenes with a FAV present on the road. The scenes differed from one another in the FAV’s messages: the external Human-Machine Interfaces (e-HMI) background color, message type and modality, the FAV’s distance from the crossing place, and its size. Eye-tracking data and objective measurements were collected. Results revealed that pedestrians looked at the e-HMI before making their decision; however, they did not always make the decision according to the e-HMIs’ color, instructions (in advice messages), or intention (in status messages). Moreover, when they acted according to the e-HMI proposition, for certain distance conditions, they tended to hesitate before making the decision. Findings suggest that pedestrians’ decision making to cross depends on a combination of the e-HMI implementation and the car distance. Future work should explore the robustness of the findings in dynamic and more complex crossing environments.

scholarly journals An Integrated Model for User State Detection of Subjective Discomfort in Autonomous Vehicles

Vehicles ◽  
2021 ◽  
Vol 3 (4) ◽  
pp. 764-777
Author(s):  
Dario Niermann ◽  
Alexander Trende ◽  
Klas Ihme ◽  
Uwe Drewitz ◽  
Cornelia Hollander ◽  
...  
Keyword(s):  
Autonomous Vehicles ◽  
Linear Models ◽  
Driving Simulator ◽  
Autonomous Vehicle ◽  
The Road ◽  
Novel Approach ◽  
Driving Scenario ◽  
On The Road ◽  
Using Data ◽  
Subjective Discomfort

The quickly rising development of autonomous vehicle technology and increase of (semi-) autonomous vehicles on the road leads to an increased demand for more sophisticated human–machine-cooperation approaches to improve trust and acceptance of these new systems. In this work, we investigate the feeling of discomfort of human passengers while driving autonomously and the automatic detection of this discomfort with several model approaches, using the combination of different data sources. Based on a driving simulator study, we analyzed the discomfort reports of 50 participants for autonomous inner city driving. We found that perceived discomfort depends on the driving scenario (with discomfort generally peaking in complex situations) and on the passenger (resulting in interindividual differences in reported discomfort extend and duration). Further, we describe three different model approaches on how to predict the passenger discomfort using data from the vehicle’s sensors as well as physiological and behavioral data from the passenger. The model’s precision varies greatly across the approaches, the best approach having a precision of up to 80%. All of our presented model approaches use combinations of linear models and are thus fast, transparent, and safe. Lastly, we analyzed these models using the SHAP method, which enables explaining the models’ discomfort predictions. These explanations are used to infer the importance of our collected features and to create a scenario-based discomfort analysis. Our work demonstrates a novel approach on passenger state modelling with simple, safe, and transparent models and with explainable model predictions, which can be used to adapt the vehicles’ actions to the needs of the passenger.

scholarly journals Machine Learning to Classify Driving Events Using Mobile Phone Sensors Data

2021 ◽  
Vol 15 (02) ◽  
pp. 124
Author(s):  
Yazan Alqudah ◽  
Belal Sababha ◽  
Esam Qaralleh ◽  
Tarek Yousseff
Keyword(s):  
Machine Learning ◽  
Road Safety ◽  
Autonomous Vehicles ◽  
Machine Learning Algorithms ◽  
Motion Sensors ◽  
The Road ◽  
Crowd Sensing ◽  
Innovative Solution ◽  
On The Road ◽  
Self Driving Cars

With the ever-increasing vehicle population and introduction of autonomous and self-driving cars, innovative research is needed to ensure safety and reliability on the road. This work introduces an innovative solution that aims at understanding vehicle behavior based on sensors data. The behavior is classified according to driving events. Understanding driving events can play a significant role in road safety and estimating the expense and risks of driving and consuming a vehicle. Rather than relying on the distance and time driven, driving events can provide a more accurate measure of vehicle driving consumption.  This measure will become more valuable as more autonomous vehicles and more ride sharing applications are introduced to roads around the world. Estimating driving events can also help better design the road infrastructure to reduce energy consumption.  By sharing data from official vehicles and volunteers, crowd sensing can be used to better understand congestion and road safety. This work studies driving events and proposes using machine learning to classify these events into different categories. The acquired data is collected using embedded mobile device motion sensors and are used to train machine learning algorithms to classify the events.

Regaining Sight of Humanity on The Roadway towards Automation

2020 ◽  
Vol 2020 (16) ◽  
pp. 88-1-88-5
Author(s):  
Mónica López-González
Keyword(s):  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Machine Learning Algorithms ◽  
Technological Advancement ◽  
Cognitive Intelligence ◽  
Safety Standards ◽  
The Road ◽  
Technological Advances ◽  
On The Road ◽  
Problem Solve

A primary goal of the auto industry is to revolutionize transportation with autonomous vehicles. Given the mammoth nature of such a target, success depends on a clearly defined balance between technological advances, machine learning algorithms, physical and network infrastructure, safety, standards and regulations, and end-user education. Unfortunately, technological advancement is outpacing the regulatory space and competition is driving deployment. Moreover, hope is being built around algorithms that are far from reaching human-like capacities on the road. Since human behaviors and idiosyncrasies and natural phenomena are not going anywhere anytime soon and so-called edge cases are the roadway norm, the industry stands at a historic crossroads. Why? Because human factors such as cognitive and behavioral insights into how we think, feel, act, plan, make decisions, and problem-solve have been ignored. Human cognitive intelligence is foundational to driving the industry’s ambition forward. In this paper I discuss the role of the human in bridging the gaps between autonomous vehicle technology, design, implementation, and beyond.

scholarly journals 5G-Enabled Autonomous Driving Demonstration with a V2X Scenario-in-the-Loop Approach

Sensors ◽  
2020 ◽  
Vol 20 (24) ◽  
pp. 7344
Author(s):  
Zsolt Szalay ◽  
Dániel Ficzere ◽  
Viktor Tihanyi ◽  
Ferenc Magyar ◽  
Gábor Soós ◽  
...  
Keyword(s):  
Autonomous Vehicles ◽  
Mass Communication ◽  
Real Life ◽  
Autonomous Driving ◽  
Mobile Technologies ◽  
Low Latency ◽  
Vehicular Communication ◽  
Digital Twin ◽  
The Road ◽  
On The Road

Autonomous vehicles are at the forefront of interest due to the expectations of changing transportation for the better. In order to make better decisions on the road, vehicles use information from various sources: their own sensors, messages arriving from surrounding vehicles and objects, as well as from centralized entities—including their own Digital Twin. Certain decisions require the information to arrive with low latency and some of this information (such as video) requires broadband communication. Furthermore, the vehicles can populate an area, so they can represent mass communication endpoints that still need low latency and massive broadband. The mobility of the vehicles obviously requires the complete coverage of the roads with reliable wireless communication technologies fulfilling the previously mentioned needs. The fifth generation of cellular mobile technologies, 5G, addresses these requirements. The current paper presents real-life scenarios—on the M86 highway and the ZalaZONE proving ground in Hungary—for the demonstration of vehicular communication with 5G support, where the cars exchange sensor and control information with each other, their environment, and their Digital Twins. The demonstrations were carried out through the Scenario-in-the-Loop (SciL) methodology, where some of the actionable triggers were not physically present around the vehicles, but sensed or simulated around their Digital Twin. The measurements around the demonstrations aim to reveal the feasibility of the 5G Non-Standalone Architecture for certain communication scenarios, and they mainly aim to reveal the current latency and throughput limitations under real-life conditions.

Sign in / Sign up

Export Citation Format

Share Document