scholarly journals Cloud2Edge Elastic AI Framework for Prototyping and Deployment of AI Inference Engines in Autonomous Vehicles

Sensors ◽  
2020 ◽  
Vol 20 (19) ◽  
pp. 5450
Author(s):  
Sorin Grigorescu ◽  
Tiberiu Cocias ◽  
Bogdan Trasnea ◽  
Andrea Margheri ◽  
Federico Lombardi ◽  
...  
Keyword(s):  
Autonomous Vehicles ◽  
Autonomous Driving ◽  
Novel Technologies ◽  
Learning Modules ◽  
Network Bandwidth ◽  
Inference Engines ◽  
Control Units ◽  
Probable Path ◽  
Self Driving Cars ◽  
Most Probable Path

Self-driving cars and autonomous vehicles are revolutionizing the automotive sector, shaping the future of mobility altogether. Although the integration of novel technologies such as Artificial Intelligence (AI) and Cloud/Edge computing provides golden opportunities to improve autonomous driving applications, there is the need to modernize accordingly the whole prototyping and deployment cycle of AI components. This paper proposes a novel framework for developing so-called AI Inference Engines for autonomous driving applications based on deep learning modules, where training tasks are deployed elastically over both Cloud and Edge resources, with the purpose of reducing the required network bandwidth, as well as mitigating privacy issues. Based on our proposed data driven V-Model, we introduce a simple yet elegant solution for the AI components development cycle, where prototyping takes place in the cloud according to the Software-in-the-Loop (SiL) paradigm, while deployment and evaluation on the target ECUs (Electronic Control Units) is performed as Hardware-in-the-Loop (HiL) testing. The effectiveness of the proposed framework is demonstrated using two real-world use-cases of AI inference engines for autonomous vehicles, that is environment perception and most probable path prediction.

scholarly journals Time-Sensitive Network (TSN) Experiment in Sensor-Based Integrated Environment for Autonomous Driving

Sensors ◽  
2019 ◽  
Vol 19 (5) ◽  
pp. 1111 ◽  
Author(s):  
Juho Lee ◽  
Sungkwon Park
Keyword(s):  
Communication Networks ◽  
Autonomous Vehicles ◽  
Performance Test ◽  
Autonomous Driving ◽  
Navigation Systems ◽  
Data Traffic ◽  
Control Units ◽  
Band Size ◽  
Integrated Environment ◽  
Vehicle Network

Recently, large amounts of data traffic from various sensors and image and navigation systems within vehicles are generated for autonomous driving. Broadband communication networks within vehicles have become necessary. New autonomous Ethernet networks are being considered as alternatives. The Ethernet-based in-vehicle network has been standardized in the IEEE 802.1 time-sensitive network (TSN) group since 2006. The Ethernet TSN will be revised and integrated into a subsequent version of IEEE 802.1Q-2018 published in 2018 when various new TSN-related standards are being newly revised and published. A TSN integrated environment simulator is developed in this paper to implement the main functions of the TSN standards that are being developed. This effort would minimize the performance gaps that can occur when the functions of these standards operate in an integrated environment. As part of this purpose, we analyzed the simulator to verify that the traffic for autonomous driving satisfies the TSN transmission requirements in the in-vehicle network (IVN) and the preemption (which is one of the main TSN functions) and reduces the overall End-to-End delay. An optimal guard band size for the preemption was also found for autonomous vehicles in our work. Finally, an IVN model for autonomous vehicles was designed and the performance test was conducted by configuring the traffic to be used for various sensors and electronic control units (ECUs).

scholarly journals Autonomous Recognition Model

2021 ◽  
Vol 10 (6) ◽  
pp. 67-73
Author(s):  
Akash gupta ◽  
Rahat Ali ◽  
Abhay Pratap Singh ◽  
P.Raja Kumar
Keyword(s):  
Artificial Intelligence ◽  
Automobile Industry ◽  
Autonomous Vehicles ◽  
Future Generation ◽  
Autonomous Driving ◽  
Traffic Signs ◽  
Use Of Technology ◽  
Human Driver ◽  
New Research ◽  
Self Driving Cars

Nowdays we are witnessing the technology transforming everything the way we used to do things and how the automobile industry is transforming itself with the use of technology IOT,Artificial intelligence,Machine learning.Companies shifting its products and its utilities in diferent way and they now want to acquire and introduce level-5 autonomous to future generation and big automobile companies are trying to achieve autonomous vechicles and we have researhed about the model that will help in assisting autonomous vechicles and trying to achieve that.We will develop this model with help of technologies like Artificial intelligence,Machine learning,Deep learning.Autonomous vehcicles will become a reality on our roads in the near future. However, the absence of a human driver requires technical solutions for a range of issues, and these are still being developed and optimised. It is a great contribution for the automotive industry which is going towards innovation and economic growth. If we talking about some past decade the momentum of new research and the world is now at the very advanced stage of technological revolution. “Autonomous-driving” vehicles. The term Self-driving cars, autonomous car, or the driverless cars have different name with common objective. The main focus is to keep the human being out of the vehicle control loop and to relieve them from the task of driving. Everyday automotive technology researchers solve challenges. In the future, without human assistance, robots will produce autonomous vehicles using IoT technology based on customer needs and prefer that these vehicles are more secure and comfortable in mobility systems such as the movement of people or goods. We will build a deep neural network model that can classify traffic signs present in the image into different categories. With this model, we are able to read and understand traffic signs which are a very important task for all autonomous vehicles .This model we have tested it and resulted in 95% accuracy.

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 Counter-Mapping the Spaces of Autonomous Driving

2018 ◽  
Author(s):  
Luis F. Alvarez León
Keyword(s):  
Private Sector ◽  
Autonomous Vehicles ◽  
Political Action ◽  
Economic Value ◽  
Autonomous Driving ◽  
The United States ◽  
The State ◽  
Production Of Space ◽  
Black Boxes ◽  
Self Driving Cars

In this article I provide an account of key tensions shaping the development of autonomous driving technologies, and explores how such tensions can open up avenues for counter-mapping the data spaces produced through these navigation technologies. The design and massive commercialization of autonomous vehicles implies the production of new models of space, generated through the integration of data collected through technologies such as lidar scanning, machine learning, and artificial intelligence. This production of space is bounded within the confines of the technological black boxes of the vehicles themselves, as well as the corporate black boxes of the companies that design and deploy them. However, there are key sources of tension surrounding the creation of these black boxes: those between market competitors; between the state and the private sector; and between civil society, the private sector, and the state. In this article I explore these tensions by focusing on the potential for counter-mapping as a means of critique, transparency, and political action across three separate aspects of the autonomous driving space-making process: (1) legislation, by examining the emergence of Right to Repair laws across the United States, beginning with the Automotive Right to Repair Law passed in Massachusetts in 2012; (2) design, through open source projects for building self-driving cars, exemplified by Udacity, a pioneer in this area; and (3) hacking, specifically interventions designed to open, critique, or disrupt autonomous driving technologies. These examinations are embedded in a political economic account that interrogates the ownership and control over the spaces produced through autonomous driving, as well as the economic value associated with such production of space. 

Cloning Safe Driving Behavior for Self-Driving Cars using Convolutional Neural Networks

2019 ◽  
Vol 12 (2) ◽  
pp. 120-127 ◽  
Author(s):  
Wael Farag
Keyword(s):  
Gradient Descent ◽  
Autonomous Driving ◽  
Driving Behavior ◽  
Training Data ◽  
Stochastic Gradient Descent ◽  
Data Set ◽  
Safe Driving ◽  
Processing Pipeline ◽  
Self Driving Cars ◽  
And Training

Background: In this paper, a Convolutional Neural Network (CNN) to learn safe driving behavior and smooth steering manoeuvring, is proposed as an empowerment of autonomous driving technologies. The training data is collected from a front-facing camera and the steering commands issued by an experienced driver driving in traffic as well as urban roads. Methods: This data is then used to train the proposed CNN to facilitate what it is called “Behavioral Cloning”. The proposed Behavior Cloning CNN is named as “BCNet”, and its deep seventeen-layer architecture has been selected after extensive trials. The BCNet got trained using Adam’s optimization algorithm as a variant of the Stochastic Gradient Descent (SGD) technique. Results: The paper goes through the development and training process in details and shows the image processing pipeline harnessed in the development. Conclusion: The proposed approach proved successful in cloning the driving behavior embedded in the training data set after extensive simulations.

Autonomy and Responsibility in Hybrid Systems

2017 ◽  
Author(s):  
Wulf Loh ◽  
Janina Loh
Keyword(s):  
Hybrid Systems ◽  
Hybrid System ◽  
Moral Dilemma ◽  
Autonomous Driving ◽  
Shared Responsibility ◽  
Driving System ◽  
Autonomous Cars ◽  
Self Driving Cars ◽  
Trolley Cases ◽  
Autonomous Driving System

In this chapter, we give a brief overview of the traditional notion of responsibility and introduce a concept of distributed responsibility within a responsibility network of engineers, driver, and autonomous driving system. In order to evaluate this concept, we explore the notion of man–machine hybrid systems with regard to self-driving cars and conclude that the unit comprising the car and the operator/driver consists of such a hybrid system that can assume a shared responsibility different from the responsibility of other actors in the responsibility network. Discussing certain moral dilemma situations that are structured much like trolley cases, we deduce that as long as there is something like a driver in autonomous cars as part of the hybrid system, she will have to bear the responsibility for making the morally relevant decisions that are not covered by traffic rules.

Female Voice Agents in Fully Autonomous Vehicles Are Not Only More Likeable and Comfortable, But Also More Competent

2020 ◽  
Vol 64 (1) ◽  
pp. 1033-1037
Author(s):  
Jiayuan Dong ◽  
Emily Lawson ◽  
Jack Olsen ◽  
Myounghoon Jeon
Keyword(s):  
Autonomous Vehicles ◽  
Autonomous Driving ◽  
Preference Ranking ◽  
Uncanny Valley ◽  
Tracking Data ◽  
Effective Solution ◽  
User Perception ◽  
Future Studies ◽  
Underlying Mechanisms ◽  
The Voice

Driving agents can provide an effective solution to improve drivers’ trust in and to manage interactions with autonomous vehicles. Research has focused on voice-agents, while few have explored robot-agents or the comparison between the two. The present study tested two variables - voice gender and agent embodiment, using conversational scripts. Twenty participants experienced autonomous driving using the simulator for four agent conditions and filled out subjective questionnaires for their perception of each agent. Results showed that the participants perceived the voice only female agent as more likeable, more comfortable, and more competent than other conditions. Their final preference ranking also favored this agent over the others. Interestingly, eye-tracking data showed that embodied agents did not add more visual distractions than the voice only agents. The results are discussed with the traditional gender stereotype, uncanny valley, and participants’ gender. This study can contribute to the design of in-vehicle agents in the autonomous vehicles and future studies are planned to further identify the underlying mechanisms of user perception on different agents.

scholarly journals An Intelligent Task Scheduling Mechanism for Autonomous Vehicles via Deep Learning

Energies ◽  
2021 ◽  
Vol 14 (6) ◽  
pp. 1788
Author(s):  
Gomatheeshwari Balasekaran ◽  
Selvakumar Jayakumar ◽  
Rocío Pérez de Prado
Keyword(s):  
Execution Time ◽  
Autonomous Vehicles ◽  
Rapid Development ◽  
Single Layer ◽  
Battery Life ◽  
Learning Approaches ◽  
Task Management ◽  
Inference System ◽  
Safe Driving ◽  
Self Driving Cars

With the rapid development of the Internet of Things (IoT) and artificial intelligence, autonomous vehicles have received much attention in recent years. Safe driving is one of the essential concerns of self-driving cars. The main problem in providing better safe driving requires an efficient inference system for real-time task management and autonomous control. Due to limited battery life and computing power, reducing execution time and resource consumption can be a daunting process. This paper addressed these challenges and developed an intelligent task management system for IoT-based autonomous vehicles. For each task processing, a supervised resource predictor is invoked for optimal hardware cluster selection. Tasks are executed based on the earliest hyper period first (EHF) scheduler to achieve optimal task error rate and schedule length performance. The single-layer feedforward neural network (SLFN) and lightweight learning approaches are designed to distribute each task to the appropriate processor based on their emergency and CPU utilization. We developed this intelligent task management module in python and experimentally tested it on multicore SoCs (Odroid Xu4 and NVIDIA Jetson embedded platforms).Connected Autonomous Vehicles (CAV) and Internet of Medical Things (IoMT) benchmarks are used for training and testing purposes. The proposed modules are validated by observing the task miss rate, resource utilization, and energy consumption metrics compared with state-of-art heuristics. SLFN-EHF task scheduler achieved better results in an average of 98% accuracy, and in an average of 20–27% reduced in execution time and 32–45% in task miss rate metric than conventional methods.

Sign in / Sign up

Export Citation Format

Share Document