scholarly journals Evolutionary vs. imitation learning for neuromorphic control at the edge

2021 ◽  
Author(s):  
Catherine Schuman ◽  
Robert Patton ◽  
Shruti Kulkarni ◽  
Maryam Parsa ◽  
Christopher Stahl ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Autonomous Vehicles ◽  
Imitation Learning ◽  
Learning Approaches ◽  
Control Task ◽  
Control Applications ◽  
Race Car ◽  
Neuromorphic Hardware ◽  
Neuromorphic Systems ◽  
And Robotics

Abstract Neuromorphic computing offers the opportunity to implement extremely low power artificial intelligence at the edge. Control applications, such as autonomous vehicles and robotics, are also of great interest for neuromorphic systems at the edge. It is not clear, however, what the best neuromorphic training approaches are for control applications at the edge. In this work, we implement and compare the performance of evolutionary optimization and imitation learning approaches on an autonomous race car control task using an edge neuromorphic implementation. We show that the evolutionary approaches tend to achieve better performing smaller network sizes that are well-suited to edge deployment, but they also take significantly longer to train. We also describe a workflow to allow for future algorithmic comparisons for neuromorphic hardware on control applications at the edge.

scholarly journals Autonomous Vehicles – a New Challenge to Human Rights?

2019 ◽  
Vol 9 ◽  
Author(s):  
Dominika Iwan
Keyword(s):  
Artificial Intelligence ◽  
Human Rights ◽  
Computer Science ◽  
Autonomous Vehicles ◽  
New Technologies ◽  
Autonomous Vehicle ◽  
Human Beings ◽  
Human Rights Law ◽  
Human Control ◽  
And Robotics

New technologies, as autonomous vehicles are, disrupt the way people exist, and con-sequently with human rights. Research devoted to artificial intelligence and robotics moves freely and the destination, for the time being, is unknown. This is the reason why special attention should be paid to the ethics of these branches of computer science in order to prevent the creation of a crisis point, when human beings are no longer neces-sary.. The aim of this paper is to examine whether such development is a new challenge to human rights law and what happens when an autonomous vehicle drives an autono-mous human being. The paper also mentions the desirable level of human control over the machine so that human dignity, from which human rights originate, is preserved.

scholarly journals Toward Digitalization of Maritime Transport?

Sensors ◽  
2019 ◽  
Vol 19 (4) ◽  
pp. 926 ◽  
Author(s):  
Pedro-Luis Sanchez-Gonzalez ◽  
David Díaz-Gutiérrez ◽  
Teresa Leo ◽  
Luis Núñez-Rivas
Keyword(s):  
Artificial Intelligence ◽  
Autonomous Vehicles ◽  
Mixed Reality ◽  
State Of The Art ◽  
Ship Design ◽  
Maritime Transport ◽  
The Subject ◽  
Basic Facts ◽  
And Robotics ◽  
Insight Into

Although maritime transport is the backbone of world commerce, its digitalization lags significantly behind when we consider some basic facts. This work verifies the state-of-the-art as it currently applies to eight digital domains: Autonomous vehicles and robotics; artificial intelligence; big data; virtual reality, augmented and mixed reality; internet of things; the cloud and edge computing; digital security; and 3D printing and additive engineering. It also provides insight into each of the three sectors into which this industry has been divided: Ship design and shipbuilding; shipping; and ports. The work, based on a systematic literature review, demonstrates that there are domains on which almost no formal study has been done thus far and concludes that there are major areas that require attention in terms of research. It also illustrates the increasing interest on the subject, arising from the necessity of raising the maritime transport industry to the same level of digitalization as other industries.

Autonomous Vehicles in the Mobility System

2020 ◽  
pp. 500-514
Author(s):  
Thilo von Pape
Keyword(s):  
Artificial Intelligence ◽  
Mobile Phones ◽  
Mobile Communication ◽  
Autonomous Vehicles ◽  
Communication Research ◽  
Collective Control ◽  
System P ◽  
Mobility System ◽  
And Control ◽  
Transportation Technologies

This chapter discusses how autonomous vehicles (AVs) may interact with our evolving mobility system and what they mean for mobile communication research. It juxtaposes a conceptualization of AVs as manifestations of automation and artificial intelligence with an analysis of our mobility system as a historically grown hybrid of communication and transportation technologies. Since the emergence of railroad and telegraph, this system has evolved on two layers: an underlying infrastructure to power and coordinate the movements of objects, people, and ideas in industrially scaled speeds, volumes, and complexity and an interface to seamlessly access this infrastructure and control it. AVs are poised to further enhance the seamlessness which mobile phones and cars already lent to mobility. But in assuming increasingly sophisticated control tasks, AVs also disrupt an established shift toward individual control, demanding new interfaces to enable higher levels of individual and collective control over the mobility infrastructure.

scholarly journals The use of artificial intelligence and robotics in regional anaesthesia

Anaesthesia ◽  
2021 ◽  
Vol 76 (S1) ◽  
pp. 171-181 ◽  
Author(s):  
M. McKendrick ◽  
S. Yang ◽  
G. A. McLeod
Keyword(s):  
Artificial Intelligence ◽  
Regional Anaesthesia ◽  
And Robotics

scholarly journals Artificial Intelligence and Behavioral Science Through the Looking Glass: Challenges for Real-World Application

2020 ◽  
Vol 54 (12) ◽  
pp. 942-947
Author(s):  
Pol Mac Aonghusa ◽  
Susan Michie
Keyword(s):  
Climate Change ◽  
Artificial Intelligence ◽  
Machine Learning ◽  
Behavior Change ◽  
Behavioral Science ◽  
Lessons Learned ◽  
Learning Approaches ◽  
Intervention Evaluation ◽  
Research Activities ◽  
Behavior Change Interventions

Abstract Background Artificial Intelligence (AI) is transforming the process of scientific research. AI, coupled with availability of large datasets and increasing computational power, is accelerating progress in areas such as genetics, climate change and astronomy [NeurIPS 2019 Workshop Tackling Climate Change with Machine Learning, Vancouver, Canada; Hausen R, Robertson BE. Morpheus: A deep learning framework for the pixel-level analysis of astronomical image data. Astrophys J Suppl Ser. 2020;248:20; Dias R, Torkamani A. AI in clinical and genomic diagnostics. Genome Med. 2019;11:70.]. The application of AI in behavioral science is still in its infancy and realizing the promise of AI requires adapting current practices. Purposes By using AI to synthesize and interpret behavior change intervention evaluation report findings at a scale beyond human capability, the HBCP seeks to improve the efficiency and effectiveness of research activities. We explore challenges facing AI adoption in behavioral science through the lens of lessons learned during the Human Behaviour-Change Project (HBCP). Methods The project used an iterative cycle of development and testing of AI algorithms. Using a corpus of published research reports of randomized controlled trials of behavioral interventions, behavioral science experts annotated occurrences of interventions and outcomes. AI algorithms were trained to recognize natural language patterns associated with interventions and outcomes from the expert human annotations. Once trained, the AI algorithms were used to predict outcomes for interventions that were checked by behavioral scientists. Results Intervention reports contain many items of information needing to be extracted and these are expressed in hugely variable and idiosyncratic language used in research reports to convey information makes developing algorithms to extract all the information with near perfect accuracy impractical. However, statistical matching algorithms combined with advanced machine learning approaches created reasonably accurate outcome predictions from incomplete data. Conclusions AI holds promise for achieving the goal of predicting outcomes of behavior change interventions, based on information that is automatically extracted from intervention evaluation reports. This information can be used to train knowledge systems using machine learning and reasoning algorithms.

scholarly journals Symbiosis with artificial intelligence via the prism of law, robots, and society

2021 ◽  
Author(s):  
Stamatis Karnouskos
Keyword(s):  
Artificial Intelligence ◽  
Social Economic ◽  
Autonomous Robots ◽  
Law And Society ◽  
Citizenship Rights ◽  
Legal Entity ◽  
Profound Impact ◽  
The People ◽  
Physical Presence ◽  
And Robotics

AbstractThe rapid advances in Artificial Intelligence and Robotics will have a profound impact on society as they will interfere with the people and their interactions. Intelligent autonomous robots, independent if they are humanoid/anthropomorphic or not, will have a physical presence, make autonomous decisions, and interact with all stakeholders in the society, in yet unforeseen manners. The symbiosis with such sophisticated robots may lead to a fundamental civilizational shift, with far-reaching effects as philosophical, legal, and societal questions on consciousness, citizenship, rights, and legal entity of robots are raised. The aim of this work is to understand the broad scope of potential issues pertaining to law and society through the investigation of the interplay of law, robots, and society via different angles such as law, social, economic, gender, and ethical perspectives. The results make it evident that in an era of symbiosis with intelligent autonomous robots, the law systems, as well as society, are not prepared for their prevalence. Therefore, it is now the time to start a multi-disciplinary stakeholder discussion and derive the necessary policies, frameworks, and roadmaps for the most eminent issues.

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.

scholarly journals A Comprehensive Study of Artificial Intelligence and Machine Learning Approaches in Confronting the Coronavirus (COVID-19) Pandemic

2021 ◽  
pp. 002073142110174
Author(s):  
Md Mijanur Rahman ◽  
Fatema Khatun ◽  
Ashik Uzzaman ◽  
Sadia Islam Sami ◽  
Md Al-Amin Bhuiyan ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Health Care ◽  
Language Processing ◽  
Probabilistic Models ◽  
Health Care Systems ◽  
Learning Approaches ◽  
Care Systems ◽  
Novel Coronavirus ◽  
Comprehensive Study

The novel coronavirus disease (COVID-19) has spread over 219 countries of the globe as a pandemic, creating alarming impacts on health care, socioeconomic environments, and international relationships. The principal objective of the study is to provide the current technological aspects of artificial intelligence (AI) and other relevant technologies and their implications for confronting COVID-19 and preventing the pandemic’s dreadful effects. This article presents AI approaches that have significant contributions in the fields of health care, then highlights and categorizes their applications in confronting COVID-19, such as detection and diagnosis, data analysis and treatment procedures, research and drug development, social control and services, and the prediction of outbreaks. The study addresses the link between the technologies and the epidemics as well as the potential impacts of technology in health care with the introduction of machine learning and natural language processing tools. It is expected that this comprehensive study will support researchers in modeling health care systems and drive further studies in advanced technologies. Finally, we propose future directions in research and conclude that persuasive AI strategies, probabilistic models, and supervised learning are required to tackle future pandemic challenges.

scholarly journals Goal-driven active learning

2021 ◽  
Vol 35 (2) ◽  
Author(s):  
Nicolas Bougie ◽  
Ryutaro Ichise
Keyword(s):  
Decision Making ◽  
Reinforcement Learning ◽  
Learning Process ◽  
Real World ◽  
Imitation Learning ◽  
Learning Approaches ◽  
Wide Range ◽  
Fixed Set ◽  
Complex Decision Making ◽  
Complex Decision

AbstractDeep reinforcement learning methods have achieved significant successes in complex decision-making problems. In fact, they traditionally rely on well-designed extrinsic rewards, which limits their applicability to many real-world tasks where rewards are naturally sparse. While cloning behaviors provided by an expert is a promising approach to the exploration problem, learning from a fixed set of demonstrations may be impracticable due to lack of state coverage or distribution mismatch—when the learner’s goal deviates from the demonstrated behaviors. Besides, we are interested in learning how to reach a wide range of goals from the same set of demonstrations. In this work we propose a novel goal-conditioned method that leverages very small sets of goal-driven demonstrations to massively accelerate the learning process. Crucially, we introduce the concept of active goal-driven demonstrations to query the demonstrator only in hard-to-learn and uncertain regions of the state space. We further present a strategy for prioritizing sampling of goals where the disagreement between the expert and the policy is maximized. We evaluate our method on a variety of benchmark environments from the Mujoco domain. Experimental results show that our method outperforms prior imitation learning approaches in most of the tasks in terms of exploration efficiency and average scores.

scholarly journals Designing an Artificial Intelligence Control Program Model to be Tested and Implemented in Virtual Reality for Automated Chevrolet Camaro

Proceedings ◽  
2020 ◽  
Vol 63 (1) ◽  
pp. 44
Author(s):  
Lavinia Andrei ◽  
Doru-Laurean Baldean ◽  
Adela-Ioana Borzan
Keyword(s):  
Artificial Intelligence ◽  
Virtual Reality ◽  
Control Program ◽  
Specific Model ◽  
Virtual Model ◽  
Program Model ◽  
Real Size ◽  
Virtual Modeling ◽  
And Robotics ◽  
Virtual Reality Application

A control program was designed with Unity 5 virtual reality application in the automotive and robotics field. Thus, a virtual model of a robotic car was tested in a virtual reality program. After optimization, the smart controller was implemented on a specific model of the automated Chevrolet Camaro. The main objective of the present paper is to design a control program model to be tested in virtual reality and in a real-size car. Results concerning the virtual modeling of an automated car and its artificial intelligence controls have been presented and discussed, outlining the forces, torques, and context awareness capabilities of the car.

Sign in / Sign up

Export Citation Format

Share Document