Search results: Found 15

Listing 1 - 10 of 15 << page
of 2
>>
Sort by
Value and Reward Based Learning in Neurobots

Authors: ---
Book Series: Frontiers Research Topics ISSN: 16648714 ISBN: 9782889194315 Year: Pages: 158 DOI: 10.3389/978-2-88919-431-5 Language: English
Publisher: Frontiers Media SA
Subject: Neurology --- Science (General)
Added to DOAB on : 2016-01-19 14:05:46
License:

Loading...
Export citation

Choose an application

Abstract

Organisms are equipped with value systems that signal the salience of environmental cues to their nervous system, causing a change in the nervous system that results in modification of their behavior. These systems are necessary for an organism to adapt its behavior when an important environmental event occurs. A value system constitutes a basic assumption of what is good and bad for an agent. These value systems have been effectively used in robotic systems to shape behavior. For example, many robots have used models of the dopaminergic system to reinforce behavior that leads to rewards. Other modulatory systems that shape behavior are acetylcholine’s effect on attention, norepinephrine’s effect on vigilance, and serotonin’s effect on impulsiveness, mood, and risk. Moreover, hormonal systems such as oxytocin and its effect on trust constitute as a value system. This book presents current research involving neurobiologically inspired robots whose behavior is: 1) Shaped by value and reward learning, 2) adapted through interaction with the environment, and 3) shaped by extracting value from the environment.

Intelligent Business Process Optimization for the Service Industry

Author:
ISBN: 9783866444546 Year: Pages: 310 p. DOI: 10.5445/KSP/1000014466 Language: ENGLISH
Publisher: KIT Scientific Publishing
Subject: Business and Management
Added to DOAB on : 2019-07-30 20:01:57
License:

Loading...
Export citation

Choose an application

Abstract

The company's sustainable competitive advantage derives from its capacity to create value for customers and to adapt the operational practices to changing situations. Business processes are the heart of each company. Therefore process excellence has become a key issue. This book introduces a novel approach focusing on the autonomous optimization of business processes by applying sophisticated machine learning techniques such as Relational Reinforcement Learning and Particle Swarm Optimization.

Intrinsic motivations and open-ended development in animals, humans, and robots

Authors: --- --- --- --- et al.
Book Series: Frontiers Research Topics ISSN: 16648714 ISBN: 9782889193721 Year: Pages: 350 DOI: 10.3389/978-2-88919-372-1 Language: English
Publisher: Frontiers Media SA
Subject: Neurology --- Science (General) --- Psychology
Added to DOAB on : 2015-11-19 16:29:12
License:

Loading...
Export citation

Choose an application

Abstract

The aim of this Research Topic for Frontiers in Psychology under the section of Cognitive Science and Frontiers in Neurorobotics is to present state-of-the-art research, whether theoretical, empirical, or computational investigations, on open-ended development driven by intrinsic motivations. The topic will address questions such as: How do motivations drive learning? How are complex skills built up from a foundation of simpler competencies? What are the neural and computational bases for intrinsically motivated learning? What is the contribution of intrinsic motivations to wider cognition? Autonomous development and lifelong open-ended learning are hallmarks of intelligence. Higher mammals, and especially humans, engage in activities that do not appear to directly serve the goals of survival, reproduction, or material advantage. Rather, a large part of their activity is intrinsically motivated - behavior driven by curiosity, play, interest in novel stimuli and surprising events, autonomous goal-setting, and the pleasure of acquiring new competencies. This allows the cumulative acquisition of knowledge and skills that can later be used to accomplish fitness-enhancing goals. Intrinsic motivations continue during adulthood, and in humans artistic creativity, scientific discovery, and subjective well-being owe much to them. The study of intrinsically motivated behavior has a long history in psychological and ethological research, which is now being reinvigorated by perspectives from neuroscience, artificial intelligence and computer science. For example, recent neuroscientific research is discovering how neuromodulators like dopamine and noradrenaline relate not only to extrinsic rewards but also to novel and surprising events, how brain areas such as the superior colliculus and the hippocampus are involved in the perception and processing of events, novel stimuli, and novel associations of stimuli, and how violations of predictions and expectations influence learning and motivation. Computational approaches are characterizing the space of possible reinforcement learning algorithms and their augmentation by intrinsic reinforcements of different kinds. Research in robotics and machine learning is yielding systems with increasing autonomy and capacity for self-improvement: artificial systems with motivations that are similar to those of real organisms and support prolonged autonomous learning. Computational research on intrinsic motivation is being complemented by, and closely interacting with, research that aims to build hierarchical architectures capable of acquiring, storing, and exploiting the knowledge and skills acquired through intrinsically motivated learning. Now is an important moment in the study of intrinsically motivated open-ended development, requiring contributions and integration across a large number of fields within the cognitive sciences. This Research Topic aims to contribute to this effort by welcoming papers carried out with ethological, psychological, neuroscientific and computational approaches, as well as research that cuts across disciplines and approaches.

Oxytocin's routes in social behavior: Into the 21st century

Authors: --- ---
Book Series: Frontiers Research Topics ISSN: 16648714 ISBN: 9782889196968 Year: Pages: 132 DOI: 10.3389/978-2-88919-696-8 Language: English
Publisher: Frontiers Media SA
Subject: Neurology --- Science (General)
Added to DOAB on : 2016-04-07 11:22:02
License:

Loading...
Export citation

Choose an application

Abstract

Our brain is endowed with an incredible capacity to be social, to trust, to cooperate, to be altruistic, to feel empathy and love. Nevertheless, the biological underpinnings of such behaviors remain partially hardwired. Seminal research in rodents has provided important insights on the identification of specific genes in modulating social behaviors, in particular, the arginine vasopressin receptor and the oxytocin receptor genes. These genes are involved in regulating a wide range of social behaviors, mother-infant interactions, social recognition, aggression and socio-sexual behavior. Remarkably, we now know that these genes contribute to social behavior in a broad range of species from voles to humans. Indeed, advances in human non-invasive neuroimaging techniques and genetics have enabled scientists to begin to elucidate the neurobiological basis of the complexity of human social behaviors using "pharmacological fMRI" and "imaging genetics". Over the past few years, there has been a strong interest focused on the role of oxytocin in modulating human social behaviors with translational relevance for understanding neuropsychiatric disorders, such as autism, schizophrenia and depression, in which deficits in social perception and social recognition are key phenotypes. The convergence of this interdisciplinary research is beginning to reveal the complex nature of oxytocin’s actions. For instance, the way that oxytocin does influence social functioning is highly related to individual differences in social experiences, but also to the inter-individual variability in the receptor distribution of this molecule in the brain. Remarkably, despite the increasing evidence that oxytocin has a key role in regulating human social behavior, we still lack of knowledge on the core mechanisms of action of this molecule. Understanding its fundamental actions is a crucial need in order to target optimal therapeutic strategies for human social disorders. The originality of this Research Topic stands on its translational focus on bridging the gap between fundamental knowledge acquired from oxytocin research in voles and monkeys and recent clinical investigations in humans. For instance, what are the key animal findings that can import further knowledge on the mechanisms of actions of this molecule in humans? What are the key experiences that can be performed in the animal model in order to answer significant science gaps in the treatment of neuropsychiatric disorders? Hence, within this Research Topic, we will review the current state of the field, identify where the gaps in knowledge are, and propose directions for future research. This issue will begin with a comparative review that examines the role of this peptide in diverse animal models, which highlights the adaptive value of oxytocin’s function across multiple species. Then, a series of reviews will examine the role of oxytocin in voles, primates, and humans with an eye toward revealing commonalities in the underlying brain circuits mediating oxytocin’s effects on social behavior. Next, there will be a translational review highlighting the evidence for oxytocin’s role in clinical applications in psychopathology. Hence, via the continuum of basic to translational research areas, we will try to address the important gaps in our understanding of the neurobiological routes of social cognition and the mechanisms of action of the neuropeptides that guide our behaviors and decisions.

Adaptive and Intelligent Temperature Control of Microwave Heating Systems with Multiple Sources

Author:
Book Series: Karlsruher Forschungsberichte aus dem Institut für Hochleistungsimpuls- und Mikrowellentechnik ISSN: 21922764 ISBN: 9783731504672 Year: Volume: 8 Pages: XIII, 231 p. DOI: 10.5445/KSP/1000051503 Language: ENGLISH
Publisher: KIT Scientific Publishing
Subject: Technology (General)
Added to DOAB on : 2019-07-30 20:02:02
License:

Loading...
Export citation

Choose an application

Abstract

In this work, an innovative real-time microwave control approach is proposed, to improve the temperature homogeneity under microwave heating. Multiple adaptive or intelligent control structures have been developed, including the model predictive control, neural network control and reinforcement learning control methods. Experimental results prove that these advanced control methods can effectively reduce the final temperature derivations and improve the temperature homogeneity.

AI based Robot Safe Learning and Control

Authors: --- --- --- --- et al.
ISBN: 9789811555039 Year: Pages: 127 DOI: 10.1007/978-981-15-5503-9 Language: English
Publisher: Springer Nature
Subject: Agriculture (General) --- Computer Science
Added to DOAB on : 2020-06-16 23:57:53
License:

Loading...
Export citation

Choose an application

Abstract

This open access book mainly focuses on the safe control of robot manipulators. The control schemes are mainly developed based on dynamic neural network, which is an important theoretical branch of deep reinforcement learning. In order to enhance the safety performance of robot systems, the control strategies include adaptive tracking control for robots with model uncertainties, compliance control in uncertain environments, obstacle avoidance in dynamic workspace. The idea for this book on solving safe control of robot arms was conceived during the industrial applications and the research discussion in the laboratory. Most of the materials in this book are derived from the authors’ papers published in journals, such as IEEE Transactions on Industrial Electronics, neurocomputing, etc. This book can be used as a reference book for researcher and designer of the robotic systems and AI based controllers, and can also be used as a reference book for senior undergraduate and graduate students in colleges and universities.

Elements of Causal Inference

Authors: --- ---
Book Series: Adaptive Computation and Machine Learning series ISBN: 9780262344296 9780262037310 Year: Pages: 288 Language: English
Publisher: The MIT Press
Subject: Computer Science
Added to DOAB on : 2019-01-17 11:41:31
License:

Loading...
Export citation

Choose an application

Abstract

A concise and self-contained introduction to causal inference, increasingly important in data science and machine learning.The mathematization of causality is a relatively recent development, and has become increasingly important in data science and machine learning. This book offers a self-contained and concise introduction to causal models and how to learn them from data. After explaining the need for causal models and discussing some of the principles underlying causal inference, the book teaches readers how to use causal models: how to compute intervention distributions, how to infer causal models from observational and interventional data, and how causal ideas could be exploited for classical machine learning problems. All of these topics are discussed first in terms of two variables and then in the more general multivariate case. The bivariate case turns out to be a particularly hard problem for causal learning because there are no conditional independences as used by classical methods for solving multivariate cases. The authors consider analyzing statistical asymmetries between cause and effect to be highly instructive, and they report on their decade of intensive research into this problem. The book is accessible to readers with a background in machine learning or statistics, and can be used in graduate courses or as a reference for researchers. The text includes code snippets that can be copied and pasted, exercises, and an appendix with a summary of the most important technical concepts.

Autonomous Control of Unmanned Aerial Vehicles

Author:
ISBN: 9783039210305 9783039210312 Year: Pages: 270 DOI: 10.3390/books978-3-03921-031-2 Language: English
Publisher: MDPI - Multidisciplinary Digital Publishing Institute
Subject: Technology (General) --- General and Civil Engineering
Added to DOAB on : 2019-06-26 08:44:06
License:

Loading...
Export citation

Choose an application

Abstract

Unmanned aerial vehicles (UAVs) are being increasingly used in different applications in both military and civilian domains. These applications include surveillance, reconnaissance, remote sensing, target acquisition, border patrol, infrastructure monitoring, aerial imaging, industrial inspection, and emergency medical aid. Vehicles that can be considered autonomous must be able to make decisions and react to events without direct intervention by humans. Although some UAVs are able to perform increasingly complex autonomous manoeuvres, most UAVs are not fully autonomous; instead, they are mostly operated remotely by humans. To make UAVs fully autonomous, many technological and algorithmic developments are still required. For instance, UAVs will need to improve their sensing of obstacles and subsequent avoidance. This becomes particularly important as autonomous UAVs start to operate in civilian airspaces that are occupied by other aircraft. The aim of this volume is to bring together the work of leading researchers and practitioners in the field of unmanned aerial vehicles with a common interest in their autonomy. The contributions that are part of this volume present key challenges associated with the autonomous control of unmanned aerial vehicles, and propose solution methodologies to address such challenges, analyse the proposed methodologies, and evaluate their performance.

Memristors for Neuromorphic Circuits and Artificial Intelligence Applications

Author:
ISBN: 9783039285761 / 9783039285778 Year: Pages: 244 DOI: 10.3390/books978-3-03928-577-8 Language: eng
Publisher: MDPI - Multidisciplinary Digital Publishing Institute
Subject: Technology (General) --- General and Civil Engineering
Added to DOAB on : 2020-06-09 16:38:57
License:

Loading...
Export citation

Choose an application

Abstract

Artificial Intelligence (AI) has found many applications in the past decade due to the ever increasing computing power. Artificial Neural Networks are inspired in the brain structure and consist in the interconnection of artificial neurons through artificial synapses. Training these systems requires huge amounts of data and, after the network is trained, it can recognize unforeseen data and provide useful information. The so-called Spiking Neural Networks behave similarly to how the brain functions and are very energy efficient. Up to this moment, both spiking and conventional neural networks have been implemented in software programs running on conventional computing units. However, this approach requires high computing power, a large physical space and is energy inefficient. Thus, there is an increasing interest in developing AI tools directly implemented in hardware. The first hardware demonstrations have been based on CMOS circuits for neurons and specific communication protocols for synapses. However, to further increase training speed and energy efficiency while decreasing system size, the combination of CMOS neurons with memristor synapses is being explored. The memristor is a resistor with memory which behaves similarly to biological synapses. This book explores the state-of-the-art of neuromorphic circuits implementing neural networks with memristors for AI applications.

Keywords

memristor --- artificial synapse --- neuromorphic computing --- memristor-CMOS hybrid circuit --- temporal pooling --- sensory and hippocampal responses --- cortical neurons --- hierarchical temporal memory --- neocortex --- memristor-CMOS hybrid circuit --- defect-tolerant spatial pooling --- boost-factor adjustment --- memristor crossbar --- neuromorphic hardware --- memristor --- compact model --- emulator --- neuromorphic --- synapse --- STDP --- pavlov --- neuromorphic systems --- spiking neural networks --- memristors --- spike-timing-dependent plasticity --- RRAM --- vertical RRAM --- neuromorphics --- neural network hardware --- reinforcement learning --- AI --- neuromorphic computing --- multiscale modeling --- memristor --- optimization --- RRAM --- simulation --- memristors --- neuromorphic engineering --- OxRAM --- self-organization maps --- synaptic device --- memristor --- neuromorphic computing --- artificial intelligence --- hardware-based deep learning ICs --- circuit design --- memristor --- RRAM --- variability --- time series modeling --- autocovariance --- graphene oxide --- laser --- memristor --- crossbar array --- neuromorphic computing --- wire resistance --- synaptic weight --- character recognition --- neuromorphic computing --- Flash memories --- memristive devices --- resistive switching --- synaptic plasticity --- artificial neural network --- spiking neural network --- pattern recognition --- strongly correlated oxides --- resistive switching --- neuromorphic computing --- transistor-like devices --- artificial intelligence --- neural networks --- resistive switching --- memristive devices --- deep learning networks --- spiking neural networks --- electronic synapses --- crossbar array --- pattern recognition

Advanced Mobile Robotics: Volume 1

Author:
ISBN: 9783039219162 9783039219179 Year: Pages: 468 DOI: 10.3390/books978-3-03921-917-9 Language: English
Publisher: MDPI - Multidisciplinary Digital Publishing Institute
Subject: General and Civil Engineering --- Technology (General)
Added to DOAB on : 2020-04-07 23:07:09
License:

Loading...
Export citation

Choose an application

Abstract

Mobile robotics is a challenging field with great potential. It covers disciplines including electrical engineering, mechanical engineering, computer science, cognitive science, and social science. It is essential to the design of automated robots, in combination with artificial intelligence, vision, and sensor technologies. Mobile robots are widely used for surveillance, guidance, transportation and entertainment tasks, as well as medical applications. This Special Issue intends to concentrate on recent developments concerning mobile robots and the research surrounding them to enhance studies on the fundamental problems observed in the robots. Various multidisciplinary approaches and integrative contributions including navigation, learning and adaptation, networked system, biologically inspired robots and cognitive methods are welcome contributions to this Special Issue, both from a research and an application perspective.

Keywords

path planning --- lane change --- excellent driver model --- neural networks --- autonomous vehicle --- remotely operated vehicle --- ocean current --- cable disturbance modeling --- lumped parameter method --- sliding mode observer --- 4WS4WD vehicle --- force control --- MPC --- PSO --- path tracking --- negative-buoyancy --- tri-tilt-rotor --- autonomous underwater vehicle (AUV) --- immersion and invariance --- object mapping --- Geometric Algebra --- Differential Evolution --- non-inertial reference frame --- centrifugal force --- turning model LIP --- trajectory planning --- space robot --- hybrid bionic robot --- chameleon --- end effector --- hybrid robot --- curve fitting --- fair optimisation --- trajectory interpolation --- piezoelectric actuator --- high step-up ratio --- high efficiency --- small size --- micro mobile robot --- biomimetic robot --- micro air vehicle --- flapping --- drag-based system --- dragonfly --- snake-like robot --- singularity analysis --- system design --- dynamical model --- nonlinear differentiator --- robotic drilling --- sliding mode control --- drilling end-effector --- fault diagnosis --- quadcopter UAV --- fault-tolerant control --- sliding mode observer --- Thau observer --- smart materials --- actuators --- robots --- electro-rheological fluids --- magneto-rheological fluids --- shape memory alloys --- medical devices --- rehabilitation system --- LOS --- motion camouflage control --- parallel navigation --- missile control system --- target tracking --- variable speed --- high-speed target --- snake robots --- head-raising --- shape-fitting --- phase-shifting --- spiral curve --- servo valve --- pneumatics --- position control --- cart --- robot --- step climbing --- transportation --- stopper --- climbing robot --- safety recovery mechanism --- cable detection --- dynamic coupling analysis --- path planning --- mobile robots --- curvature constraints --- state constraints --- extend procedure --- G3-continuity --- car-like kinematics --- obstacle avoidance system --- harmonic potential field --- curvature constraint --- non-holonomic mobile robot --- computing time --- inverse kinematics --- joint limit avoidance --- kinematic singularity --- manipulator --- obstacle avoidance --- potential field --- service robot --- graph representation --- similarity measure --- mobile robot --- static environments --- path planning --- multi-objective optimization --- NSGA-II --- evolutionary operators --- mobile robot --- coalmine --- exploration --- robotics --- ATEX --- safety --- methane --- quadruped robot --- stability criterion --- dynamic gait --- glass façade cleaning robot --- wall climbing robot --- biped mechanism --- data association --- 3D-SLAM --- localization --- mapping --- disturbance-rejection control --- extended state observer (ESO) --- hover mode --- transition mode --- negative buoyancy --- quad-tilt rotor --- autonomous underwater vehicle (AUV) --- Rodrigues parameters --- UAV --- variable spray --- prescription map translation --- PID algorithm --- grip planning --- biped climbing robots --- collision avoidance --- grip optimization --- dynamic environment --- closed-loop detection --- sparse pose adjustment (SPA) --- inertial measurement unit (IMU) --- simultaneous localization and mapping (SLAM) --- non-singular fast-terminal sliding-mode control --- industrial robotic manipulator --- external disturbance --- dynamic uncertainty --- adaptive control law --- exoskeleton --- load carriage --- muscle activities --- human–robot interaction --- discomfort --- actuatorless --- alpine ski --- human–robot interaction --- mechanism --- passive skiing turn --- skiing robot --- predictable trajectory planning --- geodesic --- constrained motion --- mobile robot --- jumping robot --- hopping robot --- continuous hopping --- single actuator --- self-reconfigurable robot --- cleaning robot --- Tetris-inspired --- polyomino tiling theory --- coverage path planning --- area decomposition --- multi-criteria decision making --- design and modeling --- kinematics --- kinematic identification --- monocular vision --- action generation --- robot motion --- undiscovered sensor values --- differential wheeled robot --- powered exoskeleton --- motion sensor --- machine learning --- unmanned aerial vehicle --- pesticide application --- deposition uniformity --- droplets penetrability --- control efficacy --- working efficiency --- subgoal graphs --- reinforcement learning --- hierarchical path planning --- uncertain environments --- mobile robots --- deep reinforcement learning --- mobile manipulation --- robot learning --- intelligent mobile robot --- pallet transportation --- master-slave --- compact driving unit --- high-gain observer --- snake robot --- series elastic actuator --- SEA --- Robot Operating System --- ROS --- non-prehensile manipulation --- manipulation planning --- contact planning --- manipulation action sequences --- robot --- obstacle avoidance --- facial and gender recognition --- q-learning --- Q-networks --- reinforcement learning --- gait cycle --- biped robots --- minimally invasive surgery robot --- inverse kinematics --- dialytic elimination --- Newton iteration --- curvilinear obstacle --- douglas–peuker polygonal approximation --- opposite angle-based exact cell decomposition --- path planning --- mobile robot --- UAV --- auto-tuning --- machine learning --- iterative learning --- extremum-seeking --- altitude controller --- enemy avoidance --- reinforcement learning --- decision making --- hardware-in-the-loop simulation --- unmanned aerial vehicles --- path planning --- multiple mobile robots --- artificial fish swarm algorithm --- expansion logic strategy --- sample gathering problem --- mobile robots --- mathematical modeling --- numerical evaluation --- centralized architecture --- optimization --- fault recovery --- reinforcement learning --- gait adaptation --- legged robot --- bio-inspired robot --- human–machine interactive navigation --- mobile robot --- topological map --- regional growth --- trajectory planning --- position/force cooperative control --- hierarchical planning --- object-oriented --- symmetrical adaptive variable impedance --- biologically-inspired --- self-learning --- formation control --- mobile robots --- loop closure detection --- convolutional neural network --- spatial pyramid pooling --- dynamic neural networks --- mobile robot navigation --- gesture recognition --- behaviour dynamics --- real-time action recognition --- formation of robots --- non-holonomic robot --- stability analysis --- Lyapunov-like function --- target assignment --- goal exchange --- path following --- switching control --- swarm-robotics --- rendezvous consensus --- robot navigation --- victim-detection --- unmanned surface vessel --- path following --- integral line-of-sight --- finite-time currents observer --- radial basis function neural networks --- input saturation --- n/a

Listing 1 - 10 of 15 << page
of 2
>>
Sort by