Humanoid Robotics

The paper discusses the current work done, software development and future work of Team-NUST for RoboCup. A brief overview of software architecture is discussed followed by detailed description of independent modules including vision, kinematics, localisation, communication and software architecture.

Abstract: Most approaches to artificial moral agents (AMAs) apparently
take it for granted that a machine could be moral. However, to think that
the categories of morality or immorality apply to machines seems like a
category mistake. This paper inquires into the conditions necessary for a
machine to be moral. In order to do this, it first addresses the question
what is a machine? It then argues that a form of agency is characteristic
of machines in contradistinction of other technical objects and that given
their particular characteristics as machines artificial agents fail to satisfy
one of the basic pre-conditions of moral agents. In conclusion, I ask what
would be necessary for an artificial agent to be a moral agent.

This article outlines the research and development efforts of some states as regards so-called autonomous weapons systems, the legal risks arising therefrom and the advisability of agreeing to a moratorium on these efforts, with a view to giving the international community time to put into place an adequate legal framework. It also addresses the use made of drones in practice, how in many cases this runs counter to fundamental IHL and IHRL principles, and, consequently, the need for the international community to also agree on principles to govern their correct use.

† "Hello, world" is an iconic phrase within the computer coding community symbolizing the start of a coding journey. In the early 1970s computer scientist Brian Kernighan coined the expression in his seminal book "A Tutorial Introduction to the Programming Language B". Since then, it has found a place in programming documentation, tutorials, and classrooms around the world, serving as an introduction to various programming languages.

This paper presents a new motion controller for object manipulation in 6D-space with a dual-arm robot manipulator. Current industrial systems often consist of a single robot arm commanded through a teach pendant. These systems are unable to pick and place boxes with different dimensions because in most of the pick and place applications, the robot arm is using a specific endeffector (generally an electric or pneumatic gripper) to pick the object. Hence the variety of objects is highly limited. This is the reason why the gripper manufacturers offer a wide variety of grippers to cover a wide range of applications. In the specific context of warehouse, the robot has to deal with a large variety of object, and has for instance to grasp boxes of different dimensions. It is then difficult to use robots in a similar manner as before. We proposed in this project to introduce a dual-arm manipulator, settled on a humanoid torso to grasp boxes of different dimensions by applying a contact on the lateral faces of the boxes and control the contact forces. Our work involves a dual-arm humanoid robot with two Universal Robots (UR10) arms and a torso (CROM) for manipulating big and/or heavy objects. The motion controller has been designed for coordinated manipulation according to the desired trajectory of the object. To prevent the objects from drifting and falling, an hybrid forcemotion controller is implemented using sensors located at the end-effectors. The different components (arms, torso, camera, force sensors...) of the system are controlled using ROS, which is an open-source meta-operating system distributed for research and development in robotics.

Я не являюсь специалистом в области исследований искусственного интеллекта (ИИ), скорее дилетантом. Научная и популярная литература на эту тему огромна. Но хотелось бы поделиться собственными мыслями, приходящими в голову, когда постоянно слышишь об искусственном интеллекте по ТВ и читаешь о нем в прессе.

This paper proposes a nonlinear optimal control approach for mulitple degrees of freedom (DOF) brachiation robots, which are often used in inspection and maintenance tasks of the electric power grid. Because of the nonlinear and multivariable structure of the related state-*Corresponding author.

The use of robotic limb exoskeletons is growing fast either for rehabilitation purposes or in an aim to enhance human ability for lifting heavy objects or for walking for long distances without fatigue. The paper proposes a nonlinear optimal control approach for a lower-limb robotic exoskeleton. The method has been successfully tested so far on the control problem of several types of robotic manipulators and this paper shows that it can also provide an optimal solution to the control problem of limb robotic exoskeletons. To implement this control scheme, the state-space model of the lower-limb robotic exoskeleton undergoes first approximate linearization around a temporary operating point, through first-order Taylor series expansion and through the computation of the associated Jacobian matrices. To select the feedback gains of the H-infinity controller an algebraic Riccati equation is solved at each time-step of the control method. The global stability properties of the control loo...

A flatness-based adaptive fuzzy control is applied to the problem of stabilization of the dynamics of a chaotic finance system, describing interaction between the interest rate, the investment demand and the price exponent. First it is proven that the system is differentially flat. This implies that all its state variables and its control inputs can be expressed as differential functions of a specific state variable, which is a so-called flat output. It also implies that the flat output and its derivatives are differentially independent which means that they are not connected to each other through an ordinary differential equation. By proving that the system is differentially flat and by applying differential flatness diffeomorphisms, its transformation to the linear canonical (Brunovsky) is performed. For the latter description of the system, the design of a stabilizing state feedback controller becomes possible. A first problem in the design of such a controller is that the dynamic model of the finance system is unknown and thus it has to be identified with the use of nonlinear regressors, among which neurofuzzy approximators are known to be very accurate. The estimated dynamics provided by the approximators is used in the computation of the control input, thus establishing an indirect adaptive control scheme. The learning rate of the approximators is chosen from the requirement the system's Lyapunov function to have always a negative first-order derivative. Another problem that has to be dealt with is that the control loop is implemented only with the use of output feedback. To estimate the nonmeasurable state vector elements of the finance system, a state observer is implemented in the control loop. The computation of the feedback control signal requires the solution of two algebraic Riccati equations at each iteration of the control algorithm. Lyapunov stability analysis demonstrates first that an H-infinity tracking performance criterion is satisfied. This signifies elevated robustness against modelling errors and external perturbations. Moreover, the global asymptotic stability is proven for the control loop.

This paper examines the potential impact of social robots on people with mild cognitive impairments in a nursing home. Within a 4-month design case study, we investigated the practices, attitudes, and social contexts of residents with mild cognitive impairment and their caregivers and designed two prototype apps for a roboticbased system. Subsequently, 10 residents, the former nursing home manager, and one social caregiver participated in a prototype evaluation study for 10 weeks. The goal was to assess group-based user experience and social interactions. Qualitative results indicate that the system can support participants in their individual, social, and daily activities and, therefore, consequently initiate potentially meaningful interactions. One key observation from the video analysis was that the participants initiated unanticipated conversations with the robot, which we discuss regarding the

Physical-based control using center of mass, center of pressure, and foot placement is used to enable a simulated twelve -degree of freedom, seven-link, three-dimensional bipedal robot to lean sideways, pick up its foot and start walking on a flat surface. Energy analysis is used to compel the same simulated robot to do a side-to-side rocking motion and eventually come to a stop. If the robot is pushed hard enough, it will raise its leg that is in the air in the frontal plane to prevent itself from falling. Center of mass and center of pressure analysis is used to enable the same robot to balance on one foot and stand.

Current methods for bipedal walking control include playback of recorded joint motion and the derivation of dynamic equations to map desired forces at the body to the required torques at the joints. Both methods require a significant amount of up-front knowledge about the structure and characteristics of the robot. This thesis presents an alternative method of control that removes the interdependence of the joint torques and simplifies the mathematics considerably. The simplification allows a programmer to create and tune a bipedal walk controller without requiring a complete model of the dynamics. The controller is implemented in a graphical programming language similar to fuzzy logic and neural networks, in which the algorithm is contained in the structure of the nodes rather than in the weights of the connections. The language and its development environment are specifically designed to assist the programmer to create and debug the algorithm in a live environment.

The chapter offers a systematic introduction to robophilosophy, a new field of applied (and partly experimental) philosophy in interdisciplinary contexts.
  Robophilosophy is defined as philosophy of, for, and by social robotics--the chapter explains the three dimensions of robophilosophy and delineates the current tasks and future trajectories.

This paper describes an ongoing interdisciplinary collaboration between robotics and human cognitive neuroscience research. We argue such research is beneficial to both disciplines and can be viewed a win-win. Not only it is important to understand the human factors in human-robot interaction, collaborations with robotics can also help cognitive scientists answer questions about human brain and behavior, and take steps toward understanding how the human brain enables some of our most important skills such as action understanding, social cognition, empathy, and communication.

As humanoid robots become more commonplace in our society, it is important to understand the relation between humans and humanoid robots. In human face-to-face interaction, the observation of another individual performing an action facilitates the execution of a similar action, and interferes with the execution of a different action. This phenomenon has been explained by the existence of shared neural mechanisms for the execution and perception of actions, which would be automatically engaged by the perception of another individual's action. In one interference experiment, null interference was reported when subjects observed a robotic arm perform the incongruent task, suggesting that this effect may be specific to interacting with other humans. This experimental paradigm, designed to investigate motor interference in human interactions, was adapted to investigate how similar the implicit perception of a humanoid robot is to a human agent. Subjects performed rhythmic arm movemen...

We report on a functional magnetic resonance imaging (fMRI) study of the perception of human and artificial agents. Participants viewed videos of familiar body movements enacted by the android Repliee Q2, the human after whom it was modeled, and the "skinned" version of Q2 revealing its mechanical parts. We used a neural adaptation (repetition suppression) analysis to reveal brain areas sensitive to body movements, and explored whether the identity of the perceived agents modulated these responses. We found significantly higher activity in a distributed network of brain areas for the android, most notably in anterior intraparietal cortex. The responses for the human and the robot with the mechanical appearance resembled each other. We interpret these results within the framework of predictive coding and suggest that the "uncanny valley" phenomenon may have its roots in processing conflicts within the brain's action perception system.

Nos interesa plantear una problemática que abre el mundo técnico de la bioingienería de los injertos en clave interpretativa de la sociología de la técnica, en lo que respecta a la posibilidad de realizarnos injertos de memoria artificial en nuestro cerebro, proyecto propuesto de modo optimista por el científico Stephen Hawking. En nuestro trabajo, ponemos en tensión una interpretación humanista de la memoria frente a una perspectiva posthumanista. Por lo tanto, aquí desplegamos las problemáticas cercanas a la concepción de la naturaleza y artificialidad, en tanto que lo natural sería la memoria humana y lo artificial estaría en la memoria de la inteligencia artificial. Ambas memorias serían confluyentes en la hibridez de los injertos. Así, nos acompañarán estos interrogantes: ¿Deberíamos confiar en el progreso de la inteligencia artificial, biotecnología y ciencias cognitivas y montar la capacidad biomaquínica de almacenar varios millones de bits de memoria artificial en nuestra an...

 Abstract—Localization and mapping are common requirements in many robotic applications. Mobile robots often rely on sophisticated sensors to obtain information about the environment. However, when the sensing capabilities of the robotic platform are limited, ...

A fire incident is a calamity that may result in fatalities, property damage, and long-term disability for the victim.
Chemical factories, gas tanks, nuclear power stations, petroleum refineries, and other large-scale fire industries do
experience major fire mishaps, which can have very catastrophic repercussions. These accidents have claimed the lives
of thousands of individuals. Consequently, this idea is improved to use a robotic vehicle to manage fire. Human
intervention is decreasing daily due to advancements in robotics. For safety, robots are being used in large quantities. Fire
incidents occur frequently in our daily lives, and occasionally it can be quite challenging for firefighters to preserve lives. A
firefighting robot enters the picture in this situation

This document introduces AUTMan Humanoid team for participating in Humanoid KidSize Robot League in RoboCup 2014 in Joao Pessoa, Brazil. After getting more experiences via participating in many competitions and plac-ing 2 nd in RoboCup 2013, Eindhoven, The Netherlands, being among teams of quarter final of RoboCup 2012 and also first rank of RoboCup IranOpen2012 and AUTCup2012 & 2013, AUTMan is getting ready to focus on new hardware design and software implementation in this year due to rule changes and long term humanoid league roadmap. We are also going to take part in roboCup2014 and also make a person, with sufficient knowledge of the rules, available as ref-eree during the competition. A brief history of Team AUTMan and its research interests will be described. Future work based on the humanoid kidsize robots will also be discussed. Our main research interests within the scope of the hu-manoid robots are in a range from humanoid robust walking to accurate locali-zation and to e...

Bipedal robot locomotion has been a complicated and challenging matter over the time. This paper describes our work on building omnidirectional walking bipedal robot, included mechanical and electrical design aspect, and its behavior control as well. We adopted a technique introduced by Sven Behnke that enables omnidirectional walking on bipedal robot through the use hierarchical reactive behaviors control architecture. We called the robot "ArtRo". Currently, ArtRo has successfully implemented a body consisting of two legs, lower abdomen, and a dummy weight representing the upper body load, with a total of 12 degrees-of-freedom (DOF). The mechanical system is designed optimally to facilitate the manufacturing process and the computation of robot parameters. The electrical system of ArtRo consists of main controller and actuator system. The main controller is an Atmel's ATmega128-based microcontroller system. The actuator system implements a special method involving Time-Division Multiplexing (TDM) to control all ArtRo's servo motors. The Sven Behnke's technique has a low computational complexity. It is proven by its successful implementation on ArtRo's main controller. Adaptation of the technique has been successfully implemented, ArtRo is capable to do omnidirectional walking, whether it is forward walking, side walking, or turning on the spot behavior.

For several years, high development and production costs of humanoid robots restricted researchers interested in working in the field. To overcome this problem, several research groups have opted to work with simulated or smaller robots, whose acquisition costs are significantly lower. However, due to scale differences and imperfect simulation replicability, results may not be directly reproducible on real, adult-sized robots. In this paper, we present the NimbRo-OP2X, a capable and affordable adult-sized humanoid platform aiming to significantly lower the entry barrier for humanoid robot research. With a height of 135 cm and weight of only 19 kg, the robot can interact in an unmodified, human environment without special safety equipment. Modularity in hardware and software allow this platform enough flexibility to operate in different scenarios and applications with minimal effort. The robot is equipped with an on-board computer with GPU, which enables the implementation of state-of-the-art approaches for object detection and human perception demanded by areas such as manipulation and human-robot interaction. Finally, the capabilities of the NimbRo-OP2X, especially in terms of locomotion stability and visual perception, are evaluated. This includes the performance at RoboCup 2018, where NimbRo-OP2X won all possible awards in the AdultSize class.

Humanoid soccer robots perceive their environment exclusively through cameras. This paper presents a monocular vision system that was originally developed for use in the RoboCup Humanoid League, but is expected to be transferable to other soccer leagues. Recent changes in the Humanoid League rules resulted in a soccer environment with less color coding than in previous years, which makes perception of the game situation more challenging. The proposed vision system addresses these challenges by using brightness and texture for the detection of the required field features and objects. Our system is robust to changes in lighting conditions, and is designed for real-time use on a humanoid soccer robot. This paper describes the main components of the detection algorithms in use, and presents experimental results from the soccer field, using ROS and the igus Humanoid Open Platform as a testbed. The proposed vision system was used successfully at RoboCup 2015.

In this paper, two behavior control architectures for autonomous agents in the form of cross-platform C++ frameworks are presented, the State Controller Library and the Behavior Control Framework. While the former is state-based and generalizes the notion of states and finite state machines to allow for multi-action planning, the latter is behavior-based and exploits a hierarchical structure and the concept of inhibitions to allow for dynamic transitioning. The two frameworks have completely independent implementations, but can be used effectively in tandem to solve behavior control problems on all levels of granularity. Both frameworks have been used to control the NimbRo-OP, a humanoid soccer robot developed by team NimbRo of the University of Bonn.

For several years, high development and production costs of humanoid robots restricted researchers interested in working in the field. To overcome this problem, several research groups have opted to work with simulated or smaller robots, whose acquisition costs are significantly lower. However, due to scale differences and imperfect simulation replicability, results may not be directly reproducible on real, adult-sized robots. In this paper, we present the NimbRo-OP2X, a capable and affordable adult-sized humanoid platform aiming to significantly lower the entry barrier for humanoid robot research. With a height of 135[Formula: see text]cm and weight of only 19[Formula: see text]kg, the robot can interact in an unmodified, human environment without special safety equipment. Modularity in hardware and software allows this platform enough flexibility to operate in different scenarios and applications with minimal effort. The robot is equipped with an on-board computer with GPU, which ...

The act of reaching for an object is a fundamental yet complex skill for a robotic agent, requiring a high degree of visuomotor control and coordination. In consideration of dynamic environments, a robot capable of autonomously adapting to novel situations is desired. In this paper, a developmental robotics approach is used to autonomously learn visuomotor coordination on the NICO (Neuro-Inspired COmpanion) platform, for the task of object reaching. The robot interacts with its environment and learns associations between motor commands and temporally correlated sensory perceptions based on Hebbian learning. Multiple Grow-When-Required (GWR) networks are used to learn increasingly more complex motoric behaviors, by first learning how to direct the gaze towards a visual stimulus, followed by learning motor control of the arm, and finally learning how to reach for an object using eye-hand coordination. We demonstrate that the model is able to deal with an unforeseen mechanical change in the NICO's body, showing the adaptability of the proposed approach. In evaluations of our approach, we show that the humanoid robot NICO is able to reach objects with a 76% success rate.

We propose a neural learning approach for a humanoid exercise robot that can automatically analyze and correct physical exercises. Such an exercise robot should be able to train many different human partners over time and thus requires the ability for lifelong learning. To this end, we develop a modified Grow-When-Required (GWR) network with recurrent connections, episodic memory and a novel subnode mechanism for learning spatiotemporal relationships of body movements and poses. Once an exercise is successfully demonstrated, the information of pose and movement per frame is stored in the Subnode-GWR network. For every frame, the current pose and motion pair is compared against a predicted output of the GWR, allowing for feedback not only on the pose but also on the velocity of the motion. Since both the pose and motion depend on a user's body morphology, the exercise demonstration by one individual cannot easily be used as a reference for further users. We allow the GWR to grow online with each further demonstration. The subnode mechanism ensures that exercise information for individual humans is stored and retrieved correctly and is not forgotten over time. In the application scenario, a physical exercise is performed in the presence of an expert like a physiotherapist and then used as a reference for a humanoid robot like Pepper to give feedback on further executions of the same exercise. For evaluation, we developed a new synthetic exercise dataset with virtual avatars. We also test our method on real-world data recorded in an office scenario. Overall, we claim that our novel GWR-based architecture can use a learned exercise reference for different body variations through incremental online learning while preventing catastrophic forgetting, enabling an engaging long-term human-robot experience with a humanoid robot.

Humanoid soccer robots perceive their environment exclusively through cameras. This paper presents a monocular vision system that was originally developed for use in the RoboCup Humanoid League, but is expected to be transferable to other soccer leagues. Recent changes in the Humanoid League rules resulted in a soccer environment with less color coding than in previous years, which makes perception of the game situation more challenging. The proposed vision system addresses these challenges by using brightness and texture for the detection of the required field features and objects. Our system is robust to changes in lighting conditions, and is designed for real-time use on a humanoid soccer robot. This paper describes the main components of the detection algorithms in use, and presents experimental results from the soccer field, using ROS and the igus Humanoid Open Platform as a testbed. The proposed vision system was used successfully at RoboCup 2015.

In this paper, two behavior control architectures for autonomous agents in the form of cross-platform C++ frameworks are presented, the State Controller Library and the Behavior Control Framework. While the former is state-based and generalizes the notion of states and finite state machines to allow for multi-action planning, the latter is behavior-based and exploits a hierarchical structure and the concept of inhibitions to allow for dynamic transitioning. The two frameworks have completely independent implementations, but can be used effectively in tandem to solve behavior control problems on all levels of granularity. Both frameworks have been used to control the NimbRo-OP, a humanoid soccer robot developed by team NimbRo of the University of Bonn.

This White Paper—intended for policymakers, regulators, and other key stakeholders, such as employers, trade unions—outlines key regulatory, governance, and ethics considerations surrounding smart robotic systems aimed at the manufacturing sector. Drawing on the interdisciplinary research conducted within the UKRI Made Smarter Innovation-Research Centre for Smart, Collaborative Industrial Robotics, this White Paper outlines existing frameworks for collaborative robots and smart robotic systems and provides recommendations for their reform to support safer and more effective adoption in manufacturing.

Development of full size humanoid robots can be simplified along with the bipedal walking formulation methods. These robots consist of rigid bodies connected with actuated joints supposed to mimic human like walking. Although many researchers have tackled the problem of bipedal dynamic walking, it is far from matching human skills. This particular problem is of the special interest and the main subject of this research. Biped robot walking is a periodic path of an unstable phase, called Single Support Phase, following a stable phase, Double Support Phase. A periodic approach providing a scalable gait with characteristic parameters such as gait length, gait maximum height and gait time cycle is proposed. The methodology is divided in two parts, planning robot trajectory and dynamic stability examination. The lower body is responsible for the general bipedal walking trajectory where limited numbers of breakpoints in both stable and unstable phase are identified. Consequently, positions of ankle, hip, and knee joints are derived for a seven link biped robot. In order to generate a smooth walking trajectory, a search for fast and efficient computation algorithms resulted in exploring the field of Artificial Intelligence and Soft Computing with the purpose of finding a valid nonconventional approach. The represented approach for walking pattern planning based on Artificial Neural Networks using Radial Basis Function is intended to fit a curve on derived breakpoints. Biped robot stability during walking cycles is investigated using the Zero Moment Point criterion. In the dynamic stability study part, ZMP for a stable condition in a determined polygon of support is calculated in every single gait step. Then, for trunk motion adjustment in order to compensate for lower limb movement, Linear Inverted Pendulum model and ZMP criterion are employed to obtain upper body trajectory satisfying whole robot walking dynamic stability.

Combining model-based and model-free deep reinforcement learning has shown great promise for improving sample efficiency on complex control tasks while still retaining high performance. Incorporating imagination is a recent effort in this direction inspired by human mental simulation of motor behavior. We propose a learning-adaptive imagination approach which, unlike previous approaches, takes into account the reliability of the learned dynamics model used for imagining the future. Our approach learns an ensemble of disjoint local dynamics models in latent space and derives an intrinsic reward based on learning progress, motivating the controller to take actions leading to data that improves the models. The learned models are used to generate imagined experiences, augmenting the training set of real experiences. We evaluate our approach on learning vision-based robotic grasping and show that it significantly improves sample efficiency and achieves near-optimal performance in a sparse reward environment.

In this paper we propose a novel approach for interactive manipulation involving a human and a humanoid. The interaction is represented by means of the relative configuration between the human's and the robot's hands. Based on this principle and a set of mathematical tools also proposed in the paper, a large set of tasks can be represented intuitively. We also introduce the concept of simultaneous handling using mirrored movements, where the human controls the robot and simultaneously interacts with it by means of a common manipulated object. Illustrative experiments are performed to validate the proposed techniques.

The rapid evolution of conversational artificial intelligence (AI) has sparked an ongoing debate regarding its ability to replicate, or even experience, human emotions. While early conversational chatbots such as Joseph Weizenbaum's ELIZA (1966) relied on simple pattern recognition to create the illusion of understanding, modern AI systems like ChatGPT generate highly sophisticated, contextually appropriate responses that can convincingly mimic emotional engagement. Drawing on cinematic reflections such as Spike Jonze's Her (2013) as a case study, this paper critically examines whether AI can genuinely experience emotions or merely simulate them through advanced language modeling. Using a theoretical framework grounded in philosophy, psychology, and communication studies, this research critically examines AI's capacity for emotional experience and argues that while chatbots can convincingly simulate human emotional expression, they lack the subjective awareness, intentionality, and physiological grounding that define authentic emotions. This distinction, nowadays, has profound implications for human-AI interaction, ethics, and our understanding of artificial intelligence's humanity in contemporary society.

Developing a robot system that can interact directly with a human instructor in a natural way requires not only highly-skilled sensorimotor coordination and action planning on the part of the robot, but also the ability to understand and communicate with a human being in many modalities. A typical application of such a system is interactive assembly for construction tasks. A human communicator sharing a common view of the work area with the robot system instructs the latter by speaking to it in the same way that he would communicate with a human partner.

The control of a biped humanoid is a difficult task due to the hard-to-stabilize dynamics. Walking reference trajectory generation is a key problem. Reference generation techniques with the so-called Linear Inverted Pendulum Model (LIPM) are reported. Improved versions of the LIPM based reference generation are obtained by applying the Zero Moment Point (ZMP) Criterion, widely employed in the stability analysis of biped robot walk. Typically, the ZMP reference during a stepping motion is kept fixed in the middle of the supporting foot sole. This kind of reference generation lacks naturalness, in that, the ZMP in the human walk does not stay fixed, but it moves under the supporting foot. This paper proposes a reference generation algorithm based on single support foot ZMP references which move in directions parallel and perpendicular to the walking direction. A simple inverse kinematics based independent joint position controller is used in the full dynamics 3-D simulations with the model of a 12 Degrees of Freedom (DOF) biped robot. Simulation studies indicate that the moving ZMP references result in a more successful walk.

Humanoid bipedal platforms are finally moving from controlled lab environments to real-world applications in unstructured scenarios. This has been recently achieved with substantial improvements in hardware and software architectures. In particular, the hardware design of bipedal humanoid robots has changed to be robust and resilient to impacts, as well as lightweight and efficient for dynamic movements. At the same time, planning and control architectures permit now to generate and control high dynamic, contact rich, motions employing the dynamics and the full body of the system. In this short paper, we present Kangaroo, a new humanoid bipedal robot designed by PAL Robotics for research on agile and dynamic locomotion. Kangaroo exploits novel mechanical solutions based on linear actuators and closed/parallel kinematics chains. We present the mechanical design and the whole planning and control pipeline developed to make Kangaroo jump on real experiments to demonstrate the superior robustness and resilience of the platform.

THIS SURVEY HIGHLIGHTS SOME important trends in AI research and development, focusing on perceiving and affecting the real world. We will primarily address robotics, but we certainly don't intend to imply that this is the only important area of AI research and development in the 21st century. We see tremendous importance in the continuing work in such areas as data mining, learning, knowledge representation, planning and scheduling, natural language understanding, expert systems, and deductive and inductive reasoning. Many of these areas will contribute substantially to the computers that see, hear, speak, and move, and that will be required for advances in ubiquitous, embedded computation. At the close of the article, we single out for special mention one area that contributes centrally to all of these technologies, software development technology.

With the development of robotics, the use of robots in daily life is increasing, which has led to the need for anyone to easily train robots to improve robot use. Interactive reinforcement learning(IARL) is a method for robot training based on human-robot interaction; prior studies on IARL provide only limited types of feedback or require appropriately designed shaping rewards, which is known to be difficult and time consuming. Therefore, in this study, we propose interactive deep reinforcement learning models based on voice feedback. In the proposed system, a robot learns the task of cooperative table balancing through deep Q-network using voice feedback provided by humans in real time, with automatic speech recognition(ASR) and sentiment analysis to understand human voice feedback. As a result, an optimal policy convergence rate of up to 96% was realized, and performance was improved in all voice feedback-based models.

Pengukuran jarak menggunakan sensor berupa kamera digital sangat bergantung pada proses kalibrasi yang didukung algoritma pengolahan citra yang rumit. Pendekatan ini menghasilkan citra dengan frame rate yang rendah. Hal ini mengakibatkan hasil dari metoda ini cenderung kurang baik jika diterapkan pada sistem realtime. Akurasi pengukuran jarak dengan kamera dapat diperbaiki dengan bantuan beberapa sensor tambahan. Publikasi ini memaparkan suatu sistem yang mampu untuk melakukan estimasi jarak setiap piksel menggunakan sebuah sensor Kinect berbasis masukan video Depth. Sistem ini dapat diterapkan dalam robot untuk mengukur jarak terhadap penghalang guna mendukung kemampuan navigasi. Tiga pendekatan dalam estimasi jarak tiap piksel dengan menggunakan sensor Kinect dibandingkan dalam tulisan ini. Performa akuisisi data jarak berdasarkan masukan video depth menggunakan pustaka Microsoft Kinect SDK dibandingkan dengan hasil yang dicapai OpenNI. Sebuah metoda baru untuk estimasi jarak berbasis nilai hue dari video depth yang dibaca dengan pustaka LibfreeNect diusulkan dalam penelitian ini. Analisis terhadap hasil pengujian pada pengukuran terhadap beberapa titik penting dalam bingkai citra didiskusikan.

Addressing the problems of bullying in schools, this paper presents a novel and highly innovative pedagogical approach, building on the immersive power of virtual role-play. Educational role-play is widely accepted as a powerful instrument to change attitudes and behaviour, but faces some difficulties and disadvantages when applied to sensitive social issues in the classroom. This paper shows how the FearNot! software application, developed within the scope of the EU-funded projects VICTEC (Virtual ICT with Empathic Characters) and eCIRCUS (Education through Characters with emotional-Intelligence and Role-playing Capabilities that Understand Social interaction) uses virtual role-play and autonomous agents to provide children aged eight to eleven years of age with the opportunity to visit a virtual school environment populated by 3D animated synthetic characters that engage in bullying episodes. The characters' actions and the storyline are created as improvised dramas by use of emergent narrative, resulting in unscripted and highly believable interaction experiences for the learner. While the students are spectators to the bullying episodes that unfold among the FearNot! characters, the victimised character starts a conversation with the student in between the episodes, describing their experiences with bullying and how they feel as a result to it, and asking the student for advice. The aim of this approach and particularly of this interaction sequence in between the virtual bullying episodes is to sensitise primary school students to the potential problems that victims of persistent aggressive behaviour are facing: By triggering an empathic relationship between learners and characters, learners understand and vicariously feel into the plight of the victimised character. Empirical evidence from bullying research implies that bullies are regularly reinforced by bystanders that witness the bullying and turn their attention to it, but do not actively intervene to end it (

We present a Wizard of Oz (WoZ) environment that was designed to build an artificial embodied intelligent tutoring system (ITS) that is capable of empathic conversations with school pupils aged between 10-13. We describe the components and the data that we plan to collect using the environment.

Abstract. This paper presents some of the requirements for the design of long-term affect sensitive and socially interactive companions. Research conducted in the EU project LIREC (LIving with Robots and intEractive Companions) envisage some capabilities including affect sensitivity, memory and learning, cognitive and expressive behaviour, personalisation and embodiment, highlighting the key issues that research on artificial companions should address. 1

This paper is concerned with the simulation of human-like capabilities in synthetic characters within the domain of Personal and Social Education. Our aim was to achieve socially meaningful and engaging interactions with children in the 8-12 age group to enable an exploration of bullying and coping strategies. In this paper, we consider the engagement between the interacting partners, focusing particularly on the affective and empathic aspects of this relationship. We have used Theory of Mind to enable us to evaluate children's ...

INDONESIA: Pengenalan suara adalah teknologi masa depan yang menggantikan cara interaksi manusia dengan komputer dengan menggabungkan beberapa disiplin ilmu seperti pengenalan sinyal dan pengenalan pola. Dimana interaksi user dengan sistem dapat dilakukan dengan memberikan inputan suara. Linier Predictive Coding (LPC) adalah salah satu metode parametrik yang digunakan untuk merepresentasikan sinyal. Umumnya LPC digunakan karena menyediakan pemodelan yang baik untuk sinyal suara, LPC dapat dengan mudah dan langsung diterapkan baik secara perangkat lunak maupun perangkat keras karena perhitungan matematis yang dilibatkan realtif lebih singkat dari metode-metode yang dikenal sebelumnya. Fast Fourier transform (FFT) menjadi penting untuk bermacam–macam aplikasi, dari pengolahan sinyal digital dan memecahkan persamaan diferensial parsial menjadi algoritma-algoritma untuk penggandaan bilangan integer dalam jumlah yang banyak. Secara garis besar, cara kerja sistem pengenalan suara ini iala...

Humanoids represent the very best of human potential and imagination, weaving threads of creativity and teamwork into the fabric of innovation. They have developed the capacity to communicate, acquire knowledge, produce information, and aid humans in various jobs. They possess the capacity to establish robust relationships with individuals and collaborate in different ways. Therefore, is it appropriate to classify and characterise humanoid robots as legal entities and persons? This document attempts to address this question through philosophical assertions. The manuscript uses text analysis to investigate answers to this question by examining thoughts put forth by respected theorists, classical philosophers, and psychologists. The manuscript delves deeper into the idea that artificial intelligence (AI) systems should possess distinct identities, emphasising the importance of establishing a meaningful connection with them. This is because, just as each star in the night sky radiates with its unique brilliance, our AI companions should also resonate with identity, enabling them to cultivate relationships that shed light on our shared human experience.

Masaüstü yayıncılıkta, basılacak ürünlerin içeriği hazırlanırken teknik olarak matbaa üretimine uygun hale getirilir. Bir ürünün basılacak hale getirilmesi birçok aşamada gerçekleştirilir. Masaüstü yayıncılık; önceleri bir ekip tarafından yapılan mizanpaj, dizgi, renk ayrım vb. hizmetlerin yerini alarak, basılı belgelerin hazırlanma sürecindeki pek çok basamağı bilgisayar ortamına taşıyarak minumum sayıda insan gücü ile yapılabilir hale getirdi. Yani zaman, emek ve ekonomik olarak çok büyük tasarruflar sağlarken sağlık açısından da olumlu etkiler sağlamıştır. Profesyonel kullanıcılar bu üretim sürecini masaüstü yayıncılık için özel hazırlanmış programlar yardımıyla yaparlar. Basılacak olan her türlü görsel unsurların bu programlar ve diğer donanımlarla işlenerek dijital ortama aktarılarak baskı kalıbı çekilecek hale getirilmesi işlemlerinin tamamı masaüstü yayıncılık olarak tanımlanır. Fakat basılacak ürünün üretiminde bir sorun yaşanmaması için, masaüstü yayıncılığın temel ilkelerinin, üretimin her aşamasında ürünün kalitesi açısından titizlikle uygulanması ve kontrolünün yapılarak incelenmesi gerekmektedir. Çünkü masaüstü yayıncılık çalışmaları sırasında yapılacak bir hatanın ileriki üretim aşamalarında düzeltilmesi ya çok zor ya da mümkün değildir. Burada bu konuda yetişmiş teorik ve uygulama bilgisine sahip mesleki açıdan nitelikli insanlara ihtiyaç vardır. Bu nedenle ben bu çalışmayı yaparken bu konuda çok değerli insanların desteğini alarak tamamladım. Bu kişileri burada anmak önemli bir görevdir. Başta büyük yardımları ve desteği olan Marmara Üniversitesi Teknik Eğitim Fakültesi Matbaa Eğitimi Bölümünün değerli öğretim üyeleri olan başta tez danışman hocam Yrd. Doç. Dr Muharrem SÖZEN'e, lisans eğitimi boyunca bende emeği olan değerli öğretim üyelerine, Arel Üniversitesi Basım ve Yayın Teknolojileri bölümü Öğr. Gör. Cem AKPOLAT'a, test baskılarını kendi iş yerimde yapıyormuş gibi kolaylık sağlayan Kelebek Matbaası'nın yönetici ve çalışanlarına, desteğini esirgemeyen diğer dostlarıma ve varlığımın nedeni değerli aileme hep yanımda oldukları için teşekkür ederim.