174 results found
Khadhouri B, Demiris Y, 2005, Compound effects of top-down and bottom-up influences on visual attention during action recognition, International Joint Conference on Artificial Intelligence (IJCAI), Publisher: International Joint Conferences on Artificial Intelligence, Pages: 1458-1463
The limited visual and computational resources available during the perception of a human action makes a visual attention mechanism essential. In this paper we propose an attention mechanism that combines the saliency of top-down (or goal-directed) elements, based on multiple hypotheses about the demonstrated action, with the saliency of bottom-up (or stimulus-driven) components. Furthermore, we use the bottom-up part to initialise the top-down, hence resulting in a selection of the behaviours that rightly require the limited computational resources. This attention mechanism is then combined with an action understanding model and implemented on a robot, where we examine its performance during the observation of object-directed human actions.
Khadhouri B, Demiris Y, 2005, Attention shifts during action sequence recognition for social robots, New York, 12th international conference on advanced robotics, 17 - 20 July 2005, Seattle, WA, Publisher: Ieee, Pages: 468-475
Simmons G, Demiris Y, 2005, Optimal robot arm control using the minimum variance model, Journal of Robotic Systems, Vol: 22, Pages: 677-690, ISSN: 0741-2223
Models of human movement from computational neuroscience provide a starting point for building a system that can produce flexible adaptive movement on a robot. There have been many computational models of human upper limb movement put forward, each attempting to explain one or more of the stereotypical features that characterize such movements. While these models successfully capture some of the features of human movement, they often lack a compelling biological basis for the criteria they choose to optimize. One that does provide such a basis is the minimum variance model (and its extension—task optimization in the presence of signal-dependent noise). Here, the variance of the hand position at the end of a movement is minimized, given that the control signals on the arm's actuators are subject to random noise with zero mean and variance proportional to the amplitude of the signal. Since large control signals, required to move fast, would have higher amplitude noise, the speed-accuracy trade-off emerges as a direct result of the optimization process. We chose to implement a version of this model that would be suitable for the control of a robot arm, using an optimal control scheme based on the discrete-time linear quadratic regulator. This implementation allowed us to examine the applicability of the minimum variance model to producing humanlike movement. In this paper, we describe our implementation of the minimum variance model, both for point-to-point reaching movements and for more complex trajectories involving via points. We also evaluate its performance in producing humanlike movement and show its advantages over other optimization based models (the well-known minimum jerk and minimum torque-change models) for the control of a robot arm.
Veskos P, Demiris Y, 2005, Robot Swinging Using van der Pol Nonlinear Oscillators, International Symposium on Adaptive Motion of Animals and Machines
In this study, we investigated the use of van der Pol oscillators in a 2-dof embodied robotic platform for a swinging task. The oscillator controlled the hip and knee joints of the robot and was capable of generating waveforms with the correct frequency and phase so as to entrain with the mechanical system.
Veskos P, Demiris Y, 2005, Developmental acquisition of entrainment skills in robot swinging using van der Pol oscillators, International Workshop On Epigenetic Robotics, Pages: 87-93
In this study we investigated the effects of different morphological configurations on a robot swinging task using van der Pol oscillators. The task was examined using two separate degrees of freedom (DoF), both in the presence and absence of neural entrainment. Neural entrainment stabilises the system, reduces time-to-steady state and relaxes the requirement for a strong coupling with the environment in order to achieve mechanical entrainment. It was found that staged release of the distal DoF does not have any benefits over using both DoF from the onset of the experimentation. On the contrary, it is less efficient, both with respect to the time needed to reach a stable oscillatory regime and the maximum amplitude it can achieve. The same neural architecture is successful in achieving neuromechanical entrainment for a robotic walking task.
Johnson M, Demiris Y, 2004, Abstraction in Recognition to Solve the Correspondence Problem for Robot Imitation, Towards Autonomous Robotic Systems, TAROS 2004, Pages: 63-70
A considerable part of the imitation problem is finding mechanisms that link the recognition of actions that are being demonstrated to the execution of the same actions by the imitator. In a situation where a human is instructing a robot, the problem is made more complicated by the difference in morphology. In this paper we present an imitation framework that allows a robot to recognise and imitate object-directed actions performed by a human demonstrator by solving the correspondence problem. The recognition is achieved using an abstraction mechanism that focuses on the features of the demonstration that are important to the imitator. The abstraction mechanism is applied to experimental scenarios in which a robot imitates human- demonstrated tasks of transporting objects be- tween tables.
Simmons G, Demiris Y, 2004, Imitation of human demonstration using a biologically inspired modular optimal control scheme, New York, IEEE/RAS International Conference on Humanoid Robots, Publisher: IEEE, Pages: 215-234
Download Citation Email Print Request Permissions Save to ProjectProgress in the field of humanoid robotics and the need to find simpler ways to program such robots has prompted research into computational models for robotic learning from human demonstration. To further investigate biologically inspired human-like robotic movement and imitation, we have constructed a framework based on three key features of human movement and planning: optimality, modularity and learning. In this paper we describe a computational motor system, based on the minimum variance model of human movement, that uses optimality principles to produce human-like movement in a robot arm. Within this motor system different movements are represented in a modular structure. When the system observes a demonstrated movement, the motor system uses these modules to produce motor commands which are used to update an internal state representation. This is used so that the system can recognize known movements and move the robot arm accordingly, or extract key features from the demonstrated movement and use them to learn a new module. The active involvement of the motor system in the recognition and learning of observed movements has its theoretical basis in the direct matching hypothesis and the use of a model for human-like movement allows the system to learn from human demonstration.
Simmons G, Demiris Y, 2004, Biologically inspired optimal robot arm control with signal-dependent noise, IEEE/RSJ International Conference on Intelligent Robots and Systems, Pages: 491-496
Progress in the field of humanoid robotics and the need to find simpler ways to program such robots has prompted research into computational models for robotic learning from human demonstration. To further investigate biologically inspired human-like robotic movement and imitation, we have constructed a framework based on three key features of human movement and planning: optimality, modularity and learning. In this paper we focus on the application of optimality principles to the production of human-like movement by a robot arm. Among computational theories of human movement, the signal-dependent noise, or minimum variance, model was chosen as a biologically realistic control scheme to produce human-like movement. A well known optimal control algorithm, the linear quadratic regulator, was adapted to implement this model. The scheme was applied both in simulation and on a real robot arm, which demonstrated human-like movement profiles in a point-to-point reaching experiment.
Demiris Y, Johnson M, 2003, Distributed, predictive perception of actions: a biologically inspired robotics architecture for imitation and learning, Connection Science, Vol: 15, Pages: 231-243, ISSN: 0954-0091
One of the most important abilities for an agent's cognitive development in a social environment is the ability to recognize and imitate actions of others. In this paper we describe a cognitive architecture for action recognition and imitation, and present experiments demonstrating its implementation in robots. Inspired by neuroscientific and psychological data, and adopting a ‘simulation theory of mind’ approach, the architecture uses the motor systems of the imitator in a dual role, both for generating actions, and for understanding actions when performed by others. It consists of a distributed system of inverse and forward models that uses prediction accuracy as a means to classify demonstrated actions. The architecture is also shown to be capable of learning new composite actions from demonstration.
Eneje E, Demiris Y, 2003, Towards Robot Intermodal Matching Using Spiking Neurons, IROS'03 Workshop on Programming by Demonstration, Pages: 95-99
For a robot to successfully learn from demonstration it must posses the ability to reproduce the actions of a teacher. For this to happen, the robot must generate motor signals to match its proprioceptively perceived state with that of the visually perceived state of a teacher. In this paper we describe a real time matching model at a neural level of description. Experimental results from matching of arm movements, using dynamically simulated articulated robots, are presented.
Johnson M, Demiris Y, 2003, An integrated rapid development environment for computer-aided robot design and simulation, Bury St Edmunds, International Conference on Mechatronics, ICOM 2003, Publisher: Wiley, Pages: 485-490
We present our work towards the development of a rapid prototyping integrated environment for the design and dynamical simulation of multibody robotic systems. Subsequently, we demonstrate its current functionality in a case study involving the construction of a 130 DoF humanoid robot that attempts to closely match human motion capabilities. The modelling system relies exclusively on open-source software libraries thus offering high levels of customization and extensibility to the end-user.
Prince CG, Demiris Y, 2003, Editorial: Introduction to the special issue on epigenetic robotics, Adaptive Behaviour, Vol: 11, Pages: 75-77, ISSN: 1059-7123
Demiris Y, 2002, Mirror neurons, imitation and the learning of movement sequences, Singapore, 9th international conference on neural information processing (ICONIP), Singapore, Singapore, 18 - 22 November 2002, Publisher: Nanyang Technological Univ, Pages: 111-115
We draw inspiration from properties of "mirror" neurons discovered in the macaque monkey brain area F5, to design and implement a distributed behaviour-based architecture that equips robots with movement imitation abilities. We combine this generative route with a learning route, and demonstrate how new composite behaviours that exhibit mirror neuron like properties can be learned from demonstration.
Demiris Y, 2002, Biologically inspired robot imitation mechanisms and their application as models of mirror neurons, Proceedings of EPSRC/BBSRC workshop on biologically inspired robotics, Pages: 126-133
Demiris Y, Hayes G, 2002, Imitation as a dual-route process featuring predictive and learning components: a biologically plausible computational model, Imitation in animals and artifacts, Editors: Dautenhahn, Nehaniv, Cambridge, Massachussetts, Publisher: MIT Press, Pages: 327-361, ISBN: 9780262042031
Balkenius C, Prince C, Demiris Y, et al., 2001, Proceedings of the first international workshop on epigenetic robotics: modeling cognitive development in robotic systems, Lund, Publisher: Lund University, ISBN: 9789163114656
, 2000, Advances in Robot Learning, 8th European Workshop on Learning Robots, EWLR-8, Lausanne, Switzerland, September 18, 1999, Proceedings, Publisher: Springer
, 1998, Learning Robots, 6th European Workshop, EWLR-6, Brighton, England, August 1-2, 1997, Proceedings, Publisher: Springer
Demiris Y, Hayes G, 1997, Do Robots Ape?, AAAI Fall Symposium on Socially Intelligent Agents, Publisher: AAAI, Pages: 28-30
Within the context of two sets of robotic experiments we have performed, we examine some representational and algorithmic issues that need to be addressed in order to equip robots with the capacity to imitate. We suggest that some of the di culties might be eased by placing imitation architectures within a wider social context.
Klingspor V, Demiris J, Kaiser M, 1997, Human-robot communication and machine learning, APPLIED ARTIFICIAL INTELLIGENCE, Vol: 11, Pages: 719-746, ISSN: 0883-9514
Klingspor V, Demiris Y, Kaiser M, 1997, Human Robot Communication and Machine Learning, Applied Artificial Intelligence, Vol: 11, Pages: 719-746
Human-Robot Interaction and especially Human-Robot Communication (HRC) is of primary importance for the development of robots that operate outside production lines and cooperate with humans. In this paper, we review the state of the art and discuss two complementary aspects of the role machine learning plays in HRC. First, we show how communication itself can benefit from learning, e.g. by building human-understandable symbols from a robot’s perceptions and actions. Second, we investigate the power of non-verbal communication and imitation learning mechanisms for robot programming.
DEMIRIS J, 1994, EXPERIMENTS TOWARDS ROBOTIC LEARNING BY IMITATION, 12th National Conference on Artificial Intelligence, Publisher: M I T PRESS, Pages: 1439-1439
Choi J, Chang HJ, Fischer T, et al., Context-aware Deep Feature Compression for High-speed Visual Tracking
We propose a new context-aware correlation filter based tracking framework toachieve both high computational speed and state-of-the-art performance amongreal-time trackers. The major contribution to the high computational speed liesin the proposed deep feature compression that is achieved by a context-awarescheme utilizing multiple expert auto-encoders; a context in our frameworkrefers to the coarse category of the tracking target according to appearancepatterns. In the pre-training phase, one expert auto-encoder is trained percategory. In the tracking phase, the best expert auto-encoder is selected for agiven target, and only this auto-encoder is used. To achieve high trackingperformance with the compressed feature map, we introduce extrinsic denoisingprocesses and a new orthogonality loss term for pre-training and fine-tuning ofthe expert auto-encoders. We validate the proposed context-aware frameworkthrough a number of experiments, where our method achieves a comparableperformance to state-of-the-art trackers which cannot run in real-time, whilerunning at a significantly fast speed of over 100 fps.
Cully A, Demiris Y, Hierarchical Behavioral Repertoires with Unsupervised Descriptors
Enabling artificial agents to automatically learn complex, versatile andhigh-performing behaviors is a long-lasting challenge. This paper presents astep in this direction with hierarchical behavioral repertoires that stackseveral behavioral repertoires to generate sophisticated behaviors. Eachrepertoire of this architecture uses the lower repertoires to create complexbehaviors as sequences of simpler ones, while only the lowest repertoiredirectly controls the agent's movements. This paper also introduces a novelapproach to automatically define behavioral descriptors thanks to anunsupervised neural network that organizes the produced high-level behaviors.The experiments show that the proposed architecture enables a robot to learnhow to draw digits in an unsupervised manner after having learned to draw linesand arcs. Compared to traditional behavioral repertoires, the proposedarchitecture reduces the dimensionality of the optimization problems by ordersof magnitude and provides behaviors with a twice better fitness. Moreimportantly, it enables the transfer of knowledge between robots: ahierarchical repertoire evolved for a robotic arm to draw digits can betransferred to a humanoid robot by simply changing the lowest layer of thehierarchy. This enables the humanoid to draw digits although it has never beentrained for this task.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.