Publications
270 results found
Ognibene D, Wu Y, Lee K, et al., 2013, Hierarchies for embodied action perception, Computational and Robotic Models of the Hierarchical Organization of Behavior, Editors: Baldassarre, Mirolli, Publisher: Springer, Pages: 81-98
During social interactions, humans are capable of initiating and responding to rich and complex social actions despite having incomplete world knowledge, and physical, perceptual and computational constraints. This capability relies on action perception mechanisms that exploit regularities in observed goal-oriented behaviours to generate robust predictions and reduce the workload of sensing systems. To achieve this essential capability, we argue that the following three factors are fundamental. First, human knowledge is frequently hierarchically structured, both in the perceptual and execution domains. Second, human perception is an active process driven by current task requirements and context; this is particularly important when the perceptual input is complex (e.g. human motion) and the agent has to operate under embodiment constraints. Third, learning is at the heart of action perception mechanisms, underlying the agent’s ability to add new behaviours to its repertoire. Based on these factors, we review multiple instantiations of a hierarchically-organised biologically-inspired framework for embodied action perception, demonstrating its flexibility in addressing the rich computational contexts of action perception and learning in robotic platforms.
Su Y, Wu Y, Lee K, et al., 2012, Robust Grasping for an Under-actuated Anthropomorphic Handunder Object Position Uncertainty, Osaka, Japan, International Conference on Humanoid Robots (Humanoids), Publisher: IEEE, Pages: 719-725
This paper presents a grasp execution strategy for grasping an object with one trial when there is uncertainty in the object position. This strategy is based on three grasping components: 1) robust grasp trajectory planning which can cope with reasonable amount of initial object position error, 2) sensor-based grasp adaptation, and 3) compliant characteristics of the under actuated mechanism. This strategy is implemented and tested on the iCub humanoid robot. Two experiments and a demo of the iCub robot playing the Towers of Hanoi game are carried out to verify our system. The results demonstrate that the iCub using this approach can successfully grasp objects under certain position error with its under-actuated anthropomorphic hand.
Chatzis SP, Demiris Y, 2012, Nonparametric mixtures of Gaussian processes with power-law behavior, IEEE Transactions on Neural Networks, Vol: 23, Pages: 1862-1871, ISSN: 2162-237X
Gaussian processes (GPs) constitute one of the most important Bayesian machine learning approaches, based on a particularly effective method for placing a prior distribution overthe space of regression functions. Several researchers have considered postulating mixtures of Gaussian processes as a means ofdealing with non-stationary covariance functions, discontinuities, multi-modality, and overlapping output signals. In existing works, mixtures of Gaussian processes are based on the introduction of a gating function defined over the space of model input variables. This way, each postulated mixture component Gaussian process is effectively restricted in a limited subset of the input space. In this work, we follow a different approach: We consider a fully generative nonparametric Bayesian model with power-law behavior, generating Gaussian processes over the whole input space of the learned task. We provide an efficient algorithm for model inference, based on the variational Bayesian framework, and exhibit its efficacy using benchmark and real-world datasets.
Lee K, Kim TK, Demiris Y, 2012, Learning Action Symbols for Hierarchical Grammar Induction, Tsukuba, Japan, International Conference on Pattern Recognition (ICPR), Publisher: IEEE, Pages: 3778-3782
We present an unsupervised method of learning action symbols from video data, which self-tunes the number of symbols to effectively build hierarchical activity grammars. A video stream is given as a sequence of unlabeled segments. Similar segments are incrementally grouped to form a hierarchical tree structure. The tree is cut into clusters where each cluster is used to train an action symbol. Our goal is to find a good set of clusters i.e. symbols where regularities are best captured in the learned representation, i.e. induced grammar. Our method has two-folds: 1) Create a candidate set of symbols from initial clusters, 2) Build an activity grammar and measure model complexity and likelihood to assess the quality of the candidate set of symbols. We propose a balanced model comparison method which avoids the problem commonly found in model complexity computations where one measurement term dominates the other. Our experiments on the towers of Hanoi and human dancing videos show that our method can discover the optimal number of action symbols effectively.
Chatzis SP, Demiris Y, 2012, A Reservoir-Driven Non-Stationary Hidden Markov Model, Pattern Recognition, Vol: 45, Pages: 3985-3996
In this work, we propose a novel approach towards sequential data modeling that leverages the strengths of hidden Markov models and echo-state networks (ESNs) in the context of non-parametric Bayesian inference approaches. We introduce a non-stationary hidden Markov model, the time-dependent state transition probabilities of which are driven by a high-dimensional signal that encodes the whole history of the modeled observations, namely the state vector of a postulated observations-driven ESN reservoir. We derive an efficient inference algorithm for our model under the variational Bayesian paradigm, and we examine the efficacy of our approach considering a number of sequential data modeling applications.
Chatzis SP, Korkinof D, Demiris Y, 2012, The Kernel Pitman-Yor Process
In this work, we propose the kernel Pitman-Yor process (KPYP) fornonparametric clustering of data with general spatial or temporalinterdependencies. The KPYP is constructed by first introducing an infinitesequence of random locations. Then, based on the stick-breaking construction ofthe Pitman-Yor process, we define a predictor-dependent random probabilitymeasure by considering that the discount hyperparameters of theBeta-distributed random weights (stick variables) of the process are notuniform among the weights, but controlled by a kernel function expressing theproximity between the location assigned to each weight and the givenpredictors.
Soh H, Su Y, Demiris Y, 2012, Online Spatio-Temporal Gaussian Process Experts with Application to Tactile Classification, International Conference on Intelligent Robots and Systems, IROS, Publisher: IEEE, Pages: 4489-4496, ISSN: 2153-0858
In this work, we are primarily concerned with robotic systems that learn online and continuously from multi-variate data-streams. Our first contribution is a new recursive kernel, which we have integrated into a sparse Gaussian Process to yield the Spatio-Temporal Online Recursive Kernel Gaussian Process (STORK-GP). This algorithm iteratively learns from time-series, providing both predictions and uncertainty estimates. Experiments on benchmarks demonstrate that our method achieves high accuracies relative to state-of-the-art methods. Second, we contribute an online tactile classifier which uses an array of STORK-GP experts. In contrast to existing work, our classifier is capable of learning new objects as they are presented, improving itself over time. We show that our approach yields results comparable to highly-optimised offline classification methods. Moreover, we conducted experiments with human subjects in a similar online setting with true-label feedback and present the insights gained.
Soh H, Demiris Y, 2012, Towards Early Mobility Independence: An Intelligent Paediatric Wheelchair with Case Studies, IROS Workshop on Progress, Challenges and Future Perspectives in Navigation and Manipulation Assistance for Robotic Wheelchairs
Standard powered wheelchairs are still heavily dependent on the cognitive capabilities of users. Unfortunately, this excludes disabled users who lack the required problem-solving and spatial skills, particularly young children. For these children to be denied powered mobility is a crucial set-back; exploration is important for their cognitive, emotional and psychosocial development. In this paper, we present a safer paediatric wheelchair: the Assistive Robot Transport for Youngsters (ARTY). The fundamental goal of this research is to provide a key-enabling technology to young children who would otherwise be unable to navigate independently in their environment. In addition to the technical details of our smart wheelchair, we present user-trials with able-bodied individuals as well as one 5-year-old child with special needs. ARTY promises to provide young children with "early access" to the path towards mobility independence.
Chatzis SP, Demiris Y, 2012, The echo state conditional random field model for sequential data modeling, Expert Systems With Applications, Vol: 39, Pages: 10303-10309, ISSN: 0957-4174
Sequential data labeling is a fundamental task in machine learning applications, with speech and natural language processing, activity recognition in video sequences, and biomedical data analysis being characteristic such examples, to name just a few. The conditional random field (CRF), a log-linear model representing the conditional distribution of the observation labels, is one of the most successful approaches for sequential data labeling and classification, and has lately received significant attention in machine learning, as it achieves superb prediction performance in a variety of scenarios. Nevertheless, existing CRF formulations do not account for temporal dependencies between the observed variables – they only postulate Markovian interdependencies between the predicted label variables. To resolve these issues, in this paper we propose a non-linear hierarchical CRF formulation that combines the power of echo state networks to extract high level temporal features with the graphical framework of CRF models, yielding a powerful and scalable probabilistic model that we apply to signal labeling tasks.
Chatzis SP, Korkinof D, Demiris Y, 2012, A Spatially-Constrained Normalized Gamma Process for Data Clustering, International Conference on Artificial Intelligence Applications and Innovations, AIA 2012, Publisher: Springer, Pages: 337-346
In this work, we propose a novel nonparametric Bayesian method for clustering of data with spatial interdependencies. Specifically, we devise a novel normalized Gamma process, regulated by a simplified (pointwise) Markov random field (Gibbsian) distribution with a countably infinite number of states. As a result of its construction, the proposed model allows for introducing spatial dependencies in the clustering mechanics of the normalized Gamma process, thus yielding a novel nonparametric Bayesian method for spatial data clustering. We derive an efficient truncated variational Bayesian algorithm for model inference. We examine the efficacy of our approach by considering an image segmentation application using a real-world dataset. We show that our approach outperforms related methods from the field of Bayesian nonparametrics, including the infinite hidden Markov random field model, and the Dirichlet process prior.
Ognibene D, Chinellato E, Sarabia M, et al., 2012, Towards Contextual Action Recognition and Target Localization with Active Allocation of Attention, Living Machines, Publisher: Springer, Pages: 192-203, ISSN: 0302-9743
Exploratory gaze movements are fundamental for gathering the most relevant information regarding the partner during social interactions. We have designed and implemented a system for dynamic attention allocation which is able to actively control gaze movements during a visual action recognition task. During the observation of a partner’s reaching movement, the robot is able to contextually estimate the goal position of the partner hand and the location in space of the candidate targets, while moving its gaze around with the purpose of optimizing the gathering of information relevant for the task. Experimental results on a simulated environment show that active gaze control provides a relevant advantage with respect to typical passive observation, both in term of estimation precision and of time required for action recognition.
Chatzis SP, Demiris Y, 2012, A Sparse Nonparametric Hierarchical Bayesian Approach Towards Inductive Transfer for Preference Modeling, Expert Systems with Applications, Vol: 39, Pages: 7235-7246
In this paper, we present a novel methodology for preference learning based on the concept of inductive transfer. Specifically, we introduce a nonparametric hierarchical Bayesian multitask learning approach, based on the notion that human subjects may cluster together forming groups of individuals with similar preference rationale (but not identical preferences). Our approach is facilitated by the utilization of a Dirichlet process prior, which allows for the automatic inference of the most appropriate number of subject groups (clusters), as well as the employment of the automatic relevance determination (ARD) mechanism, giving rise to a sparse nature for our model, which significantly enhances its computational efficiency. We explore the efficacy of our novel approach by applying it to both a synthetic experiment and a real-world music recommendation application. As we show, our approach offers a significant enhancement in the effectiveness of knowledge transfer in statistical preference learning applications, being capable of correctly inferring the actual number of human subject groups in a modeled dataset, and limiting knowledge transfer only to subjects belonging to the same group (wherein knowledge transferability is more likely).
Chatzis SP, Korkinof D, Demiris Y, 2012, A nonparametric Bayesian approach toward robot learning by demonstration, Robotics and Autonomous Systems, Vol: 60, Pages: 789-802, ISSN: 0921-8890
In the past years, many authors have considered application of machine learning methodologies to effect robot learning by demonstration. Gaussian mixture regression (GMR) is one of the most successful methodologies used for this purpose. A major limitation of GMR models concerns automatic selection of the proper number of model states, i.e., the number of model component densities. Existing methods, including likelihood- or entropy-based criteria, usually tend to yield noisy model size estimates while imposing heavy computational requirements. Recently, Dirichlet process (infinite) mixture models have emerged in the cornerstone of nonparametric Bayesian statistics as promising candidates for clustering applications where the number of clusters is unknown a priori. Under this motivation, to resolve the aforementioned issues of GMR-based methods for robot learning by demonstration, in this paper we introduce a nonparametric Bayesian formulation for the GMR model, the Dirichlet process GMR model. We derive an efficient variational Bayesian inference algorithm for the proposed model, and we experimentally investigate its efficacy as a robot learning by demonstration methodology, considering a number of demanding robot learning by demonstration scenarios.
Carlson T, Demiris Y, 2012, Collaborative Control of a Robotic Wheelchair: Evaluation of Performance, Attention and Workload, IEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics, Vol: 42, Pages: 876-888, ISSN: 1083-4419
Powered wheelchair users often struggle to drive safely and effectively and, in more critical cases, can only get around when accompanied by an assistant. To address these issues, we propose a collaborative control mechanism that assists users as and when they require help. The system uses a multiple-hypothesis method to predict the driver's intentions and, if necessary, adjusts the control signals to achieve the desired goal safely. The main emphasis of this paper is on a comprehensive evaluation, where we not only look at the system performance but also, perhaps more importantly, characterize the user performance in an experiment that combines eye tracking with a secondary task. Without assistance, participants experienced multiple collisions while driving around the predefined route. Conversely, when they were assisted by the collaborative controller, not only did they drive more safely but also they were able to pay less attention to their driving, resulting in a reduced cognitive workload. We discuss the importance of these results and their implications for other applications of shared control, such as brain-machine interfaces, where it could be used to compensate for both the low frequency and the low resolution of the user input.
Lee K, Kim TK, Demiris Y, 2012, Learning Reusable Task Components using Hierarchical Activity Grammars with Uncertainties, St. Paul, Minnesota, USA, Publisher: IEEE, Pages: 1994-1999
We present a novel learning method using activity grammars capable of learning reusable task components from a reasonably small number of samples under noisy conditions. Our linguistic approach aims to extract the hierarchical structure of activities which can be recursively applied to help recognize unforeseen, more complicated tasks that share the same underlying structures. To achieve this goal, our method 1) actively searches for frequently occurring action symbols that are subset of input samples to effectively discover the hierarchy, and 2) explicitly takes into account the uncertainty values associated with input symbols due to the noise inherent in low-level detectors. In addition to experimenting with a synthetic dataset to systematically analyze the algorithm's performance, we apply our method in human-led imitation learning environment where a robot learns reusable components of the task from short demonstrations to correctly imitate more complicated, longer demonstrations of the same task category. The results suggest that under reasonable amount of noise, our method is capable to capture the reusable structures of tasks and generalize to cope with recursions.
Soh H, Demiris Y, 2012, Iterative Temporal Learning and Prediction with the Sparse Online Echo State Gaussian Process, International Joint Conference on Neural Networks, IJCNN, Publisher: IEEE, Pages: 1-8, ISSN: 2161-4393
In this work, we contribute the online echo state gaussian process (OESGP), a novel Bayesian-based online method that is capable of iteratively learning complex temporal dynamics and producing predictive distributions (instead of point predictions). Our method can be seen as a combination of the echo state network with a sparse approximation of Gaussian processes (GPs). Extensive experiments on the one-step prediction task on well-known benchmark problems show that OESGP produced statistically superior results to current online ESNs and state-of-the-art regression methods. In addition, we characterise the benefits (and drawbacks) associated with the considered online methods, specifically with regards to the trade-off between computational cost and accuracy. For a high-dimensional action recognition task, we demonstrate that OESGP produces high accuracies comparable to a recently published graphical model, while being fast enough for real-time interactive scenarios.
Chatzis SP, Demiris Y, 2012, The copula echo state network, Pattern Recognition, Vol: 45, Pages: 570-577, ISSN: 0031-3203
Echo state networks (ESNs) constitute a novel approach to recurrent neural network (RNN) training, with an RNN (the reservoir) being generated randomly, and only a readout being trained using a simple, computationally efficient algorithm. ESNs have greatly facilitated the practical application of RNNs, outperforming classical approaches on a number of benchmark tasks. This paper studies the formulation of a class of copula-based semiparametric models for sequential data modeling, characterized by nonparametric marginal distributions modeled by postulating suitable echo state networks, and parametric copula functions that help capture all the scale-free temporal dependence of the modeled processes. We provide a simple algorithm for the data-driven estimation of the marginal distribution and the copula parameters of our model under the maximum-likelihood framework. We exhibit the merits of our approach by considering a number of applications; as we show, our method offers a significant enhancement in the dynamical data modeling capabilities of ESNs, without significant compromises in the algorithm's computational efficiency.
Ribes A, Cerquides Bueno J, Demiris Y, et al., 2012, Context-GMM: Incremental Learning of Sparse Priors for Gaussian Mixture Regression, IEEE International Conference on Robotics and Biomimetics (ROBIO), Publisher: IEEE
- Author Web Link
- Cite
- Citations: 4
Chatzis SP, Korkinof D, Demiris Y, 2012, A Quantum-Statistical Approach Toward Robot Learning by Demonstration, IEEE Transactions on Robotics, Vol: 28, Pages: 1371-1381-1371-1381, ISSN: 1941-0468
Statistical machine learning approaches have been at the epicenter of the ongoing research work in the field of robot learning by demonstration over the past few years. One of the most successful methodologies used for this purpose is a Gaussian mixture regression (GMR). In this paper, we propose an extension of GMR-based learning by demonstration models to incorporate concepts from the field of quantum mechanics. Indeed, conventional GMR models are formulated under the notion that all the observed data points can be assigned to a distinct number of model states (mixture components). In this paper, we reformulate GMR models, introducing some quantum states constructed by superposing conventional GMR states by means of linear combinations. The so-obtained quantum statistics-inspired mixture regression algorithm is subsequently applied to obtain a novel robot learning by demonstration methodology, offering a significantly increased quality of regenerated trajectories for computational costs comparable with currently state-of-the-art trajectory-based robot learning by demonstration approaches. We experimentally demonstrate the efficacy of the proposed approach.
Ribes A, Cerquides J, Demiris Y, et al., 2012, Incremental Learning of an Optical Flow Model for Sensorimotor Anticipation in a Mobile Robot, IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL), Publisher: IEEE, ISSN: 2161-9484
Chatzis SP, Korkinof D, Demiris Y, 2012, A spatially-constrained normalized Gamma process prior, Expert Systems with Applications, Vol: 39, Pages: 13019 - 13025-13019 - 13025, ISSN: 0957-4174
Ognibene D, Demiris Y, 2012, Attentional shifts during action perception, Publisher: PION LTD, Pages: 1272-1272, ISSN: 0301-0066
Claassens J, Demiris Y, 2012, Exploiting Affordance Symmetries for Task Reproduction Planning, 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids), Publisher: IEEE, Pages: 653-659, ISSN: 2164-0572
- Author Web Link
- Cite
- Citations: 2
Claassens J, Demiris Y, 2011, Generalising human demonstration data by identifying affordance symmetries in object interaction trajectories, Pages: 1980-1985
This paper concerns modelling human hand or tool trajectories when interacting with everyday objects. In these interactions symmetries may be exhibited in portions of the trajectories which can be used to identify task space redundancy. This paper presents a formal description of a set of these symmetries, which we term affordance symmetries, and a method to identify them in multiple demonstration recordings. The approach is robust to arbitrary motion before and after the symmetry artifact and relies only on recorded trajectory data. To illustrate the method's performance two examples are discussed involving two different types of symmetries. An simple illustration of the application of the concept in reproduction planning is also provided. © 2011 IEEE.
Ros R, Nalin M, Wood R, et al., 2011, Child-robot interaction in the wild: Advice to the aspiring experimenter, Pages: 335-342
We present insights gleaned from a series of child-robot interaction experiments carried out in a hospital paediatric department. Our aim here is to share good practice in experimental design and lessons learned about the implementation of systems for social HRI with child users towards application in "the wild", rather than in tightly controlled and constrained laboratory environments: a trade-off between the structures imposed by experimental design and the desire for removal of such constraints that inhibit interaction depth, and hence engagement, requires a careful balance. © 2011 ACM.
- Abstract
- Open Access Link
- Cite
- Citations: 83
Wu Y, Demiris Y, 2011, Learning Dynamical Representations of Tools for Tool-Use Recognition, International Conference on Robotics and Biomimetics (ROBIO), Publisher: IEEE, Pages: 2664-2669
We consider the problem of representing and recognising tools, a subset of objects that have special functionality and action patterns. Our proposed framework is based on the biological evidence of hierarchical representation of tools in the region of the human cortex that generates action semantics. It addresses the shortfalls of traditional learning models of object representation applied on tools. To showcase its merits, this framework is implemented as a hybrid model between the Hierarchical Attentive Multiple Models for Execution and Recognition of Actions Architecture (HAMMER) and Hidden Markov Model (HMM) to recognise and describe tools as dynamic patterns at symbolic level. The implemented model is tested and validated on two sets of experiments of 50 human demonstrations each on using 5 different tools. In the experiment with precise and accurate input data, the cross-validation statistics suggest very robust identification of the learned tools. In the experiment with unstructured environment, all errors can be explained systematically.
Chatzis SP, Korkinof D, Demiris Y, 2011, The One-Hidden Layer Non-parametric Bayesian Kernel Machine, IEEE International Conference on Tools with Artificial Intelligence (ICTAI)
In this paper, we present a nonparametric Bayesian approach towards one-hidden-layer feedforward neural net- works. Our approach is based on a random selection of the weights of the synapses between the input and the hidden layer neurons, and a Bayesian marginalization over the weights of the connections between the hidden layer neurons and the output neurons, giving rise to a kernel-based nonparametric Bayesian inference procedure for feedforward neural networks. Compared to existing approaches, our method presents a number of advan- tages, with the most significant being: (i) it offers a significant improvement in terms of the obtained generalization capabilities; (ii) being a nonparametric Bayesian learning approach, it entails inference instead of fitting to data, thus resolving the overfitting issues of non-Bayesian approaches; and (iii) it yields a full predictive posterior distribution, thus naturally providing a measure of uncertainty on the generated predictions (expressed by means of the variance of the predictive distribution), without the need of applying computationally intensive methods, e.g., bootstrap. We exhibit the merits of our approach by investigating its application to two difficult multimedia content classification applications: semantic characterization of audio scenes based on content, and yearly song classification, as well as a set of benchmark classification and regression tasks.
Claassens J, Demiris Y, 2011, Generalising human demonstration data by identifying affordance symmetries in object interaction trajectories., International Conference on Robotics and Intelligent Systems (IROS), Publisher: IEEE, Pages: 1980-1985
This paper concerns modelling human hand or tool trajectories when interacting with everyday objects. In these interactions symmetries may be exhibited in portions of the trajectories which can be used to identify task space redundancy. This paper presents a formal description of a set of these symmetries, which we term affordance symmetries, and a method to identify them in multiple demonstration recordings. The approach is robust to arbitrary motion before and after the symmetry artifact and relies only on recorded trajectory data. To illustrate the method's performance two examples are discussed involving two different types of symmetries. An simple illustration of the application of the concept in reproduction planning is also provided.
Kruijff-Korbayová I, Cuayáhuitl H, Kiefer B, et al., 2011, A conversational system for multi-session child-robot interaction with several games, Germany, KI-2012: Poster and Demo Track, Pages: 135-139
Chatzis SP, Demiris Y, 2011, Echo State Gaussian Process, IEEE Transactions on Neural Networks, Vol: 22, Pages: 1435-1445, ISSN: 1045-9227
Echo state networks (ESNs) constitute a novel approach to recurrent neural network (RNN) training, with an RNN (the reservoir) being generated randomly, and only a readout being trained using a simple computationally efficient algorithm. ESNs have greatly facilitated the practical application of RNNs, outperforming classical approaches on a number of benchmark tasks. In this paper, we introduce a novel Bayesian approach toward ESNs, the echo state Gaussian process (ESGP). The ESGP combines the merits of ESNs and Gaussian processes to provide a more robust alternative to conventional reservoir computing networks while also offering a measure of confidence on the generated predictions (in the form of a predictive distribution). We exhibit the merits of our approach in a number of applications, considering both benchmark datasets and real-world applications, where we show that our method offers a significant enhancement in the dynamical data modeling capabilities of ESNs. Additionally, we also show that our method is orders of magnitude more computationally efficient compared to existing Gaussian process-based methods for dynamical data modeling, without compromises in the obtained predictive performance.
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.