Yiannis Demiris

Hierarchical attentive multiple models for execution and recognition of actions

According to the motor theories of perception, the motor systems of an observer are actively involved in the perception of actions when these are performed by a demonstrator. In this paper we review our computational architecture, HAMMER (Hierarchical Attentive Multiple Models for Execution and Recognition), where the motor control systems of a robot are organised in a hierarchical, distributed manner, and can be used in the dual role of (a) competitively selecting and executing an action, and (b) perceiving it when performed by a demonstrator. We subsequently demonstrate that such an arrangement can provide a principled method for the top-down control of attention during action perception, resulting in significant performance gains. We assess these performance gains under a variety of resource allocation strategies. c 2006 Elsevier B.V. All rights reserved.

Collaborative Control for a Robotic Wheelchair: Evaluation of Performance, Attention, and Workload

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 drivers 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.

Distributed, predictive perception of actions: a biologically inspired robotics architecture for imitation and learning

One of the most important abilities for an agents 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. *email: y.demiris@imperial.ac.uk †email: matthew.johnson@imperial.ac.uk

Prediction of intent in robotics and multi-agent systems

Moving beyond the stimulus contained in observable agent behaviour, i.e. understanding the underlying intent of the observed agent is of immense interest in a variety of domains that involve collaborative and competitive scenarios, for example assistive robotics, computer games, robot–human interaction, decision support and intelligent tutoring. This review paper examines approaches for performing action recognition and prediction of intent from a multi-disciplinary perspective, in both single robot and multi-agent scenarios, and analyses the underlying challenges, focusing mainly on generative approaches.

Echo State Gaussian Process

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.

Perceptual Perspective Taking and Action Recognition

Robots that operate in social environments need to be able to recognise and understand the actions of other robots, and humans, in order to facilitate learning through imitation and collaboration. The success of the simulation theory approach to action recognition and imitation relies on the ability to take the perspective of other people, so as to generate simulated actions from their point of view. In this paper, simulation of visual perception is used to re-create the visual egocentric sensory space and egocentric behaviour space of an observed agent, and through this increase the accuracy of action recognition. To demonstrate the approach, experiments are performed with a robot attributing perceptions to and recognising the actions of a second robot.

Increasing robotic wheelchair safety with collaborative control: Evidence from secondary task experiments

Powered wheelchairs play a vital role in bringing independence to the severely mobility-impaired. Our robotic wheelchair aims to assist users in driving safely, without undermining their capabilities or curtailing the natural development of their skills. An important research question is to determine the conditions under which shared control is most beneficial. In this paper, we describe an experiment, where a distracting secondary task caused the majority of participants to crash the wheelchair when driving without assistance. However, when they were assisted by our collaborative controller, not only did they drive safely, but they also increased their performance in the secondary task. We demonstrate that a degree of shared control is beneficial even to proficient drivers under certain circumstances, for instance when they are under a heightened workload.

The Coordinating Role of Language in Real-Time Multimodal Learning of Cooperative Tasks

One of the defining characteristics of human cognition is our outstanding capacity to cooperate. A central requirement for cooperation is the ability to establish a “shared plan”—which defines the interlaced actions of the two cooperating agents—in real time, and even to negotiate this shared plan during its execution. In the current research we identify the requirements for cooperation, extending our earlier work in this area. These requirements include the ability to negotiate a shared plan using spoken language, to learn new component actions within that plan, based on visual observation and kinesthetic demonstration, and finally to coordinate all of these functions in real time. We present a cognitive system that implements these requirements, and demonstrate the systems ability to allow a Nao humanoid robot to learn a nontrivial cooperative task in real-time. We further provide a concrete demonstration of how the real-time learning capability can be easily deployed on a different platform, in this case the iCub humanoid. The results are considered in the context of how the development of language in the human infant provides a powerful lever in the development of cooperative plans from lower-level sensorimotor capabilities.

Online spatio-temporal Gaussian process experts with application to tactile classification

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.

2006 Special issue: Perceiving the unusual: Temporal properties of hierarchical motor representations for action perception

Recent computational approaches to action imitation have advocated the use of hierarchical representations in the perception and imitation of demonstrated actions. Hierarchical representations present several advantages, with the main one being their ability to process information at multiple levels of detail. However, the nature of the hierarchies in these approaches has remained relatively unsophisticated, and their relation with biological evidence has not been investigated in detail, in particular with respect to the timing of movements. Following recent neuroscience work on the modulation of the premotor mirror neuron activity during the observation of unpredictable grasping movements, we present here an implementation of our HAMMER architecture using the minimum variance model for implementing reaching and grasping movements that have biologically plausible trajectories. Subsequently, we evaluate the performance of our model in matching the temporal dynamics of the modulation of cortical excitability during the passive observation of normal and unpredictable movements of human demonstrators.