Publications

Journal article

Moulin-Frier C, Fischer T, Petit M, Pointeau G, Puigbo JY, Pattacini U, Low SC, Camilleri D, Nguyen P, Hoffmann M, Chang HJ, Zambelli M, Mealier AL, Damianou A, Metta G, Prescott TJ, Demiris Y, Dominey PF, Verschure PFMJet al., 2018,

DAC-h3: A Proactive Robot Cognitive Architecture to Acquire and Express Knowledge About the World and the Self

, IEEE Transactions on Cognitive and Developmental Systems, Vol: 10, Pages: 1005-1022, ISSN: 2379-8920

This paper introduces a cognitive architecture for a humanoid robot to engage in a proactive, mixed-initiative exploration and manipulation of its environment, where the initiative can originate from both the human and the robot. The framework, based on a biologically-grounded theory of the brain and mind, integrates a reactive interaction engine, a number of state-of-the art perceptual and motor learning algorithms, as well as planning abilities and an autobiographical memory. The architecture as a whole drives the robot behavior to solve the symbol grounding problem, acquire language capabilities, execute goal-oriented behavior, and express a verbal narrative of its own experience in the world. We validate our approach in human-robot interaction experiments with the iCub humanoid robot, showing that the proposed cognitive architecture can be applied in real time within a realistic scenario and that it can be used with naive users.

Journal article

Chang HJ, Fischer T, Petit M, Zambelli M, Demiris Yet al., 2018,

Learning kinematic structure correspondences using multi-order similarities

, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol: 40, Pages: 2920-2934, ISSN: 0162-8828

We present a novel framework for finding the kinematic structure correspondences between two articulated objects in videos via hypergraph matching. In contrast to appearance and graph alignment based matching methods, which have been applied among two similar static images, the proposed method finds correspondences between two dynamic kinematic structures of heterogeneous objects in videos. Thus our method allows matching the structure of objects which have similar topologies or motions, or a combination of the two. Our main contributions are summarised as follows: (i)casting the kinematic structure correspondence problem into a hypergraph matching problem by incorporating multi-order similarities with normalising weights, (ii)introducing a structural topology similarity measure by aggregating topology constrained subgraph isomorphisms, (iii)measuring kinematic correlations between pairwise nodes, and (iv)proposing a combinatorial local motion similarity measure using geodesic distance on the Riemannian manifold. We demonstrate the robustness and accuracy of our method through a number of experiments on synthetic and real data, showing that various other recent and state of the art methods are outperformed. Our method is not limited to a specific application nor sensor, and can be used as building block in applications such as action recognition, human motion retargeting to robots, and articulated object manipulation.

Conference paper

Fischer T, Chang HJ, Demiris Y, 2018,

RT-GENE: Real-time eye gaze estimation in natural environments

, European Conference on Computer Vision, Publisher: Springer Verlag, Pages: 339-357, ISSN: 0302-9743

In this work, we consider the problem of robust gaze estimation in natural environments. Large camera-to-subject distances and high variations in head pose and eye gaze angles are common in such environments. This leads to two main shortfalls in state-of-the-art methods for gaze estimation: hindered ground truth gaze annotation and diminished gaze estimation accuracy as image resolution decreases with distance. We first record a novel dataset of varied gaze and head pose images in a natural environment, addressing the issue of ground truth annotation by measuring head pose using a motion capture system and eye gaze using mobile eyetracking glasses. We apply semantic image inpainting to the area covered by the glasses to bridge the gap between training and testing images by removing the obtrusiveness of the glasses. We also present a new real-time algorithm involving appearance-based deep convolutional neural networks with increased capacity to cope with the diverse images in the new dataset. Experiments with this network architecture are conducted on a number of diverse eye-gaze datasets including our own, and in cross dataset evaluations. We demonstrate state-of-the-art performance in terms of estimation accuracy in all experiments, and the architecture performs well even on lower resolution images.

Conference paper

Nguyen P, Fischer T, Chang HJ, Pattacini U, Metta G, Demiris Yet al., 2018,

Transferring visuomotor learning from simulation to the real world for robotics manipulation tasks

, IEEE/RSJ International Conference on Intelligent Robots and Systems, Publisher: IEEE, Pages: 6667-6674, ISSN: 2153-0866

Hand-eye coordination is a requirement for many manipulation tasks including grasping and reaching. However, accurate hand-eye coordination has shown to be especially difficult to achieve in complex robots like the iCub humanoid. In this work, we solve the hand-eye coordination task using a visuomotor deep neural network predictor that estimates the arm's joint configuration given a stereo image pair of the arm and the underlying head configuration. As there are various unavoidable sources of sensing error on the physical robot, we train the predictor on images obtained from simulation. The images from simulation were modified to look realistic using an image-to-image translation approach. In various experiments, we first show that the visuomotor predictor provides accurate joint estimates of the iCub's hand in simulation. We then show that the predictor can be used to obtain the systematic error of the robot's joint measurements on the physical iCub robot. We demonstrate that a calibrator can be designed to automatically compensate this error. Finally, we validate that this enables accurate reaching of objects while circumventing manual fine-calibration of the robot.

Conference paper

Chacon Quesada R, Demiris Y, 2018,

Augmented reality control of smart wheelchair using eye-gaze–enabled selection of affordances

, https://www.idiap.ch/workshop/iros2018/files/, IROS 2018 Workshop on Robots for Assisted Living

In this paper we present a novel augmented reality head mounted display user interface for controlling a robotic wheelchair for people with limited mobility. To lower the cognitive requirements needed to control the wheelchair, we propose integration of a smart wheelchair with an eye-tracking enabled head-mounted display. We propose a novel platform that integrates multiple user interface interaction methods for aiming at and selecting affordances derived by on-board perception capabilities such as laser-scanner readings and cameras. We demonstrate the effectiveness of the approach by evaluating our platform in two realistic scenarios: 1) Door detection, where the affordance corresponds to a Door object and the Go-Through action and 2) People detection, where the affordance corresponds to a Person and the Approach action. To the best of our knowledge, this is the first demonstration of a augmented reality head-mounted display user interface for controlling a smart wheelchair.

Conference paper

Fischer T, Demiris Y, 2018,

A computational model for embodied visual perspective taking: from physical movements to mental simulation

, Vision Meets Cognition Workshop at CVPR 2018

To understand people and their intentions, humans have developed the ability to imagine their surroundings from another visual point of view. This cognitive ability is called perspective taking and has been shown to be essential in child development and social interactions. However, the precise cognitive mechanisms underlying perspective taking remain to be fully understood. Here we present a computa- tional model that implements perspective taking as a mental simulation of the physical movements required to step into the other point of view. The visual percept after each mental simulation step is estimated using a set of forward models. Based on our experimental results, we propose that a visual attention mechanism explains the response times reported in human visual perspective taking experiments. The model is also able to generate several testable predictions to be explored in further neurophysiological studies.

Conference paper

Elsdon J, Demiris Y, 2018,

Augmented reality for feedback in a shared control spraying task

, IEEE International Conference on Robotics and Automation (ICRA), Publisher: Institute of Electrical and Electronics Engineers (IEEE), Pages: 1939-1946, ISSN: 1050-4729

Using industrial robots to spray structures has been investigated extensively, however interesting challenges emerge when using handheld spraying robots. In previous work we have demonstrated the use of shared control of a handheld spraying robot to assist a user in a 3D spraying task. In this paper we demonstrate the use of Augmented Reality Interfaces to increase the user's progress and task awareness. We describe our solutions to challenging calibration issues between the Microsoft Hololens system and a motion capture system without the need for well defined markers or careful alignment on the part of the user. Error relative to the motion capture system was shown to be 10mm after only a 4 second calibration routine. Secondly we outline a logical approach for visualising liquid density for an augmented reality spraying task, this system allows the user to see target regions to complete, areas that are complete and areas that have been overdosed clearly. Finally we produced a user study to investigate the level of assistance that a handheld robot utilising shared control methods should provide during a spraying task. Using a handheld spraying robot with a moving spray head did not aid the user much over simply actuating spray nozzle for them. Compared to manual control the automatic modes significantly reduced the task load experienced by the user and significantly increased the quality of the result of the spraying task, reducing the error by 33-45%.

Journal article

Cully AHR, Demiris Y, 2018,

Quality and diversity optimization: a unifying modular framework

, IEEE Transactions on Evolutionary Computation, Vol: 22, Pages: 245-259, ISSN: 1941-0026

The optimization of functions to find the best solution according to one or several objectives has a central role in many engineering and research fields. Recently, a new family of optimization algorithms, named Quality-Diversity optimization, has been introduced, and contrasts with classic algorithms. Instead of searching for a single solution, Quality-Diversity algorithms are searching for a large collection of both diverse and high-performing solutions. The role of this collection is to cover the range of possible solution types as much as possible, and to contain the best solution for each type. The contribution of this paper is threefold. Firstly, we present a unifying framework of Quality-Diversity optimization algorithms that covers the two main algorithms of this family (Multi-dimensional Archive of Phenotypic Elites and the Novelty Search with Local Competition), and that highlights the large variety of variants that can be investigated within this family. Secondly, we propose algorithms with a new selection mechanism for Quality-Diversity algorithms that outperforms all the algorithms tested in this paper. Lastly, we present a new collection management that overcomes the erosion issues observed when using unstructured collections. These three contributions are supported by extensive experimental comparisons of Quality-Diversity algorithms on three different experimental scenarios.

Journal article

Fischer T, Puigbo J-Y, Camilleri D, Nguyen PDH, Moulin-Frier C, Lallee S, Metta G, Prescott TJ, Demiris Y, Verschure Pet al., 2018,

iCub-HRI: A software framework for complex human-robot interaction scenarios on the iCub humanoid robot

, Frontiers in Robotics and AI, Vol: 5, Pages: 1-9, ISSN: 2296-9144

Generating complex, human-like behaviour in a humanoid robot like the iCub requires the integration of a wide range of open source components and a scalable cognitive architecture. Hence, we present the iCub-HRI library which provides convenience wrappers for components related to perception (object recognition, agent tracking, speech recognition, touch detection), object manipulation (basic and complex motor actions) and social interaction (speech synthesis, joint attention) exposed as a C++ library with bindings for Java (allowing to use iCub-HRI within Matlab) and Python. In addition to previously integrated components, the library allows for simple extension to new components and rapid prototyping by adapting to changes in interfaces between components. We also provide a set of modules which make use of the library, such as a high-level knowledge acquisition module and an action recognition module. The proposed architecture has been successfully employed for a complex human-robot interaction scenario involving the acquisition of language capabilities, execution of goal-oriented behaviour and expression of a verbal narrative of the robot's experience in the world. Accompanying this paper is a tutorial which allows a subset of this interaction to be reproduced. The architecture is aimed at researchers familiarising themselves with the iCub ecosystem, as well as expert users, and we expect the library to be widely used in the iCub community.

Conference paper

Zhang F, Cully A, Demiris YIANNIS, 2017,

Personalized Robot-assisted Dressing using User Modeling in Latent Spaces

, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Publisher: IEEE, ISSN: 2153-0866

Robots have the potential to provide tremendous support to disabled and elderly people in their everyday tasks, such as dressing. Many recent studies on robotic dressing assistance usually view dressing as a trajectory planning problem. However, the user movements during the dressing process are rarely taken into account, which often leads to the failures of the planned trajectory and may put the user at risk. The main difficulty of taking user movements into account is caused by severe occlusions created by the robot, the user, and the clothes during the dressing process, which prevent vision sensors from accurately detecting the postures of the user in real time. In this paper, we address this problem by introducing an approach that allows the robot to automatically adapt its motion according to the force applied on the robot's gripper caused by user movements. There are two main contributions introduced in this paper: 1) the use of a hierarchical multi-task control strategy to automatically adapt the robot motion and minimize the force applied between the user and the robot caused by user movements; 2) the online update of the dressing trajectory based on the user movement limitations modeled with the Gaussian Process Latent Variable Model in a latent space, and the density information extracted from such latent space. The combination of these two contributions leads to a personalized dressing assistance that can cope with unpredicted user movements during the dressing while constantly minimizing the force that the robot may apply on the user. The experimental results demonstrate that the proposed method allows the Baxter humanoid robot to provide personalized dressing assistance for human users with simulated upper-body impairments.

Conference paper

Choi J, Chang HJ, Yun S, Fischer T, Demiris Y, Choi JYet al., 2017,

Attentional correlation filter network for adaptive visual tracking

, IEEE Conference on Computer Vision and Pattern Recognition, Publisher: IEEE, ISSN: 1063-6919

We propose a new tracking framework with an attentional mechanism that chooses a subset of the associated correlation filters for increased robustness and computational efficiency. The subset of filters is adaptively selected by a deep attentional network according to the dynamic properties of the tracking target. Our contributions are manifold, and are summarised as follows: (i) Introducing the Attentional Correlation Filter Network which allows adaptive tracking of dynamic targets. (ii) Utilising an attentional network which shifts the attention to the best candidate modules, as well as predicting the estimated accuracy of currently inactive modules. (iii) Enlarging the variety of correlation filters which cover target drift, blurriness, occlusion, scale changes, and flexible aspect ratio. (iv) Validating the robustness and efficiency of the attentional mechanism for visual tracking through a number of experiments. Our method achieves similar performance to non real-time trackers, and state-of-the-art performance amongst real-time trackers.

Conference paper

Yoo YJ, Chang H, Yun S, Demiris Y, Choi JYet al., 2017,

Variational autoencoded regression: high dimensional regression of visual data on complex manifold

, IEEE Conference on Computer Vision and Pattern Recognition, Publisher: IEEE, Pages: 2943-2952

This paper proposes a new high dimensional regression method by merging Gaussian process regression into a variational autoencoder framework. In contrast to other regression methods, the proposed method focuses on the case where output responses are on a complex high dimensional manifold, such as images. Our contributions are summarized as follows: (i) A new regression method estimating high dimensional image responses, which is not handled by existing regression algorithms, is proposed. (ii) The proposed regression method introduces a strategy to learn the latent space as well as the encoder and decoder so that the result of the regressed response in the latent space coincide with the corresponding response in the data space. (iii) The proposed regression is embedded into a generative model, and the whole procedure is developed by the variational autoencoder framework. We demonstrate the robustness and effectiveness of our method through a number of experiments on various visual data regression problems.

Journal article

Chang HJ, Demiris Y, 2017,

Highly articulated kinematic structure estimation combining motion and skeleton information

, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol: 40, Pages: 2165-2179, ISSN: 0162-8828

In this paper, we present a novel framework for unsupervised kinematic structure learning of complex articulated objects from a single-view 2D image sequence. In contrast to prior motion-based methods, which estimate relatively simple articulations, our method can generate arbitrarily complex kinematic structures with skeletal topology via a successive iterative merging strategy. The iterative merge process is guided by a density weighted skeleton map which is generated from a novel object boundary generation method from sparse 2D feature points. Our main contributions can be summarised as follows: (i) An unsupervised complex articulated kinematic structure estimation method that combines motion segments with skeleton information. (ii) An iterative fine-to-coarse merging strategy for adaptive motion segmentation and structural topology embedding. (iii) A skeleton estimation method based on a novel silhouette boundary generation from sparse feature points using an adaptive model selection method. (iv) A new highly articulated object dataset with ground truth annotation. We have verified the effectiveness of our proposed method in terms of computational time and estimation accuracy through rigorous experiments. Our experiments show that the proposed method outperforms state-of-the-art methods both quantitatively and qualitatively.

Conference paper

Elsdon J, Demiris Y, 2017,

Assisted painting of 3D structures using shared control with a hand-held robot

, IEEE International Conference on Robotics and Automation, Publisher: IEEE, Pages: 4891-4897

Abstract— We present a shared control method of painting3D geometries, using a handheld robot which has a singleautonomously controlled degree of freedom. The user scansthe robot near to the desired painting location, the singlemovement axis moves the spray head to achieve the requiredpaint distribution. A simultaneous simulation of the sprayingprocedure is performed, giving an open loop approximationof the current state of the painting. An online prediction ofthe best path for the spray nozzle actuation is calculated ina receding horizon fashion. This is calculated by producing amap of the paint required in the 2D space defined by nozzleposition on the gantry and the time into the future. A directedgraph then extracts its edge weights from this paint density mapand Dijkstra’s algorithm is then used to find the candidate forthe most effective path. Due to the heavy parallelisation of thisapproach and the majority of the calculations taking place on aGPU we can run the prediction loop in 32.6ms for a predictionhorizon of 1 second, this approach is computationally efficient,outperforming a greedy algorithm. The path chosen by theproposed method on average chooses a path in the top 15%of all paths as calculated by exhaustive testing. This approachenables development of real time path planning for assistedspray painting onto complicated 3D geometries. This methodcould be applied to applications such as assistive painting forpeople with disabilities, or accurate placement of liquid whenlarge scale positioning of the head is too expensive.

Journal article

Georgiou T, Demiris Y, 2017,

Adaptive user modelling in car racing games using behavioural and physiological data

, User Modeling and User-Adapted Interaction, Vol: 27, Pages: 267-311, ISSN: 1573-1391

Personalised content adaptation has great potential to increase user engagement in video games. Procedural generation of user-tailored content increases the self-motivation of players as they immerse themselves in the virtual world. An adaptive user model is needed to capture the skills of the player and enable automatic game content altering algorithms to fit the individual user. We propose an adaptive user modelling approach using a combination of unobtrusive physiological data to identify strengths and weaknesses in user performance in car racing games. Our system creates user-tailored tracks to improve driving habits and user experience, and to keep engagement at high levels. The user modelling approach adopts concepts from the Trace Theory framework; it uses machine learning to extract features from the user’s physiological data and game-related actions, and cluster them into low level primitives. These primitives are transformed and evaluated into higher level abstractions such as experience, exploration and attention. These abstractions are subsequently used to provide track alteration decisions for the player. Collection of data and feedback from 52 users allowed us to associate key model variables and outcomes to user responses, and to verify that the model provides statistically significant decisions personalised to the individual player. Tailored game content variations between users in our experiments, as well as the correlations with user satisfaction demonstrate that our algorithm is able to automatically incorporate user feedback in subsequent procedural content generation.

Conference paper

Georgiou T, Demiris Y, 2017,

Personalised Track Design in Car Racing Games

, Computational Intelligence and Games, Publisher: IEEE, ISSN: 2325-4289

Real-time adaptation of computer games’ content tothe users’ skills and abilities can enhance the player’s engagementand immersion. Understanding of the user’s potential whileplaying is of high importance in order to allow the successfulprocedural generation of user-tailored content. We investigatehow player models can be created in car racing games. Our usermodel uses a combination of data from unobtrusive sensors, whilethe user is playing a car racing simulator. It extracts featuresthrough machine learning techniques, which are then used tocomprehend the user’s gameplay, by utilising the educationaltheoretical frameworks of the Concept of Flow and Zone ofProximal Development. The end result is to provide at a nextstage a new track that fits to the user needs, which aids boththe training of the driver and their engagement in the game.In order to validate that the system is designing personalisedtracks, we associated the average performance from 41 usersthat played the game, with the difficulty factor of the generatedtrack. In addition, the variation in paths of the implementedtracks between users provides a good indicator for the suitabilityof the system.

Journal article

Korkinof D, Demiris Y, 2016,

Multi-task and multi-kernel gaussian process dynamical systems

, Pattern Recognition, Vol: 66, Pages: 190-201, ISSN: 1873-5142

In this work, we propose a novel method for rectifying damaged motion sequences in an unsupervised manner. In order to achieve maximal accuracy, the proposed model takes advantage of three key properties of the data: their sequential nature, the redundancy that manifests itself among repetitions of the same task, and the potential of knowledge transfer across different tasks. In order to do so, we formulate a factor model consisting of Gaussian Process Dynamical Systems (GPDS), where each factor corresponds to a single basic pattern in time and is able to represent their sequential nature. Factors collectively form a dictionary of fundamental trajectories shared among all sequences, thus able to capture recurrent patterns within the same or across different tasks. We employ variational inference to learn directly from incomplete sequences and perform maximum a-posteriori (MAP) estimates of the missing values. We have evaluated our model with a number of motion datasets, including robotic and human motion capture data. We have compared our approach to well-established methods in the literature in terms of their reconstruction error and our results indicate significant accuracy improvement across different datasets and missing data ratios. Concluding, we investigate the performance benefits of the multi-task learning scenario and how this improvement relates to the extent of component sharing that takes place.

Conference paper

Choi J, Chang H, Jeong J, Demiris Y, Choi JYet al., 2016,

Visual tracking using attention-modulated disintegration and integration

, IEEE Conference on Computer Vision and Pattern Recognition, Publisher: IEEE, ISSN: 1063-6919

In this paper, we present a novel attention-modulatedvisual tracking algorithm that decomposes an object intointo multiple cognitive units, and trains multiple elemen-tary trackers in order to modulate the distribution of at-tention according to various feature and kernel types. Inthe integration stage it recombines the units to memorizeand recognize the target object effectively. With respectto the elementary trackers, we present a novel attentionalfeature-based correlation filter (AtCF) that focuses on dis-tinctive attentional features. The effectiveness of the pro-posed algorithm is validated through experimental compar-ison with state-of-the-art methods on widely-used trackingbenchmark datasets.

Conference paper

Chang HJ, Fischer T, Petit M, Zambelli M, Demiris Yet al., 2016,

Kinematic structure correspondences via hypergraph matching

, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Publisher: IEEE, Pages: 4216-4225, ISSN: 1063-6919

In this paper, we present a novel framework for finding the kinematic structure correspondence between two objects in videos via hypergraph matching. In contrast to prior appearance and graph alignment based matching methods which have been applied among two similar static images, the proposed method finds correspondences between two dynamic kinematic structures of heterogeneous objects in videos. Our main contributions can be summarised as follows: (i) casting the kinematic structure correspondence problem into a hypergraph matching problem, incorporating multi-order similarities with normalising weights, (ii) a structural topology similarity measure by a new topology constrained subgraph isomorphism aggregation, (iii) a kinematic correlation measure between pairwise nodes, and (iv) a combinatorial local motion similarity measure using geodesic distance on the Riemannian manifold. We demonstrate the robustness and accuracy of our method through a number of experiments on complex articulated synthetic and real data.

Conference paper

Zambelli M, Demiris Y, 2016,

Multimodal Imitation using Self-learned Sensorimotor Representations

, IEEE/RSJ International Conference on Intelligent Robots and Systems, Publisher: IEEE, ISSN: 2153-0866

Although many tasks intrinsically involve multiplemodalities, often only data from a single modality are used toimprove complex robots acquisition of new skills. We presenta method to equip robots with multimodal learning skills toachieve multimodal imitation on-the-fly on multiple concurrenttask spaces, including vision, touch and proprioception, onlyusing self-learned multimodal sensorimotor relations, withoutthe need of solving inverse kinematic problems or explicit analyticalmodels formulation. We evaluate the proposed methodon a humanoid iCub robot learning to interact with a pianokeyboard and imitating a human demonstration. Since noassumptions are made on the kinematic structure of the robot,the method can be also applied to different robotic platforms.

Conference paper

Gao Y, Chang HJ, Demiris Y, 2016,

Iterative Path Optimisation for Personalised Dressing Assistance using Vision and Force Information

, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Publisher: IEEE, ISSN: 2153-0866

We propose an online iterative path optimisationmethod to enable a Baxter humanoid robot to assist humanusers to dress. The robot searches for the optimal personaliseddressing path using vision and force sensor information: visioninformation is used to recognise the human pose and model themovement space of upper-body joints; force sensor informationis used for the robot to detect external force resistance andto locally adjust its motion. We propose a new stochastic pathoptimisation method based on adaptive moment estimation. Wefirst compare the proposed method with other path optimisationalgorithms on synthetic data. Experimental results show thatthe performance of the method achieves the smallest error withfewer iterations and less computation time. We also evaluatereal-world data by enabling the Baxter robot to assist realhuman users with their dressing.

Journal article

Zambelli M, Demiris Y, 2016,

Online multimodal ensemble learning using self-learned sensorimotor representations

, IEEE Transactions on Cognitive and Developmental Systems, Vol: 9, Pages: 113-126, ISSN: 2379-8920

Internal models play a key role in cognitive agentsby providing on the one hand predictions of sensory consequencesof motor commands (forward models), and on the other handinverse mappings (inverse models) to realise tasks involvingcontrol loops, such as imitation tasks. The ability to predictand generate new actions in continuously evolving environmentsintrinsically requiring the use of different sensory modalities isparticularly relevant for autonomous robots, which must alsobe able to adapt their models online. We present a learningarchitecture based on self-learned multimodal sensorimotor rep-resentations. To attain accurate forward models, we propose anonline heterogeneous ensemble learning method that allows usto improve the prediction accuracy by leveraging differences ofmultiple diverse predictors. We further propose a method tolearn inverse models on-the-fly to equip a robot with multimodallearning skills to perform imitation tasks using multiple sensorymodalities. We have evaluated the proposed methods on aniCub humanoid robot. Since no assumptions are made on therobot kinematic/dynamic structure, the method can be appliedto different robotic platforms.

Conference paper

Petit M, Fischer T, Demiris Y, 2016,

Towards the Emergence of Procedural Memories from Lifelong Multi-Modal Streaming Memories for Cognitive Robots

, Workshop on Machine Learning Methods for High-Level Cognitive Capabilities in Robotics at IEEE/RSJ IROS

Various research topics are emerging as the demand for intelligent lifelong interactions between robot and humans increases. Among them, we can find the examination of persistent storage, the continuous unsupervised annotation of memories and the usage of data at high-frequency over long periods of time. We recently proposed a lifelong autobiographical memory architecture tackling some of these challenges, allowing the iCub humanoid robot to 1) create new memories for both actions that are self-executed and observed from humans, 2) continuously annotate these actions in an unsupervised manner, and 3) use reasoning modules to augment these memories a-posteriori. In this paper, we present a reasoning algorithm which generalises the robots’ understanding of actions by finding the point of commonalities with the former ones. In particular, we generated and labelled templates of pointing actions in different directions. This represents a first step towards the emergence of a procedural memory within a long-term autobiographical memory framework for robots.

Conference paper

Zambelli M, Fischer T, Petit M, Chang HJ, Cully A, Demiris Yet al., 2016,

Towards Anchoring Self-Learned Representations to Those of Other Agents

, Workshop on Bio-inspired Social Robot Learning in Home Scenarios IEEE/RSJ International Conference on Intelligent Robots and Systems, Publisher: Institute of Electrical and Electronics Engineers (IEEE)

In the future, robots will support humans in their every day activities. One particular challenge that robots will face is understanding and reasoning about the actions of other agents in order to cooperate effectively with humans. We propose to tackle this using a developmental framework, where the robot incrementally acquires knowledge, and in particular 1) self-learns a mapping between motor commands and sensory consequences, 2) rapidly acquires primitives and complex actions by verbal descriptions and instructions from a human partner, 3) discoverscorrespondences between the robots body and other articulated objects and agents, and 4) employs these correspondences to transfer the knowledge acquired from the robots point of view to the viewpoint of the other agent. We show that our approach requires very little a-priori knowledge to achieve imitation learning, to find correspondent body parts of humans, and allows taking the perspective of another agent. This represents a step towards the emergence of a mirror neuron like system based on self-learned representations.

Journal article

Petit M, Fischer T, Demiris Y, 2016,

Lifelong Augmentation of Multi-Modal Streaming Autobiographical Memories

, IEEE Transactions on Cognitive and Developmental Systems, Vol: 8, Pages: 201-213, ISSN: 2379-8920

Robot systems that interact with humans over extended periods of time will benefit from storing and recalling large amounts of accumulated sensorimotor and interaction data. We provide a principled framework for the cumulative organisation of streaming autobiographical data so that data can be continuously processed and augmented as the processing and reasoning abilities of the agent develop and further interactions with humans take place. As an example, we show how a kinematic structure learning algorithm reasons a-posteriori about the skeleton of a human hand. A partner can be asked to provide feedback about the augmented memories, which can in turn be supplied to the reasoning processes in order to adapt their parameters. We employ active, multi-modal remembering, so the robot as well as humans can gain insights of both the original and augmented memories. Our framework is capable of storing discrete and continuous data in real-time. The data can cover multiple modalities and several layers of abstraction (e.g. from raw sound signals over sentences to extracted meanings). We show a typical interaction with a human partner using an iCub humanoid robot. The framework is implemented in a platform-independent manner. In particular, we validate its multi platform capabilities using the iCub, Baxter and NAO robots. We also provide an interface to cloud based services, which allow automatic annotation of episodes. Our framework is geared towards the developmental robotics community, as it 1) provides a variety of interfaces for other modules, 2) unifies previous works on autobiographical memory, and 3) is licensed as open source software.

Conference paper

Gao Y, Chang HJ, Demiris Y, 2016,

Personalised assistive dressing by humanoid robots using multi-modal information

, Workshop on Human-Robot Interfaces for Enhanced Physical Interactions at ICRA

In this paper, we present an approach to enable a humanoid robot to provide personalised dressing assistance for human users using multi-modal information. A depth sensor is mounted on top of the robot to provide visual information, and the robot end effectors are equipped with force sensors to provide haptic information. We use visual information to model the movement range of human upper-body parts. The robot plans the dressing motions using the movement rangemodels and real-time human pose. During assistive dressing, the force sensors are used to detect external force resistances. We present how the robot locally adjusts its motions based on the detected forces. In the experiments we show that the robot can assist human to wear a sleeveless jacket while reacting tothe force resistances.

Conference paper

Fischer T, Demiris Y, 2016,

Markerless Perspective Taking for Humanoid Robots in Unconstrained Environments

, 2016 IEEE International Conference on Robotics and Automation (ICRA), Publisher: IEEE, Pages: 3309-3316

Perspective taking enables humans to imagine the world from another viewpoint. This allows reasoning about the state of other agents, which in turn is used to more accurately predict their behavior. In this paper, we equip an iCub humanoid robot with the ability to perform visuospatial perspective taking (PT) using a single depth camera mounted above the robot. Our approach has the distinct benefit that the robot can be used in unconstrained environments, as opposed to previous works which employ marker-based motion capture systems. Prior to and during the PT, the iCub learns the environment, recognizes objects within the environment, and estimates the gaze of surrounding humans. We propose a new head pose estimation algorithm which shows a performance boost by normalizing the depth data to be aligned with the human head. Inspired by psychological studies, we employ two separate mechanisms for the two different types of PT. We implement line of sight tracing to determine whether an object is visible to the humans (level 1 PT). For more complex PT tasks (level 2 PT), the acquired point cloud is mentally rotated, which allows algorithms to reason as if the input data was acquired from an egocentric perspective. We show that this can be used to better judge where object are in relation to the humans. The multifaceted improvements to the PT pipeline advance the state of the art, and move PT in robots to markerless, unconstrained environments.

Conference paper

Petit M, Demiris Y, 2016,

Hierarchical action learning by instruction through interactive grounding of body parts and proto-actions

, IEEE International Conference on Robotics and Automation, Publisher: IEEE, Pages: 3375-3382

Learning by instruction allows humans programming a robot to achieve a task using spoken language, without the requirement of being able to do the task themselves, which can be problematic for users with motor impairments. We provide a developmental framework to program the humanoid robot iCub without any hand-coded a-priori knowledge about any motor skills. Inspired by child development theories, the system involves hierarchical learning, starting with the human verbally labelling robot body parts. The robot can then focus its attention on a precise body part during robot motor babbling, and link the on-the-fly spoken descriptions of proto-actions to angle values of a specific joint. The direct grounding of proto-actions is possible through the use of a linear model which calculates the effects on the joint of the proto-action and the body part used, allowing a generalisation of the proto-action if the joint has never been used before. Eventually, transferring the grounding is allowed via learning by instructions where humans can combine the newly acquired proto-actions to build primitives and more complex actions by scaffolding them. The framework has been validated using a humanoid robot iCub, which is able to learn without any prior knowledge: 1) the name of its fingers and the corresponding joint number, 2) how to fold and unfold them and 3) how to close or open its hand and how to show numbers with its fingers.

Journal article

Lee K, Ognibene D, Chang H, Kim T-K, Demiris Yet al., 2015,

STARE: Spatio-Temporal Attention Relocation for multiple structured activities detection

, IEEE Transactions on Image Processing, Vol: 24, Pages: 5916-5927, ISSN: 1057-7149

We present a spatio-temporal attention relocation (STARE) method, an information-theoretic approach for efficient detection of simultaneously occurring structured activities. Given multiple human activities in a scene, our method dynamically focuses on the currently most informative activity. Each activity can be detected without complete observation, as the structure of sequential actions plays an important role on making the system robust to unattended observations. For such systems, the ability to decide where and when to focus is crucial to achieving high detection performances under resource bounded condition. Our main contributions can be summarized as follows: 1) information-theoretic dynamic attention relocation framework that allows the detection of multiple activities efficiently by exploiting the activity structure information and 2) a new high-resolution data set of temporally-structured concurrent activities. Our experiments on applications show that the STARE method performs efficiently while maintaining a reasonable level of accuracy.

Conference paper

Gao Y, Chang HJ, Demiris Y, 2015,

User Modelling for Personalised Dressing Assistance by Humanoid Robots

, International Conference on Intelligent Systems and Robots (IROS), Publisher: IEEE, Pages: 1840-1845

Assistive robots can improve the well-being of disabled or frail human users by reducing the burden that activities of daily living impose on them. To enable personalised assistance, such robots benefit from building a user-specific model, so that the assistance is customised to the particular set of user abilities. In this paper, we present an end-to-end approach for home-environment assistive humanoid robots to provide personalised assistance through a dressing application for users who have upper-body movement limitations. We use randomised decision forests to estimate the upper-body pose of users captured by a top-view depth camera, and model the movement space of upper-body joints using Gaussian mixture models. The movement space of each upper-body joint consists of regions with different reaching capabilities. We propose a method which is based on real-time upper-body pose and user models to plan robot motions for assistive dressing. We validate each part of our approach and test the whole system, allowing a Baxter humanoid robot to assist human to wear a sleeveless jacket.

Conference paper

Zambelli M, Demiris Y, 2015,

Online Ensemble Learning of Sensorimotor Contingencies

, Workshop on Sensorimotor Contingencies For Robotics at IROS

Forward models play a key role in cognitive agents by providing predictions of the sensory consequences of motor commands, also known as sensorimotor contingencies (SMCs). In continuously evolving environments, the ability to anticipate is fundamental in distinguishing cognitive from reactive agents, and it is particularly relevant for autonomous robots, that must be able to adapt their models in an online manner. Online learning skills, high accuracy of the forward models and multiple-step-ahead predictions are needed to enhance the robots’ anticipation capabilities. We propose an online heterogeneous ensemble learning method for building accurate forward models of SMCs relating motor commands to effects in robots’ sensorimotor system, in particular considering proprioception and vision. Our method achieves up to 98% higher accuracy both in short and long term predictions, compared to single predictors and other online and offline homogeneous ensembles. This method is validated on two different humanoid robots, namely the iCub and the Baxter.

Conference paper

Kormushev P, Demiris Y, Caldwell DG, 2015,

Kinematic-free Position Control of a 2-DOF Planar Robot Arm

Conference paper

Sarabia M, Lee K, Demiris Y, 2015,

Towards a Synchronised Grammars Framework for Adaptive Musical Human-Robot Collaboration

, IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), Publisher: IEEE, Pages: 715-721

We present an adaptive musical collaboration framework for interaction between a human and a robot. The aim of our work is to develop a system that receives feedback from the user in real time and learns the music progression style of the user over time. To tackle this problem, we represent a song as a hierarchically structured sequence of music primitives. By exploiting the sequential constraints of these primitives inferred from the structural information combined with user feedback, we show that a robot can play music in accordance with the user’s anticipated actions. We use Stochastic Context-Free Grammars augmented with the knowledge of the learnt user’s preferences.We provide synthetic experiments as well as a pilot study with a Baxter robot and a tangible music table. The synthetic results show the synchronisation and adaptivity features of our framework and the pilot study suggest these are applicable to create an effective musical collaboration experience.

Conference paper

Kucukyilmaz A, Demiris Y, 2015,

One-shot assistance estimation from expert demonstrations for a shared control wheelchair system

, International Symposium on Robot and Human Interactive Communication (RO-MAN), Publisher: IEEE, Pages: 438-443

An emerging research problem in the field of assistive robotics is the design of methodologies that allow robots to provide human-like assistance to the users. Especially within the rehabilitation domain, a grand challenge is to program a robot to mimic the operation of an occupational therapist, intervening with the user when necessary so as to improve the therapeutic power of the assistive robotic system. We propose a method to estimate assistance policies from expert demonstrations to present human-like intervention during navigation in a powered wheelchair setup. For this purpose, we constructed a setting, where a human offers assistance to the user over a haptic shared control system. The robot learns from human assistance demonstrations while the user is actively driving the wheelchair in an unconstrained environment. We train a Gaussian process regression model to learn assistance commands given past and current actions of the user and the state of the environment. The results indicate that the model can estimate human assistance after only a single demonstration, i.e. in one-shot, so that the robot can help the user by selecting the appropriate assistance in a human-like fashion.

Conference paper

Georgiou T, Demiris Y, 2015,

Predicting car states through learned models of vehicle dynamics and user behaviours

, Intelligent Vehicles Symposium (IV), Publisher: IEEE, Pages: 1240-1245

The ability to predict forthcoming car states is crucial for the development of smart assistance systems. Forthcoming car states do not only depend on vehicle dynamics but also on user behaviour. In this paper, we describe a novel prediction methodology by combining information from both sources - vehicle and user - using Gaussian Processes. We then apply this method in the context of high speed car racing. Results show that the forthcoming position and speed of the car can be predicted with low Root Mean Square Error through the trained model.

Conference paper

Chang HJ, Demiris Y, 2015,

Unsupervised Learning of Complex Articulated Kinematic Structures combining Motion and Skeleton Information

, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Publisher: IEEE, Pages: 3138-3146

In this paper we present a novel framework for unsupervised kinematic structure learning of complex articulated objects from a single-view image sequence. In contrast to prior motion information based methods, which estimate relatively simple articulations, our method can generate arbitrarily complex kinematic structures with skeletal topology by a successive iterative merge process. The iterative merge process is guided by a skeleton distance function which is generated from a novel object boundary generation method from sparse points. Our main contributions can be summarised as follows: (i) Unsupervised complex articulated kinematic structure learning by combining motion and skeleton information. (ii) Iterative fine-to-coarse merging strategy for adaptive motion segmentation and structure smoothing. (iii) Skeleton estimation from sparse feature points. (iv) A new highly articulated object dataset containing multi-stage complexity with ground truth. Our experiments show that the proposed method out-performs state-of-the-art methods both quantitatively and qualitatively.

Conference paper

Kormushev P, Demiris Y, Caldwell DG, 2015,

Encoderless Position Control of a Two-Link Robot Manipulator

Journal article

Soh H, Demiris Y, 2015,

Spatio-temporal learning with the online finite and infinite echo-state Gaussian processes

, IEEE Transactions on Neural Networks and Learning Systems, Vol: 26, Pages: 522-536, ISSN: 2162-2388

Successful biological systems adapt to change. In this paper, we are principally concerned with adaptive systems that operate in environments where data arrives sequentially and is multivariate in nature, for example, sensory streams in robotic systems. We contribute two reservoir inspired methods: 1) the online echostate Gaussian process (OESGP) and 2) its infinite variant, the online infinite echostate Gaussian process (OIESGP) Both algorithms are iterative fixed-budget methods that learn from noisy time series. In particular, the OESGP combines the echo-state network with Bayesian online learning for Gaussian processes. Extending this to infinite reservoirs yields the OIESGP, which uses a novel recursive kernel with automatic relevance determination that enables spatial and temporal feature weighting. When fused with stochastic natural gradient descent, the kernel hyperparameters are iteratively adapted to better model the target system. Furthermore, insights into the underlying system can be gleamed from inspection of the resulting hyperparameters. Experiments on noisy benchmark problems (one-step prediction and system identification) demonstrate that our methods yield high accuracies relative to state-of-the-art methods, and standard kernels with sliding windows, particularly on problems with irrelevant dimensions. In addition, we describe two case studies in robotic learning-by-demonstration involving the Nao humanoid robot and the Assistive Robot Transport for Youngsters (ARTY) smart wheelchair.

Journal article

Wu Y, Su Y, Demiris Y, 2014,

A morphable template framework for robot learning by demonstration: Integrating one-shot and incremental learning approaches

, Robotics and Autonomous Systems, Vol: 62, Pages: 1517-1530

Robot learning by demonstration is key to bringing robots into daily social environments to interact with and learn from human and other agents. However, teaching a robot to acquire new knowledge is a tedious and repetitive process and often restrictive to a specific setup of the environment. We propose a template-based learning framework for robot learning by demonstration to address both generalisation and adaptability. This novel framework is based upon a one-shot learning model integrated with spectral clustering and an online learning model to learn and adapt actions in similar scenarios. A set of statistical experiments is used to benchmark the framework components and shows that this approach requires no extensive training for generalisation and can adapt to environmental changes flexibly. Two real-world applications of an iCub humanoid robot playing the tic-tac-toe game and soldering a circuit board are used to demonstrate the relative merits of the framework.

Conference paper

Su Y, Dong W, Wu Y, Du Z, Demiris Yet al., 2014,

Increasing the Accuracy and the Repeatability of Position Control for Micromanipulations Using Heteroscedastic Gaussian Processes

, IEEE International Conference on Robotics and Automation (ICRA 2014), Pages: 4692-4698

Many recent studies describe micromanipulation systems by using complex Analytic Forward Models (AFM), but such models are difficult to build and incapable of describing unmodelable factors, such as manufacturing defects. In this work, we propose the Enhanced Analytic Forward Model (EAFM), an integrated model of the AFM and the Heteroscedastic Gaussian Processes (HGP). The EAFM can compensate the shortfalls of the AFM by training the HGP on the residual of the AFM. This also allows the HGP to learn the repeatability of the micromanipulation system. Based on the EAFM, we further contribute an optimal position controller for improving the accuracy and the repeatability. This optimal EAFM controller is implemented and tested on a three degree-of-freedom micromanipulator based micromanipulation system. Two sets of real-world experiments are carried out to verify our method. The results demonstrate that the controller using EAFM can statistically achieve higher accuracy and repeatability than solely using the AFM.

Journal article

Soh H, Demiris Y, 2014,

Incrementally Learning Objects by Touch: Online Discriminative and Generative Models for Tactile-Based Recognition

, IEEE Transactions on Haptics, Vol: 7, Pages: 512-525, ISSN: 1939-1412

Human beings not only possess the remarkable ability to distinguish objects through tactile feedback but are further able to improve upon recognition competence through experience. In this work, we explore tactile-based object recognition with learners capable of incremental learning. Using the sparse online infinite Echo-State Gaussian process (OIESGP), we propose and compare two novel discriminative and generative tactile learners that produce probability distributions over objects during object grasping/ palpation. To enable iterative improvement, our online methods incorporate training samples as they become available. We also describe incremental unsupervised learning mechanisms, based on novelty scores and extreme value theory, when teacher labels are not available. We present experimental results for both supervised and unsupervised learning tasks using the iCub humanoid, with tactile sensors on its five-fingered anthropomorphic hand, and 10 different object classes. Our classifiers perform comparably to state-of-the-art methods (C4.5 and SVM classifiers) and findings indicate that tactile signals are highly relevant for making accurate object classifications. We also show that accurate “early” classifications are possible using only 20-30 percent of the grasp sequence. For unsupervised learning, our methods generate high quality clusterings relative to the widely-used sequential k-means and self-organising map (SOM), and we present analyses into the differences between the approaches.

Journal article

Ros R, Baroni I, Demiris Y, 2014,

Adaptive human-robot interaction in sensorimotor task instruction: From human to robot dance tutors

, Robotics and Autonomous Systems, Vol: 62, Pages: 707-720, ISSN: 1872-793X

We explore the potential for humanoid robots to interact with children in a dance activity. In this context, the robot plays the role of an instructor to guide the child through several dance moves to learn a dance phrase. We participated in 30 dance sessions in schools to study human–human interaction between children and a human dance teacher, and to identify the applied methodologies. Based on the strategies observed, both social and task-dependent, we implemented a robotic system capable of autonomously instructing dance sequences to children while displaying basic social cues to engage the child in the task. Experiments were performed in a hospital with the Nao robot interacting with 12 children through multiple encounters, when possible (18 sessions, 236 min). Observational analysis through video recordings and survey evaluations were used to assess the quality of interaction. Moreover, we introduce an involvement measure based on the aggregation of observed behavioral cues to assess the level of interest in the interaction through time. The analysis revealed high levels of involvement, while highlighting the need for further research into social engagement and adaptation with robots over repeated sessions.

Conference paper

Ros R, Coninx A, Demiris Y, Patsis G, Enescu V, Sahli Het al., 2014,

Behavioral Accommodation towards a Dance Robot Tutor

, International Conference on Human-Robot Interaction, Publisher: ACM/IEEE, Pages: 278-279

We report first results on children adaptive behavior towards a dance tutoring robot. We can observe that children behavior rapidly evolves through few sessions in order to accommodate with the robotic tutor rhythm and instructions.

Abstract
Cite

Journal article

Demiris Y, Aziz-Zadeh L, Bonaiuto J, 2014,

Information Processing in the Mirror Neuron System in Primates and Machines

, Neuroinformatics, Vol: 12, Pages: 63-91, ISSN: 1539-2791

The mirror neuron system in primates matches observations of actions with the motor representations used for their execution, and is a topic of intense research and debate in biological and computational disciplines. In robotics, models of this system have been used for enabling robots to imitate and learn how to perform tasks from human demonstrations. Yet, existing computational and robotic models of these systems are found in multiple levels of description, and although some models offer plausible explanations and testable predictions, the difference in the granularity of the experimental setups, methodologies, computational structures and selected modeled data make principled meta-analyses, common in other fields, difficult. In this paper, we adopt an interdisciplinary approach, using the BODB integrated environment in order to bring together several different but complementary computational models, by functionally decomposing them into brain operating principles (BOPs) which each capture a limited subset of the model’s functionality. We then explore links from these BOPs to neuroimaging and neurophysiological data in order to pinpoint complementary and conflicting explanations and compare predictions against selected sets of neurobiological data. The results of this comparison are used to interpret mirror system neuroimaging results in terms of neural network activity, evaluate the biological plausibility of mirror system models, and suggest new experiments that can shed light on the neural basis of mirror systems.

Journal article

Lee K, Su Y, Kim T-K, Demiris Yet al., 2013,

A syntactic approach to robot imitation learning using probabilistic activity grammars

, Robotics and Autonomous Systems, Vol: 61, Pages: 1323-1334, ISSN: 0921-8890

This paper describes a syntactic approach to imitation learning that captures important task structures in the form of probabilistic activity grammars from a reasonably small number of samples under noisy conditions. We show that these learned grammars can be recursively applied to help recognize unforeseen, more complicated tasks that share underlying structures. The grammars enforce an observation to be consistent with the previously observed behaviors which can correct unexpected, out-of-context actions due to errors of the observer and/or demonstrator. To achieve this goal, our method (1) actively searches for frequently occurring action symbols that are subsets of input samples to uncover the hierarchical structure of the demonstration, and (2) considers the uncertainties of input symbols due to imperfect low-level detectors.We evaluate the proposed method using both synthetic data and two sets of real-world humanoid robot experiments. In our Towers of Hanoi experiment, the robot learns the important constraints of the puzzle after observing demonstrators solving it. In our Dance Imitation experiment, the robot learns 3 types of dances from human demonstrations. The results suggest that under reasonable amount of noise, our method is capable of capturing the reusable task structures and generalizing them to cope with recursions.

Conference paper

Korkinof D, Demiris Y, 2013,

Online Quantum Mixture Regression for Trajectory Learning by Demonstration

, IROS 2013, Publisher: IEEE, Pages: 3222-3229

In this work, we present the online Quantum Mixture Model (oQMM), which combines the merits of quan- tum mechanics and stochastic optimization. More specifically it allows for quantum effects on the mixture states, which in turn become a superposition of conventional mixture states. We propose an efficient stochastic online learning algorithm based on the online Expectation Maximization (EM), as well as a generation and decay scheme for model components. Our method is suitable for complex robotic applications, where data is abundant or where we wish to iteratively refine our model and conduct predictions during the course of learning. With a synthetic example, we show that the algorithm can achieve higher numerical stability. We also empirically demonstrate the efficacy of our method in well-known regression benchmark datasets. Under a trajectory Learning by Demonstration setting we employ a multi-shot learning application in joint angle space, where we observe higher quality of learning and reproduction. We compare against popular and well-established methods, widely adopted across the robotics community.

Conference paper

Korkinof D, Demiris Y, 2013,

Online Quantum Mixture Regression for Trajectory Learning by Demonstration

, International Conference on Intelligent Systems and Robots (IROS), Publisher: IEEE, Pages: 3222-3229, ISSN: 2153-0858

In this work, we present the online Quantum Mixture Model (oQMM), which combines the merits of quantum mechanics and stochastic optimization. More specifically it allows for quantum effects on the mixture states, which in turn become a superposition of conventional mixture states. We propose an efficient stochastic online learning algorithm based on the online Expectation Maximization (EM), as well as a generation and decay scheme for model components. Our method is suitable for complex robotic applications, where data is abundant or where we wish to iteratively refine our model and conduct predictions during the course of learning. With a synthetic example, we show that the algorithm can achieve higher numerical stability. We also empirically demonstrate the efficacy of our method in well-known regression benchmark datasets. Under a trajectory Learning by Demonstration setting we employ a multi-shot learning application in joint angle space, where we observe higher quality of learning and reproduction. We compare against popular and well-established methods, widely adopted across the robotics community.

Conference paper

Soh H, Demiris Y, 2013,

When and how to help: An iterative probabilistic model for learning assistance by demonstration

, International Conference on Intelligent Robots and Systems (IROS), Publisher: IEEE, Pages: 3230-3236, ISSN: 2153-0858

Crafting a proper assistance policy is a difficult endeavour but essential for the development of robotic assistants. Indeed, assistance is a complex issue that depends not only on the task-at-hand, but also on the state of the user, environment and competing objectives. As a way forward, this paper proposes learning the task of assistance through observation; an approach we term Learning Assistance by Demonstration (LAD). Our methodology is a subclass of Learning-by-Demonstration (LbD), yet directly addresses difficult issues associated with proper assistance such as when and how to appropriately assist. To learn assistive policies, we develop a probabilistic model that explicitly captures these elements and provide efficient, online, training methods. Experimental results on smart mobility assistance — using both simulation and a real-world smart wheelchair platform — demonstrate the effectiveness of our approach; the LAD model quickly learns when to assist (achieving an AUC score of 0.95 after only one demonstration) and improves with additional examples. Results show that this translates into better task-performance; our LAD-enabled smart wheelchair improved participant driving performance (measured in lap seconds) by 20.6s (a speedup of 137%), after a single teacher demonstration.

Conference paper

Ros R, Demiris Y, 2013,

Creative Dance: An Approach for Social Interaction between Robots and Children

, 4th International Workshop on Human Behavior Understanding (HBU), Publisher: Springer, Pages: 40-51, ISSN: 0302-9743

In this paper we discuss the potential of using a dance robot tutor with children in the context of creative dance to study child-robot interaction through several encounters. We have taken part of dance sessions in order to extract strategies and models to inspire and justify the design of a robot dance tutor. Moreover, we present implementation details and preliminary results on a pilot study to extract initial feedback to further improve and test our system with a broader children population.

Journal article

Ognibene D, Chinellato E, Sarabia M, Demiris Yet al., 2013,

Contextual action recognition and target localization with an active allocation of attention on a humanoid robot

, Bioinspiration & Biomimetics, Vol: 8

Exploratory gaze movements are fundamental for gathering the most relevant information regarding the partner during social interactions. Inspired by the cognitive mechanisms underlying human social behaviour, we have designed and implemented a system for a dynamic attention allocation which is able to actively control gaze movements during a visual action recognition task exploiting its own action execution predictions. Our humanoid robot is able, during the observation of a partner's reaching movement, to contextually estimate the goal position of the partner's hand and the location in space of the candidate targets. This is done while actively gazing around the environment, with the purpose of optimizing the gathering of information relevant for the task. Experimental results on a simulated environment show that active gaze control, based on the internal simulation of actions, provides a relevant advantage with respect to other action perception approaches, both in terms of estimation precision and of time required to recognize an action. Moreover, our model reproduces and extends some experimental results on human attention during an action perception.

Search or filter publications

Filter by type:

Filter by year:

Results

Search results

Augmented reality control of smart wheelchair using eye-gaze–enabled selection of affordances

A computational model for embodied visual perspective taking: from physical movements to mental simulation

Towards the Emergence of Procedural Memories from Lifelong Multi-Modal Streaming Memories for Cognitive Robots

Towards Anchoring Self-Learned Representations to Those of Other Agents

Personalised assistive dressing by humanoid robots using multi-modal information

User Modelling for Personalised Dressing Assistance by Humanoid Robots

Online Ensemble Learning of Sensorimotor Contingencies

Kinematic-free Position Control of a 2-DOF Planar Robot Arm

Encoderless Position Control of a Two-Link Robot Manipulator

Online Quantum Mixture Regression for Trajectory Learning by Demonstration

­