ABSTRACT. The paper describes the design of a cephalopod-inspired soft robot that is part of the art installation Tales of C (2017). Two soft modules for movement are presented, one actuated by a servo motor the other with pneumatics. It is shown that dynamic biomorphic movements can be realized with these modules using simple control signals (linear and constant changes).

ABSTRACT. Designing for kinaesthetic awareness, the perception of our body's position and movement, presents a unique set of challenges and opportunities. While these implications are relatively new in the HCI community, they resonate with theories from the field of embodied cognition, and methodological strategies developed in somatic practices. Still, moving is an interactive sound installation designed to support the perception of a person's micro-movements. We elaborate here on findings from a previous study, first emerged inductively from a grounded theory analysis of phenomenological interviews. Tracing the connections between these findings, and existing research in embodied cognition and somatic practices, reveals a range of distinctions and alternatives to flesh out the question: How can we understand and cultivate kinaesthetic awareness?

ABSTRACT. In this paper we explore an interdisciplinary approach towards an aesthetics of touch. Research into the role of the body has become increasingly prevalent in fields ranging from philosophy of mind to human-computer interaction. At the same time, haptic technology has becoming ubiquitous within personalized devices and wearables. Despite this, touch remains largely under-explored within contemporary aesthetics. We firstly outline what might be gained from artistic practices that acknowledge a multisensory model of perception. Secondly, we discuss the difficulties of arriving at a standardized taxonomy for touch-based aesthetics and why this endeavor may not be fruitful. Finally, we outline an approach based on first-person felt experiences, drawing on creative practice research involving computational technology within the fields of somatics, dance, and music.

ABSTRACT. Designing for and through movement is becoming increasingly important in human computer interaction, and it is widely accepted that the designers should develop their bodily skills and learn how to use the movement as design material. Yet, the reports on the education space around embodied interaction are scarce. We present an approach for teaching and designing embodied interaction in collaboration with contemporary dance choreographers. We describe a workshop, where after movement sessions, simple projects were implemented by the participants. The evaluation of projects and student feedback indicate that the four learning objectives, namely: 1) movement as a design material, 2) bodily skills needed for technological implementation, 3) movement qualities, and 4) practical projects, were attained for most of the participants. For some participants, however, the movement qualities were hard concepts to grasp and utilize in design, and this difficulty had an impact on all the other learning objectives. Further experiments with new tools, techniques, contexts, and guidelines are therefore required to highlight the importance of movement qualities in design.

ABSTRACT. The analysis and synthesis of human movement is both highly detailed and encompassing of larger patterns. In this experiential workshop, participants will identify their predilections, observational styles, and biases through an exploration of the various levels of movement analysis: from body part use and micro-facial expressions to interaction analysis and group behavior to gender and cultural patterns that manifest in dance, work, and common expressions.

The analysis work of Rudolf Laban and Irmgard Bartenieff, Paul Ekman, Ray Birdwhistell, Adam Kendon, Martha Davis, Alan Lomax and Forrestine Paulay addresses specific levels of detail or meta-pattern. We have organized these theories into four levels of analysis:

Individual Style

Dyadic Analysis

Group Behavior

Cultural Pattern

The proposed workshop will provide an experiential overview of the micro- and macro-levels of movement and will help participants determine the strata of observation and analysis necessary for the tasks at hand.

ABSTRACT. The ‘social dance’ is an implicit, yet vital, characteristic of dyadic interactions. Attempts to characterize this complex behavior have illustrated unconscious levels of content and temporal entrainment within artificial social contexts. Yet, when viewed in a naturalistic setting, this complex systems problem faces a number of methodological and theoretical challenges. Utilizing precise kinematic recordings while adopting the ‘micro-movement’ approach, cross coherence analysis and tenets of graph theory, this paper presents an analytical framework to characterize unfolding, nonlinear temporal exchange and entrainment across a social dyad. This framework is empirically demonstrated within a clinical domain of individuals with known social difficulties: Autism Spectrum Disorder (ASD). Results illustrate the ability for this objective methodology to quantify variability in social dynamics, and profile dyadic entrainment during naturalistic exchange—with no a priori constraints or limitations. Viewed within the context of a clinical assessment tool for ASD, results facilitate consideration of clinician impact on dyadic exchange, and point to a potential refinement of core tasks associated with such clinical batteries.

ABSTRACT. We propose a computational framework to learn stylisation patterns from example drawings or writings, and then generate new trajectories that possess similar stylistic qualities. We particularly focus on the generation and stylisation of trajectories that are similar to the ones that can be seen in calligraphy and graffiti art. Our system is able to extract and learn dynamic and visual qualities from a small number of user defined examples which can be recorded with a digitiser device, such as a tablet, mouse or motion capture sensors. Our system is then able to transform new user drawn traces to be kinematically and stylistically similar to the training examples. We implement the system using a Recurrent Mixture Density Network (RMDN) combined with a representation given by the parameters of the Sigma Lognormal model, a physiologically plausible model of movement that has been shown to closely reproduce the velocity and trace of human handwriting gestures.

ABSTRACT. In the recent domain of motion capture and analysis, a new exciting challenge has been the automatic evaluation of skill in gestures. Many researchers have already proposed methods for gesture evaluation, based on feature extraction, skill modeling and gesture comparison. However, movements can be influenced by many factors other than skill, including morphology. All these influences make comparison between gestures of different persons difficult. In this paper, we propose an original method based on constrained linear regression to remove morphology influence on motion features. To validate our method, we compare it to a baseline method, defined by a scaling of the skeleton data [14]. Results show that our method outperforms previous work both in removing morphology influence, and in improving skill influence. For a set of 326 features tested on two datasets of Taijiquan gestures, we show that morphology is completely removed for 100% of the features, whereas the baseline method only allows limited reduction of morphology influence for 74% of the features. Our method improves correlation with skill by 0.04 (p<0.0001) in average for 98% of the features, against 0.001 (p=0.68) for 58% of the features with baseline method. Our method is also more general than previous works, as it could in further perspective be applied with any interindividual factor on any feature.

ABSTRACT. Myoelectric control of prostheses is a long-established technique, using surface electromyography (sEMG) to detect the electrical signals of muscle activity and perform subsequent mechanical actions. Despite several decades' research and advances in commercial hardware, robust, responsive and intuitive control schemes remain elusive. This paper investigates several sEMG time domain features using a series of hand movements performed by eleven subjects, taken from a benchmark database. The feature sets were extracted from the data using a sliding window process and applied to five machine learning classifiers, of which Random Forest consistently performed the best. Results suggest that a few simple features such as Root Mean Square, achieve comparable performance to using the entire feature set, when identifying the hand movements, although further work is required for feature optimisation.

ABSTRACT. Analogue Movement Scores is a collaboration between dance artist Marguerite Galizia and sound artist Tom Richards. The aim was to create an interactive movement and sound performance and installation piece using non software-based electronic interfaces.

ABSTRACT. In this extended abstract we describe a practical demo based on the stage performance PIANO&DANCER, an interactive piece for a dancer and an electromechanical acoustic piano. In this demo, the dancer and the piano are two performers whose bodily movements become mutually interdependent. Œis interdependence reveals a close relationship between physical and musical gestures. Accordingly, the realisation of PIANO&DANCER was characterised by creative processes that merge choreographic and compositional methods. In order to relate the expressive movement qualities of a dancer to the creation of musical material, the performance employs a variety of techniques. ŒThese include methods for movement tracking and analysis, generative algorithms for creating spatial and temporal structures, and the application of nonconventional scales and chord transformations to shape the harmonic characteristics of the music.

ABSTRACT. 'screensaver' is a work-in-progress performance work involving four dancers, a choreographer, and a musician/coder. Relationships between movement—physical, virtual and abstract—and technology are the subject of research. We propose 'screensaver' as an intervention to raise philosophical questions and challenge assumptions about how movement can be framed within technological contexts.

ABSTRACT. Somatic movement practice supported by methods of topology-inspired architectural design, can aid design for movement in modulated reality (VR, AR, games, VFX), as well as creating interactive content for movement and gesture interfaces.

In performance arts, movement is an abstract language deployed by the artist to achieve kinaesthetic empathy with the audience. The main issue in choreographing, designing and performing for digitally-augmented movement (in live arts, games, vfx, dance) is the disconnect in communication between the performers’ embodied cognition, physically performed movement and the creation of content for real-time performance augmentation.

The main obstacles to accuracy of movement recognition, representation and coordination include wearable motion tracking systems restricting natural movement and coordination of the performer, delays between natural movement and the effects augmenting the movement of the performer, lack of feedback to the performer regarding their movement in physical space vs. in augmented space, as well as discrepancies between the 3D spatial models for previsualisation of effects and their physical unfolding in augmented space of the stage during the actual performance.

Borrowing from principles of Gestalt theory, current advances in camera vision, gesture and movement recognition, facilitate the workflow between creating content, performing and rehearsing. Learning from Gestalt, developing a vocabulary of shape in motion may allow seamless coordination, communication and creation of content for both the physical performer and the designer of interactive content for augmented performance.

Since Laban, principles of architecture and spatial design have been implemented to dance and movement theory and practice.. Animation softwares used in 3D modelling of complex geometrical structures in architecture, through particle simulation, allow to model and build architectural form at a high resolution with greater geometric complexity and formal variation. Thus, topological architectural approach may again prove to be suitable for modeling, representation, simulation and digital augmentation of the movement of performers.

In topological approach to architectural design, spatial formations are considered fluid rather than solid, and space is viewed as populated by continuous rather than discreet events unfolding in time. Informal approach to architecture promoted by the InForm manifesto (Balmond, Petresin, 2007) suggested a vocabulary of shapes and structures based on processes in morphogenesis rather than Platonic geometry or Laban. Similarly, in somatic approach to movement practice, space is not considered void but a physical entity with which the performer mindfully interacts by observing processes of transformation. Thus, the vocabulary of Informal architecture applied to somatic movement practice, and paired with just-in-time movement recognition may provide a more seamless method for creating content for digitally-augmented physical movement of the performer.

A system currently in development at Goldsmiths Computing aims to free performers’ movement from the constraints of wearable technology; real-time analysis of the tracked movements is essential for evaluating and giving giving feedback on performance, improving spatial coordination, communication of movement vocabulary, and tightly syncing movement and media content (projections, interactive audio, responsive lighting, robotics) augmenting the performance.

The demonstration and performance reveal the workflow behind the proposed method of coordinating somatic movement with interactive content using markerless movement recognition. A an augmented performance sequence will be used as a case study. Performer's movements will be filmed and analysed, using computer vision and movement recognition algorithms, with digital content augmenting the physically performed movement, in real-time.

ABSTRACT. Breakdown Harmonica is a research project focusing on analysing, understanding, and communicating an historical dance piece (Jane Dudley’s 1937 Harmonica Breakdown) to dance scholars and practitioners, as well as researchers from movement and computing disciplines. The project explored the use of animation and video games development tools to extend the traditional Labanotation score in order to make the score more readable for those without extensive training in Laban Notation and Laban Movement Analysis. This paper articulates some of the challenges faced in movement notation, and in the use of tools developed for video games and animation.

ABSTRACT. We present a method to compute a measure of karate movement quality from MoCap data. We start from the well-known common assumptions such as the following: an expert athlete is able to perform movements characterized by “stable and clean” postures and stances, i.e. she is able to conclude the movements without hesitation, that is, without noisy small fluctuations or movement ripples. This is given by a high level control of the movement, emerging from a strong synchrony between limbs, in particular in the starting and ending phases of a single movement of a kata (sequence of movements). This also corresponds to the concept of “soft entrainment” in music performance, another motor task characterized by high skills and expressivity. To explore this hypothesis, we collected a dataset of motion capture data of movements of seven athletes while performing two different kata’s for a total of 29 trials. The athletes have various levels of experience and age, but all are “black belt” in karate: we classified them into three groups based on their skill (from Level 3: athletes with less experience to Level 5: expert athletes). For each trial, we computed the acceleration of the limbs (arms and legs) and carried out a multiscale analysis to identify and extract significant events. Such events correspond to maxima and minima of acceleration intensity (i.e. peaks of high acceleration or deceleration), and correspond to the start and end points of each movement segment in a kata. Significant events were then selected and an event-synchronization approach was used to measure the amount of synchrony between the two arms and between the two legs. Results show that expert performers present higher synchronization with respect to beginners, resulting in more stable and clean movements perceived by observers.

ABSTRACT. A novel computational method for the analysis of expressive full-body movement qualities is introduced, which exploits concepts and tools from graph theory and game theory. The human skeletal structure is modeled as an undirected graph, where the joints are the vertices and the edge set contains both physical and nonphysical links. Physical links correspond to connections between adjacent physical body joints (e.g., the forearm, which connects the elbow to the wrist). Nonphysical links act as “bridges” between parts of the body not directly connected by the skeletal structure, but sharing very similar feature values. The edge weights depend on features obtained by using Motion Capture data. Then, a mathematical game is constructed over the graph structure, where the vertices represent the players and the edges represent communication channels between them. Hence, the body movement is modeled in terms of a game built on the graph structure. Since the vertices and the edges contribute to the overall quality of the movement, the adopted game-theoretical model is of cooperative nature. A game-theoretical concept, called Shapley value, is exploited as a centrality index to estimate the contribution of each vertex to a shared goal (e.g., to the way a particular movement quality is transferred among the vertices). The proposed method is applied to a data set of Motion Capture data of subjects performing expressive movements, recorded in the framework of the H2020-ICT-2015 EU Project WhoLoDance, Project no. 688865. Preliminary results are presented.

ABSTRACT. Behavioral and theoretical studies have focused on identifying the kinematic and temporal characteristics of various movements ranging from simple reaching to

Complex two-dimensional and three-dimensional and drawing motions. Such features were quite instrumental in investigating the organizing principles that underlie trajectory formation. Similar kinematic principles play also a critical role in visual perception of motion and in action recognition. In my talk I will review the results of several studies aimed at identifying the neural correlates of the behavioral findings. I will also present a new theory of trajectory formation which is inspired by geometrical invariance. The theory proposes that movement time, kinematics, and compositionality arise from cooperation among Euclidian and Non-Euclidian geometries.

Mathematically expressing these ideas, a computational scheme was used in modeling 2D and 3D drawing and locomotion trajectories. I will also discuss the findings from several behavioral and brain imaging studies showing the similarities between motion perception and production. Finally I will talk about the topic of motor timing in human movements- what principles and models can account for the selection of both global durations and the durations of individual movement segments within complex actions. I will conclude by discussing the implications of the above studies with respect to visual and digital arts and robotics.