Entrainment offers a rich theoretical understanding of how rhythmic stimuli are embodied in movement. Behavioural research examines how entrained coordination arises in the presence of sound and interpersonal interactions, which are reflected in sensorimotor and physiological responses. This paper explores the affordances of generative models for sound-movement mapping designed to support dyadic embodied interaction. We adopt a set of physical partner-based exercises that emphasise spatio-temporal coordination, guided by a moving prop. A tangible artefact is orchestrated around this prop, integrating two mapping strategies: an explicit, one-to-one mapping, and a latent mapping using a deep generative model for neural synthesis. A study compares these approaches as six dyads perform the exercises. Our findings suggest that sound feedback influenced participants’ peripheral awareness, and that the latent mapping offered relevant design opportunities for evoking familiar embodied sensations and bringing attention to emergent qualities of dyadic movement.

There is a growing interest in interactive visuals for dance performance. Recent research has identified potential in using interactive visuals to convey to the audience otherwise non-visible elements of performances. Informed by soma design, and with a co-design perspective, we aim to make apparent non-visible bodily aspects of dancers. We propose to design interactive visuals from body maps, following two approaches – Machine Learning and Composite Animation. We conducted a multi-stage study involving 12 dancers. We present and discuss the results of our evaluations, confirming that both prototypes were successful in addressing our aim, with some limitations. We discuss our two approaches, different uses and actors in different stages, tensions between research and dance creation, and potential applications. Our main contributions are the two approaches for designing interactive visuals from body maps and their analysis. These are materialized in two software systems released as open-source and in their design framework descriptions.

Deep Pressure Therapy relies on exerting firm touch to help individuals with sensory sensitivity. We performed first-person explorations of deep pressure enabled by shape-changing actuation driven by breathing sensing. This revealed a novel design space with rich, evocative, aesthetically interesting interactions that can help increase breathing awareness and appreciation through: (1) applying symmetrical as well as asymmetrical pressure on the torso; (2) using pressure to direct attention to muscles or bone structure involved in different breathing patterns; (3) apply synchronous as well as asynchronous feedback following or opposing the user’s breathing rhythm through applying rhythmic pressure. Taken together these explorations led us to design (4) breathing correspondence interactions – a balance point right between leading and following users’ breathing patterns by first applying deep pressure – almost to the point of being unpleasant – and then releasing in rhythmic flow.