Strokes are a leading cause of disability, with many survivors experiencing significant mobility impairments. While robot-assisted rehabilitation offers a promising solution, its adoption seems challenged by high upfront costs, low flexibility and complex configuration workflows. To address these challenges, this study conducts an interaction analysis to identify key requirements for empowering therapists to self-configure and adapt a flexible, cost-effective robot during gait rehabilitation tasks. Our analysis is based on 20 training sequences from a 60-hour video dataset collected across three experimental setups, involving young adults with motor impairments training with the assistance of the robot. Drawing methods from Ethnomethodology and Conversation Analysis (EMCA), we examined the sequential organization of actions between technology, therapist and participant, identifying three main stages: setup, training, and completion. During setup, coordinated actions prepare the participant and the robot for the main training task; during training, participant and robot engage in movement while the therapist iterates adjustments; and in completion, coordinated actions prepare the participant for transitioning back to their conventional support system. Our analysis highlights some requirements and strategies for developing End-User Development (EUD) environments for robot-assisted physiotherapy, emphasizing user-driven workflows, multimodal transitions between robot’s assistance modes, and real-time robotic feedback that maintains coherence with therapists’ practices. • Robot-assisted physical training follows a structured sequence with 3 main phases. • The gaze, speech, and touch of the therapists indicate transitions between phases. • Robot control modes adapt across phases to support evolving therapeutic goals. • Software engagement varies with each phase of therapy and the patient’s condition. • Therapists can adjust assistance settings before, during, and after active therapy.

This workshop is dedicated to discuss and explore the specific interdisciplinary aspects of Bodily human robot interaction, and establish a common ground for this area as a recognized and continued research topic. Bodily interaction with robots and robotic devices is partially established in niche applications such as exoskeletons, assistive devices and advanced machines for physical training where bodily interaction is the application. Bodily interaction is expected to develop a broader role in human robot interaction, for instance in manufacturing and in social and entertainment robotics. The direct exchange of force and motion in bodily interaction create a range of engineering challenges, but also entwine engineering directly with topics that traditionally reside in the realm of health and humanistic science, from biomechanics to human's social responses to the prompting and responses of physical interaction.

This paper presents a novel method for analyzing and designing kinesthetic interaction between humans and robots. The method is based on a combination of Social Embodied Interaction (SEI) analysis and Finite State Machine design. The method is presented along with its application to design and analyze an interactive training program for the robotic training device RoboTrainer-Light, with the objective of programming the robot so an optimal training pattern will emerge in the interaction, using only the exchange of force and motion to achieve this.

Training with a robotic training partner, is a physical, powerful, and yet intimate form of robot/human interaction (RHI). In this paper we report on the early stages of a project, that aims to study and use the human kinesthetic "language" of co-motion, used in physical human/robot interaction such as training.