A multimodal user interface for touchless control of robotic ultrasound

Abstract

PurposePast research contained the investigation and development of robotic ultrasound. In this context, interfaces which allow for interaction with the robotic system are of paramount importance. Few researchers have addressed the issue of developing non-tactile interaction approaches, although they could be beneficial for maintaining sterility during medical procedures. Interaction could be supported by multimodality, which has the potential to enable intuitive and natural interaction. To assess the feasibility of multimodal interaction for non-tactile control of a co-located robotic ultrasound system, a novel human–robot interaction concept was developed.MethodsThe medical use case of needle-based interventions under hybrid computed tomography and ultrasound imaging was analyzed by interviewing four radiologists. From the resulting workflow, interaction tasks were derived which include human–robot interaction. Based on this, characteristics of a multimodal, touchless human–robot interface were elaborated, suitable interaction modalities were identified, and a corresponding interface was developed, which was thereafter evaluated in a user study with eight participants.ResultsThe implemented interface includes voice commands, combined with hand gesture control for discrete control and navigation interaction of the robotic US probe, respectively. The interaction concept was evaluated by the users in the form of a quantitative questionnaire with a average usability. Qualitative analysis of interview results revealed user satisfaction with the implemented interaction methods and potential improvements to the system.ConclusionA multimodal, touchless interaction concept for a robotic US for the use case of needle-based procedures in interventional radiology was developed, incorporating combined voice and hand gesture control. Future steps will include the integration of a solution for the missing haptic feedback and the evaluation of its clinical suitability.