User-Defined Body Gestures for Navigational Control of a Humanoid Robot

Abstract

This paper presents a study that allows users to define intuitive gestures to navigate a humanoid robot. For eleven navigational commands, 385 gestures, performed by 35 participants, were analyzed. The results of the study reveal user-defined gesture sets for both novice users and expert users. In addition, we present, a taxonomy of the userdefined gesture sets, agreement scores for the gesture sets, time performances of the gesture motions, and present implications to the design of the robot control, with a focus on recognition and user interfaces.

User-Defined Body Gestures for an Interactive Storytelling Scenario

“…The system never recognized a wrong gesture, so th verall, we got positive feedback about the integration, eract by using the new gesture set. istribution of our gesture set is concerned, we got qu rison to our previous work that investigated user-defi umanoid robot [14]. We got much less deictic gestures a re metaphoric ones.…”

“…Researchers already adopted this process for other areas, e.g. Kurdyukova et al [11] used it to design gestures for transferring data between tablet computers and a multi-display environment, and Obaid et al [14] applied the process to create a full body gesture set for the navigational control of humanoid robots. In this paper, we adapt the process by Wobbrock et al to identify intuitive gestures for an interactive storytelling scenario.…”

“…Each dimension consisted of multiple items as shown in Table 1. The dimensions were based on the taxonomy we had used in [14], we only left out the view-point dimension, as our interactive storytelling scenario always kept the user in a first-person perspective and there were no changes in the view-point for this reason. Furthermore, we changed the wording of the gesture type dimension to be closer to McNeill [12].…”

“…However, a gesture that is intuitive for the developers does not necessarily have to be intuitive for the majority of users. A different approach that creates a user-defined gesture set has been addressed by several other domains, such as surface computing [18], public displays [11], or human robot interaction [14].…”

Traveller: An Interactive Cultural Training System Controlled by User-Defined Body Gestures

“…An approach that employs a user-defined gesture set has been presented by Wobbrock et al for surface computing [14], and was adapted for other areas, such as public displays [9] or human robot interaction [11]. Its basic idea is to show specific effects within a system to users, who are then asked to perform gestures that should trigger these effects.…”