Cornelia Wendt

Evaluation of a novel biologically inspired trajectory generator in human-robot interaction

In many future joint-action scenarios, humans and robots will have to interact physically in order to cooperate successfully. Ideally, human-robot interaction should not require training on the human side, but should be intuitive and simple. Previously, we reported on a simple case of physical human-robot interaction, a hand-over task [1]. Even such a basic task as manually handing over an object from one agent to another requires that both partners agree upon certain basic prerequisites and boundary conditions. While some of them are negotiated explicitly, e.g. by verbal communication, others are determined indirectly and adaptively in the course of the cooperation. In the previous study we compared a human-human hand-over interaction with the same task performed by a human and a robot. However, the trajectories used for the robot, a conventional trapezoidal velocity profile in joint coordinates and a minimum-jerk profile of the end-effector, have little resemblance to the natural movements of humans. In this study we introduce a novel trajectory generator that is a variation of the traditional minimum-jerk profile, the ‘decoupled minimum-jerk’ profile. Its trajectory is much closer to those observed in human-human experiments. We evaluated its performance concerning human comfort and acceptance in a simple hand-over experiment by using a post-test questionnaire. The evaluation of the questionnaire revealed no difference with respect to comfort, human-likeness, or subjective safety of the new planner compared to the minimum-jerk profile. Thus, the ‘decoupled minimum-jerk’ planner, which offers important advantages with respect to target approach, proved to be a promising alternative to the previously used minimum-jerk profile.

Real-time framework for multimodal human-robot interaction

This paper presents a new framework for multimodal data processing in real-time. This framework comprises modules for different input and output signals and was designed for human-human or human-robot interaction scenarios. Single modules for the recording of selected channels like speech, gestures or mimics can be combined with different output options (i.e. robot reactions) in a highly flexible manner. Depending on the included modules, online as well as offline data processing is possible. This framework was used to analyze human-human interaction to gain insights on important factors and their dynamics. Recorded data comprises speech, facial expressions, gestures and physiological data. This naturally produced data was annotated and labeled in order to train recognition modules which will be integrated into the existing framework. The overall aim is to create a system that is able to recognize and react to those parameters that humans take into account during interaction. In this paper, the technical implementation and application in a human-human and a human-robot interaction scenario is presented.

Emotion induction during human-robot interaction

Summary form only given. The aim of the presented study was to measure physiological correlates of emotions that are of particular interest in the field of human-robot interaction (HRI). Therefore, we did not focus on self-induced basic emotions but rather evoked states that might occur naturally in this context. Our video shows how such states (namely stress, boredom, surprise, and perplexity) were elicited during a joint construction task with an industrial robot (see figure 1). Participants were asked to build different LEGO objects, while the robot arm was passing the bricks with predetermined velocity. States of stress and boredom were generated by varying the handover interval from 3 seconds (stress) to 5 seconds (normal working condition) up to 35 seconds (boredom). Surprise was induced by passing an unexpected component. At the end of the experiment, we additionally wanted to know how people react if the robot seems to tease them by repeatedly changing the handover position. This experiment was realized by the support of researchers from the MMK and the IWB of the Technical University Munich who provided the technical facilities and know-how. The underlying project is supported within the DFG excellence initiative research cluster “Cognition for Technical Systems - CoTeSys”, see also www.cotesys.org.

Physiology and HRI: Recognition of over- and underchallenge

Contrary to common emotion recognition techniques by face or speech analysis, physiological data are involuntary and continuously available. Thus, they allow for emotion detection even in situations without spoken words or in case of non-extreme emotions, which are more likely to occur in human-robot interaction (HRI). In this paper, we describe the results of an experiment investigating non-extreme emotional states relevant for HRI scenarios (over- and underchallenge). Those states occurred naturally during the course of a LEGO construction task by manipulating working speed. Data collected from 28 subjects were analyzed and the results of different types of discriminant analysis and nearest neighbour methods were compared. Based on two physiological modalities (HR, SCR), correct classification rates of up to 76% for seven features and 74% for only two features were achieved. Overchallenge could be discriminated very well from the other two conditions (96.4 - 85.7%), whereas underchallenge is often confused with the intermediate condition with normal working speed.