Gregor Zolynski

Safety for an Autonomous Bucket Excavator During Typical Landscaping Tasks

The Robotics Research Lab in Kaiserserlautern, Germany, pursues the goal of automating a mobile bucket excavator for excavation and loading tasks. This document contains a short introduction to the autonomous bucket excavator THOR, a concept for low-level safety using laser scanners, and a high-level collision avoidance system using behavior-based control.

Effective Visualization of Long Term Health Data to Support Behavior Change

The reflective stage, which is crucial for behavior change, can be facilitated with suitable visualizations that allow users to answer specific questions with regard to their health data. To date, effective visualizations which combine time series data and the appraisal of this data in one chart are, however, rare. To close this gap in research, twenty participants compared two alternative long-term visualizations of health behavior: an accumulated bar chart and a point chart which both include appraisals of the underlying health data based on current recommendations of leading health organizations, such as the World Health Organization or the European Food Information Council. Participants answered three types of question (progress over time, correlations between different health behaviors, and health consciousness). The sequence of visualization for the underlying data sets was cross balanced over participants. The accumulated bar chart resulted in more trials in which participants were unable to answer. In some cases, this type of visualization also resulted in biased interpretations with regard to progress over time and health consciousness. Summarizing, we recommend the point chart, in which the background is colored according to the recommendation of the respective health behavior. Both types of visualization are, however, not optimal for the identification of correlations.

Stress-Mentor: Linking Gamification and Behavior Change Theory in a Stress Management Application

Gamification is widely accepted in mobile health applications as one way to enhance user experience. Moreover, linking gamification with insights from behavior change theory offers a promising approach to ensure user’s adherence and long-term behavior change. Gamification is, however, hardly found in current stress management applications. To close this gap in research, we present Stress-Mentor, a stress management app that realizes established behavior change techniques within an extensive gamification framework.

Towards More Interactive Stress-Related Self-monitoring Tools to Improve Quality of Life

Self-monitoring with diaries is one way to identify stress causing events and the respective personal reactions. Considering the broad distribution of smartphones over the past decade, an interactive stress diary application (app) was developed. Diary entries are linked to changes in the appearance of an avatar to support regular usage behavior through vicarious reinforcement.

Human head pose estimation using multi-appearance features

Non-verbal interaction signals are of great interest in the research field of natural human-robot interaction. These signals are not limited to gestures and emotional expressions since other signals - like the interpersonal distance and orientation - do also have large influence on the communication process. Therefore, this paper presents a marker-less mono-ocular object pose estimation using a model-to-image registration technique. The object model uses different feature types and visibilities which allow the modeling of various objects. Final experiments with different feature types and tracked objects show the flexibility of the system. It turned out that the introduction of feature visibility allows pose estimations when only a subset of the modeled features is visible. This visibility is an extension to similar approaches found in literature.