Multimodal Human-robot Interaction setup with NAO
Gaze is known to be a dominant modality for conveying spatial information, and it has been used for grounding in human-robot dialogues. In this work, we present the prototype of a gaze-supported multi-modal dialogue system that enhances two core tasks in human-robot collaboration:
Recently, we published a prototype for gaze-guided object classification at UbiComp conference 2016. This topic also raised interest of Pupil Labs, the manufacturer of the applied eye tracking device.
Gaze-guided Object Classification Demo
The WaterCoaster started as a seminar project (Gamified Life) comprising the design of a hardware prototype and a mobile app measuring the water intake of humans. Applying gamification elements, we wanted to persuade the user to drink more frequently and to drink a healthier amount of water during work time. We published the results as late breaking work at CHI 2016
The gaze estimation error is inherent in head-mounted eye trackers and seriously impacts performance, usability, and user experience of gaze-based interfaces. Particularly in mobile settings, this error varies constantly as users move in front and look at different parts of a display. We envision a new class of gaze-based interfaces that are aware of the gaze estimation error and adapt to it in real time. As a first step towards this vision, we introduce an error model that is able to predict the gaze estimation error. Our method covers major building blocks of mobile gaze estimation, specifically mapping of pupil positions to scene camera coordinates, marker-based display detection, and mapping of gaze from scene camera to on-screen coordinates. We develop our model through a series of principled measurements of a state-of-the-art head-mounted eye tracker. Continue reading
This post presents images and first impressions on the final prototype of the Aero One portable loudspeaker. The audio quality is adequate for the size and cost of the device. The low frequencies are a bit quiet, probably due to the chosen drivers and the low-power amplifier. On the other side, an approximated runtime of around 6h with high volume and a considerably longer runtimes at room volume are very appealing.
