HAIR: Head-mounted AR Intention Recognition

David Puljiz, Bowen Zhou, Ke Ma, Björn Hein

Keywords: Human Intention Estimation, Augmented Reality, Human-robot Collaboration, Head Mounted Displays

TL;DR: Intention estimation in HRI based on wearable sensors

Abstract: Human teams exhibit both implicit and explicit intention sharing. To further development of human-robot collaboration, intention recognition is crucial on both sides. Present approaches rely on a vast sensor suite on and around the robot to achieve intention recognition. This relegates intuitive human-robot collaboration purely to such bulky systems, which are inadequate for large-scale, real-world scenarios due to their complexity and cost. In this paper we propose an intention recognition system that is based purely on a portable head-mounted display. In addition robot intention visualization is also supported. We present experiments to show the quality of our human goal estimation component and some basic interactions with an industrial robot. HAIR should raise the quality of interaction between robots and humans, instead of such interactions raising the hair on the necks of the human coworkers.

Track: full paper

Broader Impacts:

The work presented here increases the intuitiveness, efficiency and safety of HRI. On on hand it provides a constant input to the robot about the goal of the human coworker as well as the action the worker intends to perform. On the other hand it greatly increases the situational awareness of the user by providing multi-cue communication of the robotic manipulator's goals and motion intentions. All of this is achieved without any sensors on or around the robot and without any set-up as the system is purely based on equipment worn by the human, namely a head-mounted display. Moreover it is not relegated to any specific manipulator and works with all commercially available manipulators.

We envision that such portable systems will play a crucial role in the future by lowering the complexity and the price of robot systems while increasing the safety and efficiency, especially in scenarios where a single human interacts with multiple different robot systems, as is expected in the future.