VR Environment for the Study of Collocated Interaction Between Small UAVs and Humans

Two issues that are crucial to the integration of flying robotic systems into human populated environments include: how humans perceive autonomous flying robots, and how to design and control flying robots to improve the level of comfort and perceived safety for collocated others. This work represents a comprehensive virtual reality test environment to explore scripted and unscripted interactions with flying robots. We employ a multimethod approach by incorporating behavioral measures, self-report questionnaires, and physiological data to characterize human arousal during a variety of predetermined and real-time scenarios in both indoor and outdoor environments. By combining complementary methodological techniques, we can converge on a data-driven model of social etiquette for flying robots; this model can then be reparametrized in terms of planning and control solutions to govern the robot’s behavior in a real-world context.

[1]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[2]  Yuichi Nakamura,et al.  Approximation of dynamical systems by continuous time recurrent neural networks , 1993, Neural Networks.

[3]  Lukás Burget,et al.  Extensions of recurrent neural network language model , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[4]  Holger Regenbrecht,et al.  The Experience of Presence: Factor Analytic Insights , 2001, Presence: Teleoperators & Virtual Environments.

[5]  Morgan Quigley,et al.  ROS: an open-source Robot Operating System , 2009, ICRA 2009.

[6]  Robert S. Kennedy,et al.  Simulator Sickness Questionnaire: An enhanced method for quantifying simulator sickness. , 1993 .

[7]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[8]  Bilge Mutlu,et al.  Communication of Intent in Assistive Free Flyers , 2014, 2014 9th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[9]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[10]  M. Benedek,et al.  A continuous measure of phasic electrodermal activity , 2010, Journal of Neuroscience Methods.