Two demos were accepted for presentation at ACM SenSys’19 in New York City, NY, in November 2019.
A demo led by Joseph DeChicchis, titled Adaptive AR Visual Output Security Using Reinforcement Learning Trained Policies, demonstrates how reinforcement learning-based policies for hologram positioning perform on Magic Leap One augmented reality sets. This demo builds on the work on learning for hologram positioning in AR led by Surin Ahn, previously evaluated via simulations alone. Related work:
- S. Ahn, M. Gorlatova, P. Naghizadeh, M. Chiang, Personalized Augmented Reality Via Fog-based Imitation Learning, in Proc. IEEE Workshop on Fog Computing and the IoT, Apr. 2019 (co-located with IEEE CPS-IoT Week). [Paper PDF] [Imitation learning demo] [Extended version of the paper]
- S. Ahn, M. Gorlatova, P. Naghizadeh, M. Chiang, P. Mittal, Adaptive Fog-based Output Security for Augmented Reality, in Proc. ACM SIGCOMM VR/AR Network Workshop, Budapest, Hungary, Aug. 2018. [Paper PDF]
Additionally, a demo led by Jovan Stojkovic, Zida Liu, and Guohao Lan, titled Edge Assisted Collaborative Image Recognition for Augmented Reality, presents a dynamic approach for handling heterogeneous multi-user visual inputs for image recognition in augmented reality, demonstrated on an edge-assisted Google ARCore platform.
[SenSys19aToAppear] J. DeChicchis, S. Ahn, M. Gorlatova, Demo: Adaptive Augmented Reality Visual Output Security Using Reinforcement Learning Trained Policies, to appear in Proc. ACM Conference on Embedded Networked Sensor Systems (ACM SenSys’19), New York City, NY, Nov. 2019.
[SenSys19bToAppear] J. Stojkovic, Z. Liu, G. Lan, C. Joe-Wong, M. Gorlatova, Demo: Edge-assisted Collaborative Image Recognition for Augmented Reality, to appear in Proc. ACM Conference on Embedded Networked Sensor Systems (ACM SenSys’19), New York City, NY, Nov. 2019.