NIH

 
 

GEAR (Grounded Early Adaptive Rehabilitation) is an interdisciplinary research effort that aims at improving pediatric rehabilitation outcomes and drastically expanding intervention possibilities for young children with mobility disabilities, through controlled and adaptive social interaction with robots.

Publications


  1. Subregular Complexity and Deep Learning. Workshop on Learning and Automata, 2017.

  2. Use of Socially Assistive Robots in Early Rehabilitation  to Promote Mobility for Infants with Motor Delays.  International Conference on Social Robotics 2017.

  3. Principles of building “smart” environments in pediatric early rehabilitationWorkshop in Robotics: Science and Systems 2017.

  4. Temporal Convolutional Networks for Action Segmentation and DetectionIEEE Conference on Computer Vision and Pattern Recognition 2017,

  5. Deep Moving Poselets for Video-based Action Recognition. IEEE Conference on Applications of Computer Vision 2017

  6. Learning Models of Human-Robot Interaction from Small Data. IEEE Mediterranean Conference on Control and Automation 2017.

  7. Effect of adding vectors embedding second-order strictly piecewise automata to recurrent neural networks.  International Conference on Grammatical Inference 2016.

  8. Using model theory for grammatical inference: a case study in phonologyInternational Conference on Grammatical Inference 2016.

  9. Segmental Spatio-Temporal CNNs for Fine-grained Action Segmentation and ClassificationEuropean Conference on Computer Vision 2016.



Software


  1. Source code for synchronized networked data collection, post-processing and playback, under the GPLv3 public license:

  2. https://github.com/prarobo/gear

News

Our experimental setup for data collection is (almost) ready.  We are running pilot studies to fine tune the system components.


We should be able to proceed with subject recruitment very soon!