eduzhai > Applied Sciences > Computer Science >

Covert Perceptual Capability Development

  • paiqiu
  • (0) Download
  • 20210805
  • Save

... pages left unread,continue reading

Document pages: 4 pages

Abstract: In this paper, we propose a model to developrobots’ covert perceptual capability using reinforcement learning. Covert perceptual behavior is treated as action selected by a motivational system. We apply this model tovision-based navigation. The goal is to enablea robot to learn road boundary type. Insteadof dealing with problems in controlled environments with a low-dimensional state space,we test the model on images captured in non-stationary environments. Incremental Hierarchical Discriminant Regression is used togenerate states on the fly. Its coarse-to-finetree structure guarantees real-time retrievalin high-dimensional state space. K Nearest-Neighbor strategy is adopted to further reduce training time complexity.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×