عنوان انگلیسی مقاله:
A data-efficient deep learning approach for deployable multimodal social robots
ترجمه فارسی عنوان مقاله:
یک روش یادگیری عمیق با کارآیی داده ها برای روبات های اجتماعی چند حالته قابل استفاده
Sciencedirect - Elsevier - Neurocomputing, Corrected proof: doi:10:1016/j:neucom:2018:09:104
The deep supervised and reinforcement learning paradigms (among others) have the potential to endow interactive multimodal social robots with the ability of acquiring skills autonomously. But it is still not very clear yet how they can be best deployed in real world applications. As a step in this direction, we propose a deep learning-based approach for efficiently training a humanoid robot to play multimodal games—and use the game of ‘Noughts and Crosses’ with two variants as a case study. Its minimum re- quirements for learning to perceive and interact are based on a few hundred example images, a few example multimodal dialogues and physical demonstrations of robot manipulation, and automatic sim- ulations. In addition, we propose novel algorithms for robust visual game tracking and for competitive policy learning with high winning rates, which substantially outperform DQN-based baselines. While an automatic evaluation shows evidence that the proposed approach can be easily extended to new games with competitive robot behaviours, a human evaluation with 130 humans playing with the Pepper robot confirms that highly accurate visual perception is required for successful game play.
Keywords: Deep reinforcement learning | Deep supervised learning | Interactive robots | Multimodal perception and interaction | Board games