Complicated robot activity recognition by quality-aware deep reinforcement learning

Xing Li, Junpei Zhong (Corresponding Author), M. M. Kamruzzaman

Research output: Journal article publicationJournal articleAcademic researchpeer-review

2 Citations (Scopus)

Abstract

Automatic robot activity understanding plays an important role in human–computer interaction (HCI), especially in smart home service robots. Existing manipulator control methods, such as position control, vision-based control method, fail to meet the requirements of autonomous learning. Reinforcement learning can cope with the interaction of robot control and environment; however, the method should relearn the control method when the position of target object changes. To solve this problem, this paper proposes a quality model to utilize deep reinforcement learning scheme to achieve an end-to-end manipulator control. Specifically, we design a policy search algorithm to achieve automatic learning of manipulator. To avoid relearning of manipulator, we design convolutional neural network control scheme to remain the robustness of manipulator. Extensive experiment has shown the effectiveness of our proposed method.

Original languageEnglish
Pages (from-to)480-485
Number of pages6
JournalFuture Generation Computer Systems
Volume117
DOIs
Publication statusPublished - Apr 2021
Externally publishedYes

Keywords

  • Deep reinforcement learning
  • End-to-end learning
  • Human–computer interaction
  • Policy search
  • Quality model

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this