Reinforcement Learning for Structural Control

This study focuses on improving structural control through reinforcement learning. For the purposes of this study, structural control involves controlling the shape of an active tensegrity structure. Although the learning methodology employs case-based reasoning, which is often classified as supervised learning, it has evolved into reinforcement learning, since it learns from errors. Simple retrieval and adaptation functions are proposed. The retrieval function compares the response of the structure subjected to the current loading event and the attributes of cases. When the response of the structure and the case attributes are similar, this case is retrieved and adapted to the current control task. The adaptation function takes into account the control quality that has been achieved by the retrieved command in order to improve subsequent commands. The algorithm provides two types of learning: reduction of control command computation time and increase of control command quality over retrieved cases. Results from experimental testing on a full-scale active tensegrity structure are presented to validate performance.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/08873801
• Authors:
  • Adam, Bernard
  • Smith, Ian F C
• Publication Date: 2008-3

Language

• English

Media Info

• Media Type: Print
• Features: Figures; Illustrations; Photos; References; Tables;
• Pagination: pp 133-139
• Serial:
  • Journal of Computing in Civil Engineering
  • Volume: 22
  • Issue Number: 2
  • Publisher: American Society of Civil Engineers
  • ISSN: 0887-3801

Subject/Index Terms

• TRT Terms: Adaptive control; Algorithms; Material reinforcement; Mathematical methods; Nonlinear systems; Structural engineering
• Uncontrolled Terms: Structural control; Tensegrity structure
• Subject Areas: Bridges and other structures; Design; Highways; I24: Design of Bridges and Retaining Walls;

Filing Info

• Accession Number: 01091520
• Record Type: Publication
• Files: TRIS
• Created Date: Apr 23 2008 9:25AM