0

Full Content is available to subscribers

Subscribe/Learn More  >

How to Beat Flappy Bird: A Mixed-Integer Model Predictive Control Approach

[+] Author Affiliations
Matthew Piper, Pranav Bhounsule, Krystel K. Castillo-Villar

University of Texas at San Antonio, San Antonio, TX

Paper No. DSCC2017-5285, pp. V002T07A003; 9 pages
doi:10.1115/DSCC2017-5285
From:
  • ASME 2017 Dynamic Systems and Control Conference
  • Volume 2: Mechatronics; Estimation and Identification; Uncertain Systems and Robustness; Path Planning and Motion Control; Tracking Control Systems; Multi-Agent and Networked Systems; Manufacturing; Intelligent Transportation and Vehicles; Sensors and Actuators; Diagnostics and Detection; Unmanned, Ground and Surface Robotics; Motion and Vibration Control Applications
  • Tysons, Virginia, USA, October 11–13, 2017
  • Conference Sponsors: Dynamic Systems and Control Division
  • ISBN: 978-0-7918-5828-8
  • Copyright © 2017 by ASME

abstract

Flappy Bird is a mobile game that involves tapping the screen to navigate a bird through a gap between pairs of vertical pipes. When the bird passes through the gap, the score increments by one and the game ends when the bird hits the floor or a pipe. Surprisingly, Flappy Bird is a very difficult game and scores in single digits are not uncommon even after extensive practice. In this paper, we create three controllers to play the game autonomously. The controllers are: (1) a manually tuned controller that flaps the bird based on a vertical set point condition; (2) an optimization-based controller that plans and executes an optimal path between consecutive tubes; (3) a model-based predictive controller (MPC). Our results showed that on average, the optimization-based controller scored highest, followed closely by the MPC, while the manually tuned controller scored the least. A key insight was that choosing a planning horizon slightly beyond consecutive tubes was critical for achieving high scores. The average computation time per iteration for the MPC was half that of optimization-based controller but the worst case time (maximum time) per iteration for the MPC was thrice that of optimization-based controller. The success of the optimization-based controller was due to the intuitive tuning of the terminal position and velocity constraints while for the MPC the important parameters were the prediction and control horizon. The MPC was straightforward to tune compared to the other two controllers. Our conclusion is that MPC provides the best compromise between performance and computation speed without requiring elaborate tuning.

Copyright © 2017 by ASME

Figures

Tables

Interactive Graphics

Video

Country-Specific Mortality and Growth Failure in Infancy and Yound Children and Association With Material Stature

Use interactive graphics and maps to view and sort country-specific infant and early dhildhood mortality and growth failure data and their association with maternal

NOTE:
Citing articles are presented as examples only. In non-demo SCM6 implementation, integration with CrossRef’s "Cited By" API will populate this tab (http://www.crossref.org/citedby.html).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In