Using a Memory of Motion to Efficiently Warm-Start a Nonlinear Predictive Controller

N. Mansard, A. DelPrete, M. Geisert, S. Tonneau, O. Stasse

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Predictive control is an efficient model-based methodology to control complex dynamical systems. In general, it boils down to the resolution at each control cycle of a large nonlinear optimization problem. A critical issue is then to provide a good guess to initialize the nonlinear solver so as to speed up convergence. This is particularly important when disturbances or changes in the environment prevent the use of the trajectory computed at the previous control cycle as initial guess. In this paper, we introduce an original and very efficient solution to automatically build this initial guess. We propose to rely on off-line computation to build an approximation of the optimal trajectories, that can be used on-line to initialize the predictive controller. To that end, we combined the use of sampling-based planning, policy learning with generic representations (such as neural networks), and direct optimal control. We first propose an algorithm to simultaneously build a kinodynamic probabilistic roadmap (PRM) and approximate value function and control policy. This algorithm quickly converges toward an approximation of the optimal state-control trajectories (along with an optimal PRM). Then, we propose two methods to store the optimal trajectories and use them to initialize the predictive controller. We experimentally show that directly storing the state-control trajectories leads the predictive controller to quickly converges (2 to 5 iterations) toward the (global) optimal solution. The results are validated in simulation with an unmanned aerial vehicle (UAV) and other dynamical systems.
Original languageEnglish
Title of host publication2018 IEEE International Conference on Robotics and Automation (ICRA)
Place of PublicationBrisbane, QLD, Australia
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages2986-2993
Number of pages8
ISBN (Electronic)978-1-5386-3081-5, 978-1-5386-3080-8
ISBN (Print)978-1-5386-3082-2
DOIs
Publication statusPublished - 1 May 2018
Event2018 IEEE International Conference on Robotics and Automation - The Brisbane Convention & Exhibition Venue, Brisbane, Australia
Duration: 21 May 201825 May 2018
http://icra2018.org/

Publication series

Name
PublisherIEEE
ISSN (Electronic)2577-087X

Conference

Conference2018 IEEE International Conference on Robotics and Automation
Abbreviated titleICRA2018
Country/TerritoryAustralia
CityBrisbane
Period21/05/1825/05/18
Internet address

Keywords

  • autonomous aerial vehicles
  • iterative methods
  • learning (artificial intelligence)
  • nonlinear control systems
  • optimal control
  • optimisation
  • path planning
  • predictive control
  • sampling methods
  • trajectory optimisation (aerospace)
  • direct optimal control
  • control policy
  • optimal state-control trajectories
  • nonlinear predictive controller
  • nonlinear optimization problem
  • model-based methodology
  • control cycle
  • kinodynamic probabilistic roadmap
  • nonlinear solver
  • unmanned aerial vehicle
  • UAV
  • complex dynamical systems
  • sampling-based planning
  • policy learning
  • Computational modeling
  • Approximation algorithms
  • Optimal control
  • Planning
  • Robots
  • Trajectory optimization

Fingerprint

Dive into the research topics of 'Using a Memory of Motion to Efficiently Warm-Start a Nonlinear Predictive Controller'. Together they form a unique fingerprint.

Cite this