LQR-RRT*: Optimal sampling-based motion planning with automatically derived extension heuristics

Journal Article

The RRT* algorithm has recently been proposed as an optimal extension to the standard RRT algorithm [1]. However, like RRT, RRT* is difficult to apply in problems with complicated or underactuated dynamics because it requires the design of a two domain-specific extension heuristics: a distance metric and node extension method. We propose automatically deriving these two heuristics for RRT* by locally linearizing the domain dynamics and applying linear quadratic regulation (LQR). The resulting algorithm, LQR-RRT*, finds optimal plans in domains with complex or underactuated dynamics without requiring domain-specific design choices. We demonstrate its application in domains that are successively torque-limited, underactuated, and in belief space. © 2012 IEEE.

Full Text

Duke Authors

Cited Authors

  • Perez, A; Platt, R; Konidaris, G; Kaelbling, L; Lozano-Perez, T

Published Date

  • January 1, 2012

Published In

Start / End Page

  • 2537 - 2542

International Standard Serial Number (ISSN)

  • 1050-4729

Digital Object Identifier (DOI)

  • 10.1109/ICRA.2012.6225177

Citation Source

  • Scopus