RRT-CoLearn: Towards kinodynamic planning without numerical trajectory optimization

Wouter Wolfslag, Mukunda Bharatheesha, Thomas Moerland, Martijn Wisse

Research output: Contribution to journalArticleScientificpeer-review

6 Citations (Scopus)

Abstract

Sampling-based kinodynamic planners, such as Rapidly-exploring Random Trees (RRTs), pose two fundamental challenges: computing a reliable (pseudo-)metric for the distance between two randomly sampled nodes, and computing a steering input to connect the nodes. The core of these challenges is a Two Point Boundary Value Problem, which is known to be NP-hard. Recently, the distance metric has been approximated using supervised learning, reducing computation time drastically. The previous work on such learning RRTs use direct optimal control to generate the data for supervised learning. This paper proposes to use indirect optimal control instead, because it provides two benefits: it reduces the computational effort to generate the data, and it provides a low dimensional parametrization of the action space. The latter allows us to learn both the distance metric and the steering input to connect two nodes. This eliminates the need for a local planner in learning RRTs. Experimental results on a pendulum swing up show 10-fold speed-up in both the offline data generation and the online planning time, leading to at least a 10-fold speed-up in the overall planning time.

Original languageEnglish
Pages (from-to)1655-1662
JournalIEEE Robotics and Automation Letters
Volume3
Issue number3
DOIs
Publication statusPublished - 2018

Fingerprint Dive into the research topics of 'RRT-CoLearn: Towards kinodynamic planning without numerical trajectory optimization'. Together they form a unique fingerprint.

  • Cite this