RRT-CoLearn: towards kinodynamic planning without numerical trajectory optimization

Author name not available (Why is that?)

Publication date: 27 October 2017

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.

Has companion code repository: https://github.com/ortix/generative-colearn

This page was built for publication: RRT-CoLearn: towards kinodynamic planning without numerical trajectory optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6293119)