RRT-CoLearn: Towards Kinodynamic Planning Without Numerical Trajectory Optimization

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 random nodes, and computing a steering input to connect the nodes. The core of these challenges is a two point bounda...

Full description

Saved in:
Bibliographic Details
Published in:IEEE robotics and automation letters 2018-07, Vol.3 (3), p.1655-1662
Main Authors: Wolfslag, Wouter J., Bharatheesha, Mukunda, Moerland, Thomas M., Wisse, Martijn
Format: Article
Language:English
Subjects:
Approximation algorithms
Boundary value problems
Computation
Heuristic algorithms
learning and adaptive systems
Motion and path planning
Nodes
Optimal control
optimization and optimal control
Parameterization
Pendulums
Planning
Prediction algorithms
Steering
Supervised learning
Trajectory
Trajectory optimization
Trajectory planning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 random nodes, and computing a steering input to connect the nodes. The core of these challenges is a two point boundary value problem, known to be NP-hard. Recently, the distance metric has been approximated using supervised learning, reducing computation time drastically. Previous work on such learning RRTs use direct optimal control to generate the data for supervised learning. This letter 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. This eliminates the need for a local planner in learning RRTs. Experimental results on a pendulum swing up show tenfold speed-up in both the offline data generation and the online planning time.
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2018.2801470