Improving Autonomous Robotic Navigation Using Imitation Learning

Simple item page
dc.contributor.authorCèsar-Tondreau, Brianen
dc.contributor.authorWarnell, Garretten
dc.contributor.authorStump, Ethanen
dc.contributor.authorKochersberger, Kevin B.en
dc.contributor.authorWaytowich, Nicholas R.en
dc.date.accessioned2021-09-02T17:44:47Zen
dc.date.available2021-09-02T17:44:47Zen
dc.date.issued2021-06-01en
dc.description.abstractAutonomous navigation to a specified waypoint is traditionally accomplished with a layered stack of global path planning and local motion planning modules that generate feasible and obstacle-free trajectories. While these modules can be modified to meet task-specific constraints and user preferences, current modification procedures require substantial effort on the part of an expert roboticist with a great deal of technical training. In this paper, we simplify this process by inserting a Machine Learning module between the global path planning and local motion planning modules of an off-the shelf navigation stack. This model can be trained with human demonstrations of the preferred navigation behavior, using a training procedure based on Behavioral Cloning, allowing for an intuitive modification of the navigation policy by non-technical users to suit task-specific constraints. We find that our approach can successfully adapt a robot’s navigation behavior to become more like that of a demonstrator. Moreover, for a fixed amount of demonstration data, we find that the proposed technique compares favorably to recent baselines with respect to both navigation success rate and trajectory similarity to the demonstrator.en
dc.description.versionPublished versionen
dc.format.extent10 pagesen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationCèsar-Tondreau B, Warnell G, Stump E, Kochersberger K and Waytowich NR (2021) Improving Autonomous Robotic Navigation Using Imitation Learning. Front. Robot. AI 8:627730. doi: 10.3389/frobt.2021.627730en
dc.identifier.doihttps://doi.org/10.3389/frobt.2021.627730en
dc.identifier.urihttp://hdl.handle.net/10919/104917en
dc.identifier.volume8en
dc.language.isoenen
dc.publisherFrontiers Mediaen
dc.rightsCreative Commons Attribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.subjectautonomous navigationen
dc.subjectlearning from demonstrationen
dc.subjectimitation learningen
dc.subjecthuman in the loopen
dc.subjectrobot learning and behavior adaptationen
dc.titleImproving Autonomous Robotic Navigation Using Imitation Learningen
dc.title.serialFrontiers in Robotics and AIen
dc.typeArticle - Refereeden
dc.type.dcmitypeTexten

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
frobt-08-627730.pdf
Size:
2.04 MB
Format:
Adobe Portable Document Format
Description:
Download

Collections

Open Access Subvention Fund Articles
Scholarly Works, Mechanical Engineering
Strategic Growth Area: Creativity and Innovation (C&I)