Volltext-Downloads (blau) und Frontdoor-Views (grau)

Tell Your Robot What To Do: Evaluation of Natural Language Models for Robot Command Processing

  • The use of natural language to indicate robot tasks is a convenient way to command robots. As a result, several models and approaches capable of understanding robot commands have been developed, which however complicates the choice of a suitable model for a given scenario. In this work, we present a comparative analysis and benchmarking of four natural language understanding models - Mbot, Rasa, LU4R, and ECG. We particularly evaluate the performance of the models to understand domestic service robot commands by recognizing the actions and any complementary information in them in three use cases: the RoboCup@Home General Purpose Service Robot (GPSR) category 1 contest, GPSR category 2, and hospital logistics in the context of the ROPOD project.

Export metadata

Additional Services


Show usage statistics
Document Type:Conference Object
Author:Erick Romero Kramer, Argentina Ortega Sainz, Alex MitrevskiORCiD, Paul G. Plöger
Parent Title (English):Chalup, Niemueller et al. (Eds.): RoboCup 2019: Robot World Cup XXIII. Proceedings of the 23rd RoboCup International Symposium, 8 July 2019, Sydney, Australia. Lecture Notes in Computer Science (LNCS), Vol 11531
First Page:255
Last Page:267
Publisher:Springer International Publishing
Place of publication:Cham
Date of first publication:2019/12/01
Abstract provided by the author.
Keyword:Benchmarking; Comparative analysis; Natural language understanding; Robot commands
Departments, institutes and facilities:Fachbereich Informatik
Projects:ROPOD - Ultra-flat, ultra-flexible, cost-effective robotic pods for handling legacy in logistics (EC/H2020/731848)
Dewey Decimal Classification (DDC):0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Entry in this database:2019/06/05