An Imitation Learning Approach for Truck Loading Operations in Backhoe Machines

C. MASTALLI, J. CAPPELLETTO, R. ACUÑA, A. TERRONES, G. FERNÁNDEZ-LÓPEZ

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract / Description of output

Abstract This paper presents a motion planning and control system architecture development for autonomous earthmoving operations in excavating machines such as loading a dump truck. The motion planning system is imitation learning based, which is a general approach for learning motor skills from human demonstration. This scheme of supervised learning is based on a dynamical movement primitives (DMP) as control policies (CP). The DMP is a non-linear differential equation that encode movements, which are used to learn tasks in backhoe machines. A general architecture to achieve autonomous truck loading operations is described. Also, the effectiveness of our approach for truck loading task is demonstrated, where the machine can adapt to different operating scenarios.
Original languageEnglish
Title of host publicationAdaptive Mobile Robotics
Subtitle of host publicationProceedings of the Fifteenth International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines
PublisherWorld Scientific
Pages821-830
Number of pages10
ISBN (Electronic)978-981-4414-96-5
ISBN (Print)978-981-4415-94-1
DOIs
Publication statusPublished - 30 Sept 2012
Event15th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines - Baltimore, United States
Duration: 23 Jul 201226 Jul 2012

Conference

Conference15th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines
Abbreviated titleCLAWAR 2012
Country/TerritoryUnited States
CityBaltimore
Period23/07/1226/07/12

Keywords / Materials (for Non-textual outputs)

  • Imitation Learning
  • Dynamical Movement Primitives
  • ExcavatingRobots
  • Backhoe Machine

Fingerprint

Dive into the research topics of 'An Imitation Learning Approach for Truck Loading Operations in Backhoe Machines'. Together they form a unique fingerprint.

Cite this