A proposed architecture for autonomous operations in backhoe machines

Carlos Mastalli; Gerardo Fernández-López

doi:10.1007/978-3-319-08338-4_111

A proposed architecture for autonomous operations in backhoe machines

Carlos Mastalli^*, Gerardo Fernández-López

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

In this work is developed an architecture which consists of four main components: perception system, tasks planning, motion planner, and control systems that allow autonomous operations in backhoe machines. In the first part is described the architecture of control system. A set of techniques for collision mapping of the scene is described and implemented. Moreover, a motion planning system based on Learning fromDemonstration using DynamicMovement Primitives as control policy is proposed, which allows backhoe machines to perform operations in autonomous manner. A statement of reasons is presented, wherein we justified the implementation of such motion system versus planners like A∗, Probabilistic RoadMap (PRM), Rapidly-exploring Random Tree (RRT), etc. In addition, we present the performance of the architecture in a simulation environment.

Original language	English
Title of host publication	Intelligent Autonomous Systems 13
Editors	Emanuele Menegatti, Nathan Michael, Karsten Berns, Hiroaki Yamaguchi
Publisher	Springer
Pages	1549-1559
Number of pages	11
ISBN (Electronic)	9783319083384
ISBN (Print)	9783319083377
DOIs	https://doi.org/10.1007/978-3-319-08338-4_111
Publication status	Published - 3 Sept 2015
Event	13th International Conference on Intelligent Autonomous Systems 2014 - Padova, Italy Duration: 15 Jul 2014 → 18 Jul 2014

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	302
ISSN (Print)	2194-5357
ISSN (Electronic)	2194-5365

Conference

Conference	13th International Conference on Intelligent Autonomous Systems 2014
Abbreviated title	IAS 2014
Country/Territory	Italy
City	Padova
Period	15/07/14 → 18/07/14

Keywords

Autonomous backhoe machine
Dynamic movement primitives
Learning from demonstration
Perception system

ASJC Scopus subject areas

Control and Systems Engineering
General Computer Science

Access to Document

10.1007/978-3-319-08338-4_111

Cite this

@inproceedings{6c9b82b0c7f446ff965a88fa41d87843,

title = "A proposed architecture for autonomous operations in backhoe machines",

abstract = "In this work is developed an architecture which consists of four main components: perception system, tasks planning, motion planner, and control systems that allow autonomous operations in backhoe machines. In the first part is described the architecture of control system. A set of techniques for collision mapping of the scene is described and implemented. Moreover, a motion planning system based on Learning fromDemonstration using DynamicMovement Primitives as control policy is proposed, which allows backhoe machines to perform operations in autonomous manner. A statement of reasons is presented, wherein we justified the implementation of such motion system versus planners like A∗, Probabilistic RoadMap (PRM), Rapidly-exploring Random Tree (RRT), etc. In addition, we present the performance of the architecture in a simulation environment.",

keywords = "Autonomous backhoe machine, Dynamic movement primitives, Learning from demonstration, Perception system",

author = "Carlos Mastalli and Gerardo Fern{\'a}ndez-L{\'o}pez",

note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2016.; 13th International Conference on Intelligent Autonomous Systems 2014, IAS 2014 ; Conference date: 15-07-2014 Through 18-07-2014",

year = "2015",

month = sep,

day = "3",

doi = "10.1007/978-3-319-08338-4_111",

language = "English",

isbn = "9783319083377",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer",

pages = "1549--1559",

editor = "Emanuele Menegatti and Nathan Michael and Karsten Berns and Hiroaki Yamaguchi",

booktitle = "Intelligent Autonomous Systems 13",

}

Mastalli, C & Fernández-López, G 2015, A proposed architecture for autonomous operations in backhoe machines. in E Menegatti, N Michael, K Berns & H Yamaguchi (eds), Intelligent Autonomous Systems 13. Advances in Intelligent Systems and Computing, vol. 302, Springer, pp. 1549-1559, 13th International Conference on Intelligent Autonomous Systems 2014, Padova, Italy, 15/07/14. https://doi.org/10.1007/978-3-319-08338-4_111

A proposed architecture for autonomous operations in backhoe machines. / Mastalli, Carlos; Fernández-López, Gerardo.
Intelligent Autonomous Systems 13. ed. / Emanuele Menegatti; Nathan Michael; Karsten Berns; Hiroaki Yamaguchi. Springer, 2015. p. 1549-1559 (Advances in Intelligent Systems and Computing; Vol. 302).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - A proposed architecture for autonomous operations in backhoe machines

AU - Mastalli, Carlos

AU - Fernández-López, Gerardo

N1 - Publisher Copyright: © Springer International Publishing Switzerland 2016.

PY - 2015/9/3

Y1 - 2015/9/3

N2 - In this work is developed an architecture which consists of four main components: perception system, tasks planning, motion planner, and control systems that allow autonomous operations in backhoe machines. In the first part is described the architecture of control system. A set of techniques for collision mapping of the scene is described and implemented. Moreover, a motion planning system based on Learning fromDemonstration using DynamicMovement Primitives as control policy is proposed, which allows backhoe machines to perform operations in autonomous manner. A statement of reasons is presented, wherein we justified the implementation of such motion system versus planners like A∗, Probabilistic RoadMap (PRM), Rapidly-exploring Random Tree (RRT), etc. In addition, we present the performance of the architecture in a simulation environment.

AB - In this work is developed an architecture which consists of four main components: perception system, tasks planning, motion planner, and control systems that allow autonomous operations in backhoe machines. In the first part is described the architecture of control system. A set of techniques for collision mapping of the scene is described and implemented. Moreover, a motion planning system based on Learning fromDemonstration using DynamicMovement Primitives as control policy is proposed, which allows backhoe machines to perform operations in autonomous manner. A statement of reasons is presented, wherein we justified the implementation of such motion system versus planners like A∗, Probabilistic RoadMap (PRM), Rapidly-exploring Random Tree (RRT), etc. In addition, we present the performance of the architecture in a simulation environment.

KW - Autonomous backhoe machine

KW - Dynamic movement primitives

KW - Learning from demonstration

KW - Perception system

UR - http://www.scopus.com/inward/record.url?scp=84945969295&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-08338-4_111

DO - 10.1007/978-3-319-08338-4_111

M3 - Conference contribution

AN - SCOPUS:84945969295

SN - 9783319083377

T3 - Advances in Intelligent Systems and Computing

SP - 1549

EP - 1559

BT - Intelligent Autonomous Systems 13

A2 - Menegatti, Emanuele

A2 - Michael, Nathan

A2 - Berns, Karsten

A2 - Yamaguchi, Hiroaki

PB - Springer

T2 - 13th International Conference on Intelligent Autonomous Systems 2014

Y2 - 15 July 2014 through 18 July 2014

ER -

A proposed architecture for autonomous operations in backhoe machines

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this