Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Predicting bucket-filling control actions of a wheel-loader operator using aneural network ensemble
Luleå tekniska universitet, Institutionen för system- och rymdteknik, EISLAB.ORCID-id: 0000-0001-7395-7557
Luleå tekniska universitet, Institutionen för system- och rymdteknik, EISLAB.ORCID-id: 0000-0001-5662-825x
Luleå tekniska universitet, Institutionen för system- och rymdteknik, Datavetenskap.
2018 (engelsk)Inngår i: 2018 International Joint Conference on Neural Networks (IJCNN), Piscataway, NJ: IEEE, 2018, artikkel-id 8489388Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Automatic bucket filling is an open problem since three decades. In this paper, we address this problem with supervised machine learning using data collected from manual operation. The range-normalized actuations of lift joystick, tilt joystick and throttle pedal are predicted using information from sensors on the machine and the prediction errors are quantified. We apply linear regression, k-nearest neighbors, neural networks, regression trees and ensemble methods and find that an ensemble of neural networks results in the most accurate predictions. The prediction root-mean-square-error (RMSE) of the lift action exceeds that of the tilt and throttle actions, and we obtain an RMSE below 0.2 for complete bucket fillings after training with as little as 135 bucket filling examples

sted, utgiver, år, opplag, sider
Piscataway, NJ: IEEE, 2018. artikkel-id 8489388
Serie
Proceedings of the International Joint Conference on Neural Networks, E-ISSN 2161-4407
HSV kategori
Forskningsprogram
Industriell elektronik; Distribuerade datorsystem
Identifikatorer
URN: urn:nbn:se:ltu:diva-71382DOI: 10.1109/IJCNN.2018.8489388Scopus ID: 2-s2.0-85055724313ISBN: 978-1-5090-6014-6 (digital)OAI: oai:DiVA.org:ltu-71382DiVA, id: diva2:1259751
Konferanse
2018 International Joint Conference on Neural Networks (IJCNN);8-13 July 2018;Rio de Janeiro, Brazil
Tilgjengelig fra: 2018-10-30 Laget: 2018-10-30 Sist oppdatert: 2019-02-11bibliografisk kontrollert
Inngår i avhandling
1. Automation of Wheel-Loaders
Åpne denne publikasjonen i ny fane eller vindu >>Automation of Wheel-Loaders
2018 (engelsk)Doktoravhandling, med artikler (Annet vitenskapelig)
Alternativ tittel[sv]
Automation av hjullastare
Abstract [en]

Automation and tele-remote operation of mobile earth moving machines is desired for safety and productivity reasons. With tele-operation and automation, operators can avoid harsh ergonomic conditions and hazardous environments with poor air quality, and the productivity can in principle be improved by saving the time required to commute to and from work areas. Tele-remote operation of a wheel-loader is investigated and compared with manual operation, and it is found that the constrained perception of the machine is a challenging problem with remote operations. Real-time video transmission over wireless is difficult, but presents a way towards improving the remote operator’s quality of experience. To avoid glitches in the real-time video, arising from variable wireless conditions, the use of SCReAM (Self-Clocked Rate Adaptation for Multimedia) protocol is proposed. Experiments with a small scale robot over LTE show the usefulness of SCReAM for time-critical remote control applications. Automation of the bucket-filling step in the loading cycle of a wheel-loader has been an open problem, despite three decades of research. To address the bucket-filling problem, imitation learning has been applied using expert operator data, experiments are performed with a 20-tonne Volvo L180H wheel-loader and an automatic bucket-filling solution is proposed, developed and demonstrated in field-tests. The conducted experiments are in the realm of small data (100 bucket-filling examples), shallow time-delayed neural-network (TDNN), and a wheel-loader interacting with a non-stationary pile-environment. The total delay length of the TDNN model is found to be an important hyperparameter, and the trained and tuned model comes close to the performance of an expert operator with slightly longer bucket-filling time. The proposed imitation learning trained on medium coarse gravel succeeds in filling buckets in a gravel cobble pile. However, a general solution for automatic bucket-filling needs to be adaptive to possible changes in operating conditions. To adapt an initial imitation model for unseen operating conditions, a reinforcement learning approach is proposed and evaluated. A deterministic actor-critic algorithm is used to update actor (control policy) and critic (policy evaluation) networks. The experiments show that by use of a carefully chosen reward signal the models learns to improve and maximizes bucket weights in a gravel-cobble pile with only 40 bucket-filling trials. This shows that an imitation learning based bucket-filling solution equipped with a reinforcement learning agent is well suited for the continually changing operating conditions found in the construction industry. The results presented in this thesis are a demonstration of the use of artificial intelligence and machine learning methods for the operation of construction equipment. Wheel-loader OEMs can use these results to develop an autonomous bucket-filling function that can be used in manual, tele-remote or fully autonomous operations.

sted, utgiver, år, opplag, sider
Luleå: Luleå University of Technology, 2018
Serie
Doctoral thesis / Luleå University of Technology 1 jan 1997 → …, ISSN 1402-1544
HSV kategori
Forskningsprogram
Industriell elektronik
Identifikatorer
urn:nbn:se:ltu:diva-71460 (URN)978-91-7790-258-4 (ISBN)978-91-7790-259-1 (ISBN)
Disputas
2019-01-31, A1545, Luleå, 10:00 (engelsk)
Opponent
Veileder
Tilgjengelig fra: 2018-11-06 Laget: 2018-11-06 Sist oppdatert: 2019-02-19bibliografisk kontrollert

Open Access i DiVA

fulltext(354 kB)26 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 354 kBChecksum SHA-512
f81292cef79a605868a4d69608971bd2835e10cace91e6dd01736542c80ead2da80b4792c35fbced51d48a770cdb34d8a3effa0dfc5da9d3fcb1da1d455b2acb
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fulltekstScopus

Personposter BETA

Dadhich, SiddharthSandin, FredrikBodin, Ulf

Søk i DiVA

Av forfatter/redaktør
Dadhich, SiddharthSandin, FredrikBodin, Ulf
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 26 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

doi
isbn
urn-nbn

Altmetric

doi
isbn
urn-nbn
Totalt: 44 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf