kth.sePublications KTH
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Combining Planning and Learning of Behavior Trees for Robotic Assembly
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL. ABB Robotics, Västerås, Sweden.ORCID iD: 0000-0003-0312-8811
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL. ABB Corporate Research, Västerås, Sweden.ORCID iD: 0000-0002-6119-6399
ABB Robotics, Västerås, Sweden.
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL.ORCID iD: 0000-0003-0579-3372
Show others and affiliations
2022 (English)In: 2022 International Conference on Robotics and Automation (ICRA), Institute of Electrical and Electronics Engineers (IEEE) , 2022, p. 11511-11517Conference paper, Published paper (Refereed)
Abstract [en]

Industrial robots can solve tasks in controlled environments, but modern applications require robots able to operate also in unpredictable surroundings. An increasingly popular reactive policy architecture in robotics is Behavior Trees (BTs) but as other architectures, programming time drives cost and limits flexibility. The two main branches of algorithms to generate policies automatically, automated planning and machine learning, both have their own drawbacks and have not previously been combined for generation of BTs. We propose a method for creating BTs by combining these branches, inserting the result of an automated planner into the population of a Genetic Programming algorithm. Experiments confirm that the proposed method performs well on a variety of robotic assembly problems and outperforms the base methods used separately. We also show that this high level learning of Behavior Trees can be transferred to a real system without further training. 

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE) , 2022. p. 11511-11517
Series
Proceedings - IEEE International Conference on Robotics and Automation, ISSN 1050-4729
Keywords [en]
Assembly, Behavior Trees, Genetic Programming, Forestry, Genetic algorithms, Industrial robots, Learning algorithms, Machine learning, Robot programming, Robotic assembly, Architecture programming, Automated machines, Automated planning, Behaviour Trees, Controlled environment, Genetic programming algorithms, Machine-learning, Modern applications, Policy architecture, Programming time
National Category
Robotics and automation Computer Sciences
Identifiers
URN: urn:nbn:se:kth:diva-322408DOI: 10.1109/ICRA46639.2022.9812086ISI: 000941277603011Scopus ID: 2-s2.0-85127077124OAI: oai:DiVA.org:kth-322408DiVA, id: diva2:1718911
Conference
39th IEEE International Conference on Robotics and Automation, ICRA 2022, 23 May 2022 through 27 May 2022, Philadelphia, USA
Note

Part of proceedings: ISBN 9781728196817, QC 20230125

Available from: 2022-12-14 Created: 2022-12-14 Last updated: 2026-02-13Bibliographically approved
In thesis
1. Creating Behavior Trees for Autonomous Versatile Robots
Open this publication in new window or tab >>Creating Behavior Trees for Autonomous Versatile Robots
2026 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

This thesis tackles the long-standing problem of writing computer programs to control robots, ideally generating programs automatically without actually programming at all. For motivation, we notice that in recent years, two strong trends in industry are those of collaborative and mobile robotics. These application types share a critical property where robot programs now have to autonomously react to diverse events. Autonomous robots that operate without regular human intervention or guidance must therefore be controlled by policies that execute different actions depending on the circumstances, but creating a robust policy is considerably more difficult than writing a linear program that always executes the same instructions. There is also an established global industrial trend of more flexible production and smaller batches, leading to programming and commissioning costs becoming a larger share of the total cost of a robot application. All of this put together has increased the already high pressure to make robots easier and faster to program, or in other words, to make them more versatile. A popular and growing policy architecture used in robotics is behavior trees, driven by their inherent reactivity, transparency, and modularity. How to create behavior trees easily, however, is a highly active research topic, with many methods proposed from varying fields such as machine learning, automated planning, and intuitive user interfaces. In this thesis we study how we can improve and combine various methods such that they complement each other and the resulting system performs better. We propose several composite systems and validate their effectiveness in creating behavior tree policies in multiple robotic benchmark experiments.

Abstract [sv]

Denna avhandling tar upp det långvariga problemet med att skriva datorprogram för att styra robotar, helst genom att generera program automatiskt utan att egentligen programmera alls. Som motivering noterar vi att två starka trender i branschen under senare år är kollaborativa och mobila robotar. Dessa applikationstyper delar en kritisk egenskap där robotprogrammen nu måste reagera autonomt på olika händelser. Autonoma robotar som arbetar utan regelbunden mänsklig inblandning eller vägledning måste därför styras av policyer som utför olika åtgärder beroende på omständigheterna, men att skapa en robust policy är betydligt svårare än att skriva ett linjärt program som alltid utför samma instruktioner. Det finns också en etablerad global industriell trend mot mer flexibel produktion och mindre serier, vilket leder till att programmerings- och driftsättnings-kostnader blir en större andel av den totala kostnaden för en robotapplikation. Allt detta sammantaget har ökat det redan höga trycket på att göra robotar enklare och snabbare att programmera, eller med andra ord, att göra dem mer mångsidiga. En populär och växande policyarkitektur som används inom robotik är beteendeträd, drivet av deras inbyggda reaktivitet, transparens och modularitet. Hur man enkelt skapar beteendeträd är dock ett mycket aktivt forskningsämne, med många metoder föreslagna från olika områden såsom maskininlärning, automatiserad planering och intuitiva användargränssnitt. I denna avhandling studerar vi hur vi kan förbättra och kombinera olika metoder så att de kompletterar varandra och det resulterande systemet presterar bättre. Vi föreslår flera sammansatta system och validerar deras effektivitet i att skapa beteendeträdspolicyer i flera olika jämförande robotexperiment.

Place, publisher, year, edition, pages
Stockholm, Sweden: KTH Royal Institute of Technology, 2026. p. xii, 99
Series
TRITA-EECS-AVL ; 2026:17
Keywords
Behavior trees, robotics
National Category
Robotics and automation
Research subject
Computer Science
Identifiers
urn:nbn:se:kth:diva-376730 (URN)978-91-8106-538-1 (ISBN)
Public defence
2026-03-12, https://kth-se.zoom.us/j/68851106286, F3 (Flodis), Lindstedtsvägen 26 & 28, KTH Campus, Stockholm, 14:00 (English)
Opponent
Supervisors
Funder
Wallenberg AI, Autonomous Systems and Software Program (WASP)
Note

QC 20260213

Available from: 2026-02-14 Created: 2026-02-13 Last updated: 2026-03-04Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Styrud, JonathanIovino, MatteoBjörkman, MårtenSmith, Christian

Search in DiVA

By author/editor
Styrud, JonathanIovino, MatteoBjörkman, MårtenSmith, Christian
By organisation
Robotics, Perception and Learning, RPL
Robotics and automationComputer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 121 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf