https://www.mdu.se/

mdu.sePublications
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
Risk-Aware Planning of Collaborative Mobile Robot Applications with Uncertain Task Durations
Mälardalen University, School of Innovation, Design and Engineering, Embedded Systems. Abb Ab, Västerås, Sweden.
Mälardalen University, School of Innovation, Design and Engineering, Embedded Systems.ORCID iD: 0000-0002-9051-929x
Mälardalen University, School of Innovation, Design and Engineering, Embedded Systems.ORCID iD: 0000-0001-6132-7945
Show others and affiliations
2024 (English)In: IEEE Int. Workshop Robot Human Commun., RO-MAN, Institute of Electrical and Electronics Engineers (IEEE) , 2024, p. 1191-1198Conference paper, Published paper (Refereed)
Abstract [en]

The efficiency of collaborative mobile robot applications is influenced by the inherent uncertainty introduced by humans' presence and active participation. This uncertainty stems from the dynamic nature of the working environment, various external factors, and human performance variability. The observed makespan of an executed plan will deviate from any deterministic estimate. This raises questions about whether a calculated plan is optimal given uncertainties, potentially risking failure to complete the plan within the estimated timeframe. This research addresses a collaborative task planning problem for a mobile robot serving multiple humans through tasks such as providing parts and fetching assemblies. To account for uncertainties in the durations needed for a single robot and multiple humans to perform different tasks, a probabilistic modeling approach is employed, treating task durations as random variables. The developed task planning algorithm considers the modeled uncertainties while searching for the most efficient plans. The outcome is a set of the best plans, where no plan is better than the other in terms of stochastic dominance. Our proposed methodology offers a systematic framework for making informed decisions regarding selecting a plan from this set, considering the desired risk level specific to the given operational context.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE) , 2024. p. 1191-1198
Series
IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), ISSN 1944-9437
Keywords [en]
Collaborative robots, Industrial robots, Microrobots, Mobile robots, Nanorobots, Robot applications, Robot programming, Stochastic systems, Collaborative task planning, Deterministics, Dynamic nature, External factors, Human performance, Makespan, Performance variability, Risk aware, Uncertainty, Working environment
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
URN: urn:nbn:se:mdh:diva-69257DOI: 10.1109/RO-MAN60168.2024.10731449ISI: 001348918600153Scopus ID: 2-s2.0-85209780572ISBN: 9798350375022 (print)OAI: oai:DiVA.org:mdh-69257DiVA, id: diva2:1918146
Conference
IEEE International Workshop on Robot and Human Communication, RO-MAN
Available from: 2024-12-04 Created: 2024-12-04 Last updated: 2026-02-16Bibliographically approved
In thesis
1. Task Planning of Industrial Mobile Robots in Collaborative Dynamic Environments
Open this publication in new window or tab >>Task Planning of Industrial Mobile Robots in Collaborative Dynamic Environments
2025 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Over the past decades, industrial robotics has transitioned from fixed, single-purpose machines to flexible, collaborative mobile systems capable of navigating complex factory environments. Today's manufacturing demands, driven by labor scarcity, the need for rapid reconfiguration, and advances in AI and sensing, require robots to perform increasingly sophisticated, non-repetitive tasks alongside human workers. Designing and executing efficient multi-robot missions in such dynamic, human-in-the-loop settings presents multiple challenges: expressing high-level production requirements in a planner-friendly way, handling unexpected execution errors, scaling to large task allocations, and accounting for uncertainties in task durations and human behavior.

This thesis introduces an intuitive task modeling formalism and a suite of algorithmic methods that address these challenges end-to-end. First, we propose a domain-expert-friendly syntax for defining single-robot production missions, automatically generating problem definitions compatible with diverse off-the-shelf planners. To support rapid recovery from errors, we present task roadmaps, a novel planning algorithm that reuses the original search tree to accelerate replanning when execution deviates. We extend the formalism to a multi-robot kitting use case with alternative task locations and introduce a scalable, clustering-based approach to maintain computational tractability.

Recognizing the inherent uncertainties of human-robot collaboration, we further develop a collaborative stochastic task planning framework that integrates human risk preferences and models variability in task and routing durations. Finally, we tackle a collaborative production scenario with complex cross-schedule dependencies, proposing a stochastic scheduling method that generates optimized, deadlock-free plans while balancing efficiency with human well-being.

Extensive simulations and experiments grounded in real-world applications demonstrate that our methods significantly improve planning efficiency, robustness, and adaptability in dynamic industrial settings, paving the way toward more resilient, human-centric robotic automation.

Abstract [sv]

Under de senaste decennierna har industrirobotiken utvecklats från stationära maskiner specialiserade för enstaka typer av uppgifter till flexibla, kollaborativa och mobila system som kan navigera i komplexa fabriksmiljöer. Dagens tillverkningskrav, drivna av bristen på arbetskraft, behovet av snabba omställningar samt framsteg inom AI och sensorteknik, fordrar att robotar utför alltmer sofistikerade, icke-repetitiva uppgifter tillsammans med mänsklig arbetskraft. Att effektivt utforma och genomföra produktionsuppdrag som omfattar samarbete mellan robotar och människor i den typen av dynamiska miljöer medför flera utmaningar: att specificera produktionsprocessen på en användarvänlig abstraktionsnivå som underlättar resursplaneringen,att hantera oväntade fel under exekvering, att skala upp antalet arbetsmoment som ska fördelas och att hantera osäkerheter i tidsåtgång och mänskligt beteende.

Denna avhandling introducerar ett intuitivt sätt att definiera och organisera arbetsmomentsamt en uppsättning algoritmiska metoder som hanterar utmaningarna genom hela kedjan.Först föreslår vi en användarvänlig modellering för att definiera produktionsuppdrag för en robot, med automatisk generering av planeringsproblem kompatibla med olika kommersiella planeringsverktyg. För att möjliggöra en snabb återhämtning vid fel under drift presenterar vi task roadmaps, en ny planeringsalgoritm som återanvänder det ursprungliga sökträdet för att accelerera en omplanering  när exekveringen avviker. Vi utökar modelleringen till en multi-robot kitting-applikation med alternativa upphämtningsplatser och introducerar en klustringsbaserad algoritm som är beräkningsmässigt hanterbar för uppskalade problem.

Med hänsyn till de inneboende osäkerheterna i människa–robot-samarbete utvecklar vi dessutom ett kollaborativt stokastiskt ramverk för planering av robot-uppgifter som integrerar mänskliga riskpreferenser och modellerar en varierande tidsåtgång för arbetsmoment och förflyttningar. Slutligen behandlar vi ett kollaborativt produktionsscenario med komplexa korsschemaberoenden och föreslår en stokastisk schemaläggningsmetod som genererar optimerade, låsningsfria planer där effektivitet balanseras med mänskligt välbefinnande.

Omfattande simuleringar och experiment baserade på realistiska applikationer visar att våra metoder väsentligen förbättrar effektivitet, robusthet och anpassningsbarhet av robot-planering i dynamiska industriella miljöer, vilket banar väg för en mer hållbar, människocentrerad robotautomatisering.

Place, publisher, year, edition, pages
Västerås: Mälardalens universitet, 2025
Series
Mälardalen University Press Dissertations, ISSN 1651-4238 ; 441
National Category
Robotics and automation
Research subject
Computer Science
Identifiers
urn:nbn:se:mdh:diva-73159 (URN)978-91-7485-721-4 (ISBN)
Public defence
2025-10-24, My och digitalt, Mälardalens universitet, Västerås, 09:15 (English)
Opponent
Supervisors
Available from: 2025-09-02 Created: 2025-09-02 Last updated: 2025-10-10Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Lager, AndersMiloradović, BrankoSpampinato, GiacomoNolte, ThomasPapadopoulos, Alessandro

Search in DiVA

By author/editor
Lager, AndersMiloradović, BrankoSpampinato, GiacomoNolte, ThomasPapadopoulos, Alessandro
By organisation
Embedded Systems
Electrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 265 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