kth.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
Pedestrian-Aware Motion Planning for Autonomous Driving in Complex Urban Scenarios
Department of Mobility Systems Engineering at the Technical University of Munich.ORCID iD: 0000-0001-7120-0796
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL.ORCID iD: 0000-0002-2069-6581
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL.ORCID iD: 0000-0003-4173-2593
Department of Mobility Systems Engineering at the Technical University of Munich.ORCID iD: 0000-0001-9197-2849
(English)Manuscript (preprint) (Other academic)
Abstract [en]

Motion planning in uncertain environments like complex urban areas is a key challenge for autonomous vehicles (AVs). The aim of our research is to investigate how AVs can navigate crowded, unpredictable scenarios with multiple pedestrians while maintaining a safe and efficient vehicle behavior. So far, most research has concentrated on static or deterministic traffic participant behavior. This paper introduces a novel algorithm for motion planning in crowded spaces by combining social force principles for simulating realistic pedestrian behavior with a risk-aware motion planner.

We evaluate this new algorithm in a 2D simulation environment to rigorously assess AV-pedestrian interactions, demonstrating that our algorithm enables safe, efficient, and adaptive motion planning, particularly in highly crowded urban environments—a first in achieving this level of performance. This study has not taken into consideration real-time constraints and has been shown only in simulation so far. Further studies are needed to investigate the novel algorithm in a complete software stack for AVs on real cars to investigate the entire perception, planning and control pipeline in crowded scenarios. We release the code developed in this research as an open-source resource for further studies and development. It can be accessed at the following link: https://github.com/TUM-AVS/PedestrianAwareMotionPlanning.

National Category
Robotics and automation
Identifiers
URN: urn:nbn:se:kth:diva-362135OAI: oai:DiVA.org:kth-362135DiVA, id: diva2:1950713
Note

QC 20250409

Available from: 2025-04-08 Created: 2025-04-08 Last updated: 2025-04-14Bibliographically approved
In thesis
1. Mind the Unknown: Risk- and Occlusion-Aware Motion Planning for Autonomous Vehicles
Open this publication in new window or tab >>Mind the Unknown: Risk- and Occlusion-Aware Motion Planning for Autonomous Vehicles
2025 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Autonomous vehicles (AVs) must navigate uncertain environments while ensuring safety, particularly in scenarios involving risk and occlusions. This thesis develops structured approaches to risk- and occlusion-aware motion planning, integrating theoretical advancements with real-world validation.

To address risk in motion planning, we introduce a framework that quantifies both the probability and severity of safety violations, enabling AVs to reason about risk while maintaining operational efficiency. Complementing this, we investigate pedestrian-aware motion planning in urban environments, incorporating a harm-based risk model to balance safety and progress in interactions with vulnerable road users.

Occlusions pose a major challenge by limiting direct visibility of critical road users. We develop a method for tracking and reasoning about hidden obstacles using reachability analysis and formal logics. By incorporating prior observations, our approach systematically refines possible states of occluded agents, reducing unnecessary conservatism. For high-speed driving, we refine velocity bounds on occluded traffic participants, preventing worst-case assumptions that could lead to excessive braking. Additionally, we explore vehicle-to-everything (V2X) communication to enhance situational awareness, enabling AVs to infer and share information about occluded regions in real time.

Finally, we propose an occlusion-aware planning framework that integrates tree-based motion planning with reachability-based occlusion tracking. This enables AVs to proactively reason about future observations—or their absence—ensuring robust decision-making under limited sensing. By reducing overly conservative constraints while maintaining safety guarantees, our approach addresses key issues in occlusion-aware motion planning.

Together, these contributions advance the ability of AVs to operate safely and efficiently in demanding environments, supporting scalable real-world deployment.

Abstract [sv]

Autonoma fordon måste fatta säkra beslut trots osäkerheter i trafiken, särskilt i riskfyllda situationer och när sikten är begränsad. Denna avhandling presenterar metoder för att planera ett fordons rörelser på ett sätt som tar hänsyn till både risker och skymda hinder. Här kombineras teoretiska resultat med praktisk validering i realistiska trafikförhållanden.

För att hantera riskerna i planeringen introducerar vi ett ramverk som systematiskt bedömer både sannolikheten och konsekvenserna av potentiella säkerhetsproblem. Detta möjliggör en mer nyanserad plan som tar hänsyn till säkerheten utan att begränsa fordonet i onödan. Vi studerar särskilt planering i stadstrafik och utvecklar en riskmodell som väger säkerhet mot effektiv framkomlighet vid möten med exempelvis fot\-gängare och cyklister.

Skymd sikt utgör en utmaning för autonoma fordon. För att bemöta detta utvecklar vi en metod baserad på räckviddsanalys och logisk slutledning, som kan resonera kring möjliga dolda trafikanter. Genom att använda tidigare observationer kan metoden utesluta omöjliga scenarier och därmed undvika överdrivet defensiva beslut. För motorvägskörning inför vi även antaganden om trafikanters möjliga accelerationer, vilket ytterligare minskar behovet av onödiga inbromsningar. Dessutom undersöker vi hur fordonskommunikation (V2X) kan användas för att dela information om skymda områden och därmed förbättra fordonens beslutsunderlag.

Slutligen föreslår vi ett planeringsramverk där en trädstruktur av möjliga rörelser kombineras med räckviddsanalys för att hantera skymd sikt. Detta tillåter att proaktivt resonera kring framtida observationer och deras möjliga frånvaro. På så sätt kan fordonen fatta säkra och effektiva beslut även när sikten är begränsad. Vår metod adresserar därmed viktiga utmaningar inom området och bidrar till att minska onödiga säkerhetsmarginaler utan att kompromissa med säkerheten. Tillsammans stärker dessa resultat autonoma fordons förmåga att navigera säkert och effektivt i komplexa trafikmiljöer. Detta öppnar för bredare användning i verkliga trafiksystem.

Place, publisher, year, edition, pages
KTH Royal Institute of Technology, 2025. p. 58
Series
TRITA-EECS-AVL ; 2025-42
National Category
Robotics and automation
Identifiers
urn:nbn:se:kth:diva-362364 (URN)978-91-8106-247-2 (ISBN)
Public defence
2025-05-09, Kollegiesalen,Brinellvägen 6, https://kth-se.zoom.us/j/62547376681, Stockholm, 09:00 (English)
Opponent
Supervisors
Funder
Wallenberg AI, Autonomous Systems and Software Program (WASP)
Note

QC 20250415

Available from: 2025-04-15 Created: 2025-04-14 Last updated: 2025-04-28Bibliographically approved

Open Access in DiVA

fulltext(6481 kB)72 downloads
File information
File name FULLTEXT01.pdfFile size 6481 kBChecksum SHA-512
0b66e83d3c0897d75042fde31507f6c1a5cdb78facd705e101555e5f5de1e739c4eb8312f709567c60de690ff98fc722b82f02746bb17c2bb4b43eb79926f710
Type fulltextMimetype application/pdf

Authority records

Nyberg, TrulsTumova, Jana

Search in DiVA

By author/editor
Moller, KorbinianNyberg, TrulsTumova, JanaBetz, Johannes
By organisation
Robotics, Perception and Learning, RPL
Robotics and automation

Search outside of DiVA

GoogleGoogle Scholar
Total: 75 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 354 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