Using Unsupervised Learning to Explore Robot-Pedestrian Interactions in Urban Environments

Sebastian Zug, Georg Jager, Norman Seyffer, Martin Plank, Gero Licht, Felix Wilhelm Siebert

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

This study identifies a gap in data-driven approaches to robot-centric pedestrian interactions and proposes a corresponding pipeline. The pipeline utilizes unsupervised learning techniques to identify patterns in interaction data of urban environments, specifically focusing on conflict scenarios. Analyzed features include the robot's and pedestrian's speed and contextual parameters such as proximity to intersections. They are extracted and reduced in dimensionality using Principal Component Analysis (PCA). Finally, K-means clustering is employed to uncover underlying patterns in the interaction data. A use case application of the pipeline is presented, utilizing real-world robot mission data from a mid-sized German city. The results indicate the need for enriching interaction representations with contextual information to enable fine-grained analysis and reasoning. Nevertheless, they also highlight the need for expanding the data set and incorporating additional contextual factors to enhance the robots situational awareness and interaction quality.

Original languageEnglish
Title of host publicationProceedings of the 2024 IEEE International Symposium on Robotic and Sensors Environments (ROSE)
Number of pages8
PublisherIEEE
Publication date2024
DOIs
Publication statusPublished - 2024
Event2024 IEEE International Symposium on Robotic and Sensors Environments - Chemnitz, Germany
Duration: 20 Jun 202421 Jun 2024

Conference

Conference2024 IEEE International Symposium on Robotic and Sensors Environments
Country/TerritoryGermany
CityChemnitz
Period20/06/202421/06/2024

Fingerprint

Dive into the research topics of 'Using Unsupervised Learning to Explore Robot-Pedestrian Interactions in Urban Environments'. Together they form a unique fingerprint.

Cite this