2026-09-10T09:45:00Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:27560 2026-09-10T05:38:43Z ddc:004 open_access

From Trajectories to Relations: Interpreting Overtake Manoeuvres with Large Language Models and Qualitative Spatial Representations (Short Paper) Verdoodt, Jana Zhang, Changbo De Sloover, Lars Huang, Haosheng Van de Weghe, Nico micro-scale traffic analysis overtaking behaviour symbolic movement encoding spatial reasoning expert evaluation This paper explores whether qualitative spatial encodings make overtake manoeuvres more interpretable to a large language model (LLM). Using simulated traffic trajectories from a microscopic road-network model, we encode the same overtake event at three levels of complexity through Point-Descriptor-Precedence (PDP) inequality matrices. An LLM is then used in a staged, zero-shot API workflow in which longitudinal and lateral descriptor encodings derived from these matrices are interpreted separately and then merged into a final manoeuvre interpretation. Outputs are assessed through expert-based qualitative evaluation focusing on relational correctness, spatial precision, completeness, and interpretive adequacy. For the selected case, the results suggest that the model can produce meaningful natural-language interpretations at all three levels, but that these change as complexity increases. The 2-point representation yields the clearest focal manoeuvre, the 5-point representation offers the best balance between contextual richness and interpretability, and the 10-point representation produces the most nuanced structural reading, although in a less concise form. The paper should be read as an exploratory study of representation effects rather than as a benchmark of LLM performance. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Jana Verdoodt and Changbo Zhang and Lars De Sloover and Haosheng Huang and Nico Van de Weghe 2026 Is Part Of LIPIcs, Volume 393, 17th International Conference on Spatial Information Theory (COSIT 2026) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.COSIT.2026.16 urn:nbn:de:0030-drops-275607 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.COSIT.2026.16 eng https://creativecommons.org/licenses/by/4.0/legalcode