ROBOT MOTION PLANNING WITH LARGE LANGUAGE MODELS: LANGUAGE-TO-PATHS GUIDANCE OVER SUPERFACETS
Albanian Journal of Natural and Technical Sciences · 25.06.2026 · 31 (2) · 7-36
DOI: 10.67537/ajnts3102017 ↗Kurz gefasst
Fachartikel in der Zeitschrift Albanian Journal of Natural and Technical Sciences, online erschienen am 25.06.2026. Verfasst von Evis Plaku und 1 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Robots operating in cluttered environments must compute collision-free motions under nonholonomic dynamics while maintaining fast, reliable planning. This article presents a language-guided motion-planning framework built on a visibility-aware superfacet decomposition, which partitions free space into navigable regions connected by a region graph. A large language model (LLM) converts natural-language preferences into a constrained domain-specific language (DSL) containing route, waypoint, constraint, and parameter hints. Each hint is validated by an affordance/feasibility gate that enforces connectivity and visibility, rejects unreachable suggestions, accounts for recent failures, and bounds updates. Validated hints softly bias inter-region costs and sampling priorities, while kinodynamic rollouts and collision checking determine final feasibility. Experiments with car-like and snake-like robots in cluttered 2D scenes show an approximately 18% reduction in mean planning time and fewer dead-end explorations relative to the superfacet baseline. The framework maintains comparable success rates and path quality, demonstrating that natural-language guidance can be integrated without increasing computational overhead. This makes the framework practical for non-expert operators to direct robot navigation without knowledge of the underlying planning mechanics.
Zitieren
APA
Plaku, E., & Civici, N. (2026). ROBOT MOTION PLANNING WITH LARGE LANGUAGE MODELS: LANGUAGE-TO-PATHS GUIDANCE OVER SUPERFACETS. Albanian Journal of Natural and Technical Sciences, 31(2), 7-36. https://doi.org/10.67537/ajnts3102017
Vancouver
Plaku E, Civici N. ROBOT MOTION PLANNING WITH LARGE LANGUAGE MODELS: LANGUAGE-TO-PATHS GUIDANCE OVER SUPERFACETS. Albanian Journal of Natural and Technical Sciences. 2026;31(2):7-36. doi:10.67537/ajnts3102017
BibTeX
@article{Plaku2026,
author = {Plaku, Evis and Civici, Nikolla},
title = {ROBOT MOTION PLANNING WITH LARGE LANGUAGE MODELS: LANGUAGE-TO-PATHS GUIDANCE OVER SUPERFACETS},
journal = {Albanian Journal of Natural and Technical Sciences},
year = {2026},
volume = {31},
number = {2},
pages = {7--36},
doi = {10.67537/ajnts3102017}
}
EUVIMED