
Ensuring traffic rule compliance in motion planners is crucial but challenging. This dissertation introduces a trajectory repair framework that couples satisfiability modulo theories with game theory and reachability analysis to enforce compliance with formalized rules, prioritizing repair over costly replanning. We also propose an offline method leveraging large language models to diagnose and enhance motion planners. Evaluations confirm that our approach advances legally safe automated driving. Die Einhaltung von Verkehrsregeln in Bewegungsplanern ist essenziell, aber herausfordernd. Diese Dissertation präsentiert ein Trajektorienreparatur-Framework, das Erfüllbarkeit-Modulo-Theorien, Spieltheorie und mengenbasierte Erreichbarkeitsanalyse kombiniert, um die Einhaltung formalisierter Regeln zu gewährleisten. Reparatur wird gegenüber kostenintensiver Neuplanung priorisiert. Zudem nutzen wir große Sprachmodelle zur Diagnose und Verbesserung von Bewegungsplanern. Evaluierungen bestätigen den Fortschritt rechtssicherer automatisierter Fahrzeuge.
Motion and path planning;formal methods in robotics and automation;intelligent transportation systems;trajectory repair;automated software repair, Technik, Bewegungs- und Pfadplanung;formale Methoden in Robotik und Automatisierung;intelligente Transportsysteme;Trajektorienreparatur;automatisierte Softwarereparatur, ddc: ddc:600
Motion and path planning;formal methods in robotics and automation;intelligent transportation systems;trajectory repair;automated software repair, Technik, Bewegungs- und Pfadplanung;formale Methoden in Robotik und Automatisierung;intelligente Transportsysteme;Trajektorienreparatur;automatisierte Softwarereparatur, ddc: ddc:600
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
