arXiv Robotics — research abstracts· Francisco Mart\'in Rico, Esther Aguado Gonz\'alez, Francisco Miguel Moreno Olivo, Rodrigo P\'erez Rodr\'iguez, Jos\'e Miguel Guerrero Hern\'andez, Francisco J. Rodr\'iguez Lera·2026-10-30 04:00 UTC· 12 hours agoSignalEditorial score76

Kairos: Semantics-Aware Orchestration of Planning Engines across Classical, Numeric, Temporal and Hybrid PDDL

Summary

Kairos is a planning system that dynamically selects and combines multiple PDDL engines to address a wide range of planning tasks. It outperforms specialized planners in several PDDL variants and is open-source, offering a benchmark for further research.

Editorial context

This paper introduces Kairos, a planning system that integrates multiple PDDL engines to handle diverse planning tasks efficiently. It demonstrates superior performance across various PDDL variants and provides open-source tools for further research.

Source: arXiv Robotics — research abstracts · Read original article ↗

Loading article text…

Source：arXiv Robotics — research abstracts · arxiv.org

#Research #Robot policies #Reinforcement learning #Evaluation