arXiv cs.AI· 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·· 2 小时前AI 评分39
Kairos：面向经典、数值、时序与混合 PDDL 的语义感知规划引擎编排
Kairos: Semantics-Aware Orchestration of Planning Engines across Classical, Numeric, Temporal and Hybrid PDDL
AI 导读
Kairos 是一个语义感知的规划编排系统，根据任务的 PDDL 语义从五种引擎（含接地启发式搜索、压缩 snap-action 时序搜索、时间步混合动力学、提升搜索）中选择并调度，所有候选计划经独立验证器校验。
正文 · 原文
Abstract:Planning at run time, as in robots that re-plan while they act, needs a planner that reads the PDDL its users write (durative actions, numeric resources, time windows, continuous change), answers quickly, and delivers only validated plans. Specialised planners are strong on individual fragments of PDDL, but they differ in coverage, latency and in what their failures mean. We study whether selecting heterogeneous engines from the semantics of each task can give broad coverage of PDDL, from STRIPS to PDDL+, while remaining competitive with specialised planners and making explicit what each answer guarantees. Kairos profiles each task to decide which of five engines apply (ground heuristic search, compressed and snap-action temporal search, time steps for hybrid dynamics, lifted search) and schedules them under one budget of time and memory. Every candidate plan is checked by a validator independent of the planner's transformations, and "unsolvable" is reported only when a search whose exhaustion is a proof exhausts its space. On 1,756 tasks from nine comparative suites, Kairos solves more tasks at the full limits than the strongest evaluated planner of each suite, with the largest differences on numeric, temporal, PDDL3 and PDDL+ planning, and it also solves the most tasks at 100 ms and 1 s. Resampling over domains, the gain is above zero in six of the nine suites, while on classical planning against LAMA it is within the noise. A further 450 feature-oriented tasks and 26 one-feature probes show that Kairos handles all seventeen features probed, where no other planner evaluated handles more than eight. Ablations identify compressed temporal search and the novelty fallback as major contributors, and a comparison with VAL traces every disagreement to a PDDL+ convention or to a documented VAL defect. Planner and benchmark are open source.
| Comments: | 32 pages, 3 figures, 11 tables. Submitted to the Journal of Artificial Intelligence Research. Code: this https URL ; benchmark, scripts and results: this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Robotics (cs.RO) |
| ACM classes: | I.2.8 |
| Cite as: | arXiv:2610.39454 [cs.AI] |
| (or arXiv:2610.39454v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.39454 arXiv-issued DOI via DataCite |
Submission history
From: Francisco Martín-Rico [view email]
[v1]
Thu, 29 Oct 2026 06:25:01 UTC (112 KB)
来源：arXiv cs.AI · arxiv.org