RecPo 框架:通过重组已有技能知识库实现机器人技能快速适配
Reconfiguring Procedural Knowledge for Compositional Robot Skill Adaptation
做机器人或具身智能的值得看这篇:RecPo 不训新策略,而是把已学技能存成知识库,新任务来了直接组合查询,1 毫秒出方案。真实机器人上改几条记忆就能换目标,省掉了每个任务重训的成本。
arXiv 论文提出 RecPo 框架,研究通用行为模型如何通过重组已有程序性知识来适配新任务,而不是从头学习新行为。作者将这种能力定义为"可重构性":在任务规格只给出高层目标、程序规格只暴露有限可复用因子的稀疏条件下,低成本地重新组织已有技能组件与关系。
RecPo 的核心机制是以任务无关的方式表示技能:它维护一个由技能诱导的状态转移组成的程序知识库,每个"程序视图"(procedure view)暴露一个可复用因子并保留局部技能连通性。部署时用同一组视图解析任务规格,在存储的关系上求解组合查询,从而绑定出可执行的技能序列。
在扩展版 Franka Kitchen 长程任务基准上,RecPo 达到 91.9% 的有序完成率,每回合任务推理耗时仅 1.0 ms,且在不同程序支持度和任务记录稀疏度下均保持稳定。真实机器人实验还表明,仅通过局部内存编辑就能完成适配,无需针对具体任务重新训练。
Reconfiguring Procedural Knowledge for Compositional Robot Skill Adaptation
General-purpose behavior models increasingly internalize broad procedural knowledge during training, making their adaptation to new goals and skill interfaces less a problem of learning entirely new behaviors than of reconfiguring existing competence. We study this capability as reconfigurability, the ability to realize new behaviors by cost-efficiently restructuring existing components and relations under sparse governing information, where task specifications provide high-level goals and procedure specifications expose a limited set of reusable factors, leaving the concrete bindings and compositions required for execution underdetermined. We propose RecPo, a framework that represents skills task-agnostically through multiple procedure views and materializes executable skill sequences by composing stored transitions to realize task-specific changes. RecPo maintains a procedure knowledge base of skill-induced transitions, with each view exposing a reusable factor and preserving local skill connectivity. At deployment, it interprets task specifications through the same views and resolves the resulting compositional queries over the stored relations to bind skills for execution. On long-horizon tasks in an extended Franka Kitchen benchmark, RecPo achieves 91.9% ordered completion with 1.0 ms of task inference per episode across varying procedure support and task-record sparsity. Real-robot studies further demonstrate adaptation through local memory edits without task-specific retraining.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include RecPo, robots, Franka Kitchen, skill learning.
Source attribution: curated from arXiv cs.AI (@Daehee Lee, Dongsu Lee, Sanghyun Ahn, Minjong Yoo, Honguk Woo).