用逻辑编程从示范中学习可解释的机器人任务规则
Learning Compositional Symbolic Task Rules from Demonstrations with Inductive Logic Programming
- 通过分层逻辑编程分解复杂任务，逐级学习符号规则
- 在合成积木组装场景中实现对未见物体的任务泛化
- 适合需要可解释、可复用任务结构的研究与工程
从示范学习（LfD）不仅要掌握任务执行方式，还需捕捉解释示范行为的高层任务结构。随着机器人自主性提升，任务表示必须具备可检查性、可重用性和人类可理解性。为此，本文研究如何利用归纳逻辑编程（ILP）表示并学习机器人任务，将复杂任务分解为不同抽象层次的简化学习目标。系统从示范和先验知识中推断符号规则，并在学习高层任务结构时复用已学规则。我们在合成块组装场景中评估该方法，结果表明所学抽象具有可解释性，并能支持对更难、未见过的任务（含新物体）实现强泛化。这些结果初步证明分层ILP是任务级LfD的一种可行路径。
原文摘要 · Abstract (English)
Learning from Demonstration~(LfD) should capture not only how a task is executed, but also its high-level task structure that explains the demonstrated behavior. As robots become more autonomous, such task representations must be inspectable, reusable, and human-interpretable. To address this, we study how to represent and learn robotic tasks with inductive logic programming~(ILP) by decomposing a complex task into a series of simpler learning objectives at different abstraction (ontological) levels. The system infers symbolic rules from demonstrations and prior (domain) knowledge, and reuses learned rules when learning higher-level task structure. We evaluate the approach in a synthetic block-assembly scenario and show that the learned abstractions are interpretable and support strong generalization to harder, held-out tasks with unseen objects. These results provide preliminary evidence that decomposed ILP is a feasible approach to task-level LfD.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。