Learning Compositional Symbolic Task Rules from Demonstrations with Inductive Logic Programming

Oleh Borys, Karla Stepanova

Keywords: task learning, learning from demonstration, ILP, symbolic reasoning, task ontology, rule induction

TL;DR: We present an ILP framework for task-level LfD that induces compositional FOL rules from demonstrations and prior knowledge by decomposing a complex task into simpler targets at multiple abstraction levels, and show preliminary experimental results.

Abstract: 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.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 22