LTL-Transfer: Skill Transfer for Temporal Task Specification

Jason Xinyu Liu, Ankit Shah, Eric Rosen, Mingxi Jia, George Konidaris, Stefanie Tellex

Keywords: zero-shot skill transfer, formal methods

TL;DR: LTL-Transfer is a zero-shot transfer algorithm that reuses skills learning during training to solve novel test tasks without violating any safety constraints.

Abstract: Deploying robots in real-world environments, such as households and manufacturing lines, requires generaliza- tion across novel task specifications without violating safety constraints. Linear temporal logic (LTL) is a widely used task specification language with a compositional grammar that naturally induces commonalities among tasks while preserving safety guarantees. However, most prior work on reinforce- ment learning with LTL specifications treats every new task independently, thus requiring large amounts of training data to generalize. We propose LTL-Transfer, a zero-shot transfer algorithm that composes task-agnostic skills learned during training to safely satisfy a wide variety of novel LTL task specifications. Experiments in Minecraft-inspired domains show that after training on only 50 tasks, LTL-Transfer can solve over 90% of 100 challenging unseen tasks and 100% of 300 commonly used novel tasks without violating any safety constraints. We deployed LTL-Transfer at the task-planning level of a quadruped mobile manipulator to demonstrate its zero-shot transfer ability for fetch-and-deliver and navigation tasks.

Submission Number: 14