Deploying robots in real-world environments, such as households and manufacturing lines, requires generalization 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 reinforcement learning with LTL specifications treats every new task independently, thus requiring large amounts of training data to generalize.
We propose a zero-shot transfer algorithm, LTL-Transfer, 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.
@inproceedings{liu2024transfer,
title = {LTL-Transfer: Skill Transfer for Temporal Task Specification},
author = {Liu, Jason Xinyu and Shah, Ankit and Rosen, Eric and Jia, Mingxi and Konidaris, George and Tellex, Stefanie},
booktitle = {2024 IEEE International Conference on Robotics and Automation (ICRA)},
year = {2024},
}