SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning

TL;DR

SAGAS is a novel offline, model-free framework that combines symbolic synthesis and learned reachability graphs to enable zero-shot generalization for robotic planning with LTL specifications.

Contribution

It introduces SAGAS, which learns a reusable reachability graph from offline data and performs semantic graph augmentation for unseen LTL tasks without retraining.

Findings

Enables zero-shot generalization to unseen LTL specifications.

Produces executable, cost-efficient behaviors from offline data.

Outperforms existing methods on locomotion task suites.

Abstract

Linear Temporal Logic (LTL) provides a rigorous framework for specifying long-horizon robotic tasks, yet existing approaches face a trade-off: model-based synthesis relies on accurate labeled transition systems, whereas learning-based methods often require online interaction, task-specific rewards, or specification-conditioned training. We study LTL-specified robotic planning and execution in a stricter offline, model-free setting, where the agent is given only fixed, task-agnostic trajectory fragments, with no dynamics model, task demonstrations, or online data collection. To address this setting, we propose SAGAS, a framework that combines the compositionality of symbolic synthesis with the data-driven reachability structure learned from offline trajectories. SAGAS first learns a reusable latent reachability graph and a frozen goal-conditioned executor from fragmented offline data. For each new LTL formula, it performs task-time semantic graph augmentation to ground state-defined propositions on the learned graph, and applies B\"uchi product search to synthesize a cost-aware accepting prefix--suffix waypoint plan executed by the frozen executor. By shifting formula-specific reasoning from policy learning to test-time graph augmentation and symbolic search, SAGAS enables zero-shot generalization to unseen, data-supported LTL specifications without task-specific reward design, policy retraining, or online interaction. Experiments on LTL task suites constructed from OGBench locomotion domains show that this design produces executable and cost-efficient prefix--suffix behaviors for diverse unseen LTL tasks from fragmented offline data.