Zero-Shot Signal Temporal Logic Planning with Disjunctive Branch Selection in Dynamic Semantic Maps

TL;DR

This paper introduces a zero-shot STL planning method that combines Transformer architectures and heuristic strategies to generate feasible trajectories in dynamic environments without retraining.

Contribution

It presents a novel zero-shot STL planning framework that effectively handles disjunctive subformulas and ensures logical coherence across sub-tasks.

Findings

Achieves superior zero-shot generalization to changing environments.

Handles complex disjunctive STL subformulas effectively.

Demonstrates consistent performance gains in dynamic semantic maps.

Abstract

Signal Temporal Logic (STL) offers verifiable task specifications and is crucial for safety-critical control. Yet STL planning remains challenging: exact optimization-based methods are often too slow, and learning-based methods struggle to generalize across varying environments. We propose a zero-shot STL planning solver for variable-map environments that generates feasible trajectories without retraining. By integrating a map-conditioned Transformer architecture with a lightweight heuristic, our approach effectively handles complex disjunctive (OR) subformulas. Furthermore, we leverage Transitive Reinforcement Learning (TRL) to ensure consistent temporal grounding and logical coherence across decomposed sub-tasks. Experiments on dynamic semantic maps with diverse obstacle layouts demonstrate consistent gains, highlighting the framework's superior zero-shot generalization to changing environments and broad STL coverage.