Zero-Shot Trajectory Planning for Signal Temporal Logic Tasks

TL;DR

This paper introduces a hierarchical zero-shot planning framework that generates executable trajectories for complex STL tasks with unknown dynamics, using only task-agnostic data and diffusion models.

Contribution

It presents a novel zero-shot planning method for STL tasks that decomposes specifications, searches for timed waypoints, and uses diffusion models for trajectory generation.

Findings

Guarantees STL satisfaction formally.

Effective in generating feasible trajectories.

Works across diverse long-horizon tasks.

Abstract

Signal Temporal Logic (STL) is a powerful specification language for describing complex temporal behaviors of continuous signals, making it well-suited for high-level robotic task descriptions. However, generating executable plans for STL tasks is challenging, as it requires consideration of the coupling between the task specification and the system dynamics. Existing approaches either follow a model-based setting that explicitly requires knowledge of the system dynamics or adopt a task-oriented data-driven approach to learn plans for specific tasks. In this work, we address the problem of generating executable STL plans for systems with unknown dynamics. We propose a hierarchical planning framework that enables zero-shot generalization to new STL tasks by leveraging only task-agnostic trajectory data during offline training. The framework consists of three key components: (i) decomposing the STL specification into several progresses and time constraints, (ii) searching for timed waypoints that satisfy all progresses under time constraints, and (iii) generating trajectory segments using a pre-trained diffusion model and stitching them into complete trajectories. We formally prove that our method guarantees STL satisfaction, and simulation results demonstrate its effectiveness in generating dynamically feasible trajectories across diverse long-horizon STL tasks.