DAG-STL: A Hierarchical Framework for Zero-Shot Trajectory Planning under Signal Temporal Logic Specifications

• URL: http://arxiv.org/abs/2604.18343v1
• Date: Mon, 20 Apr 2026 14:41:37 GMT
• Title: DAG-STL: A Hierarchical Framework for Zero-Shot Trajectory Planning under Signal Temporal Logic Specifications
• Abstract summary: We study offline STL planning under unknown dynamics using only task-agnostic trajectory data.<n>We instantiate this idea in DAG-STL, a hierarchical framework that converts long-horizon STL planning into three stages.<n> Experiments in Maze2D, OGBench AntMaze, and the Cube domain show that DAG-STL substantially outperforms direct robustness-guided diffusion.
• Score: 7.389002274709231
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Signal Temporal Logic (STL) is a powerful language for specifying temporally structured robotic tasks. Planning executable trajectories under STL constraints remains difficult when system dynamics and environment structure are not analytically available. Existing methods typically either assume explicit models or learn task-specific behaviors, limiting zero-shot generalization to unseen STL tasks. In this work, we study offline STL planning under unknown dynamics using only task-agnostic trajectory data. Our central design philosophy is to separate logical reasoning from trajectory realization. We instantiate this idea in DAG-STL, a hierarchical framework that converts long-horizon STL planning into three stages. It first decomposes an STL formula into reachability and invariance progress conditions linked by shared timing constraints. It then allocates timed waypoints using learned reachability-time estimates. Finally, it synthesizes trajectories between these waypoints with a diffusion-based generator. This decomposition--allocation--generation pipeline reduces global planning to shorter, better-supported subproblems. To bridge the gap between planning-level correctness and execution-level feasibility, we further introduce a rollout-free dynamic consistency metric, an anytime refinement search procedure for improving multiple allocation hypotheses under finite budgets, and a hierarchical online replanning mechanism for execution-time recovery. Experiments in Maze2D, OGBench AntMaze, and the Cube domain show that DAG-STL substantially outperforms direct robustness-guided diffusion on complex long-horizon STL tasks and generalizes across navigation and manipulation settings. In a custom environment with an optimization-based reference, DAG-STL recovers most model-solvable tasks while retaining a clear computational advantage over direct optimization based on the explicit system model.

Related papers

• Zero-Shot Signal Temporal Logic Planning with Disjunctive Branch Selection in Dynamic Semantic Maps [5.359659831465926]
  Signal Temporal Logic (STL) offers verifiable task specifications and is crucial for safety-critical control.<n>We propose a zero-shot STL planning solver for variable-map environments that generates feasible trajectories without retraining.
  arXiv  Detail & Related papers  (2026-05-02T03:32:23Z)
• GraSP-STL: A Graph-Based Framework for Zero-Shot Signal Temporal Logic Planning via Offline Goal-Conditioned Reinforcement Learning [5.573866102893894]
  We study offline, zero-shot planning under Signal Temporal Logic (STL) specifications.<n>We propose GraSP-STL, a graph-search-based framework for zero-shot STL planning from offline trajectories.
  arXiv  Detail & Related papers  (2026-03-31T10:15:42Z)
• STL-SVPIO: Signal Temporal Logic guided Stein Variational Path Integral Optimization [8.345095354174623]
  Signal Temporal Logic (STL) enables formal specification of complex constraints for robotic task planning.<n>We introduce Signal Vari Temporal Integral Optimization (STL-SVPIO), which reframes STL as a globally informative, differentiable reward-shaping mechanism.<n>We demonstrate that STL-SVPIO significantly outperforms existing methods in both robustness and efficiency for traditional STL tasks.
  arXiv  Detail & Related papers  (2026-03-06T00:53:38Z)
• Agentic Spatio-Temporal Grounding via Collaborative Reasoning [80.83158605034465]
  Temporal Video Grounding aims to retrieve thetemporal tube of a target object or person in a video given a text query.<n>We propose the Agentic Spatio-Temporal Grounder (ASTG) framework for the task of STVG towards an open-world and training-free scenario.<n>Specifically, two specialized agents SRA (Spatial Reasoning Agent) and TRA (Temporal Reasoning Agent) constructed leveraging on modern Multimoal Large Language Models (MLLMs)<n>Experiments on popular benchmarks demonstrate the superiority of the proposed approach where it outperforms existing weakly-supervised and zero-shot approaches by a margin
  arXiv  Detail & Related papers  (2026-02-10T10:16:27Z)
• LLM-Grounded Dynamic Task Planning with Hierarchical Temporal Logic for Human-Aware Multi-Robot Collaboration [17.886091169216538]
  Large Language Models (LLM) enable non-experts to specify openworld multi-robot tasks.<n>LLM plans often lack feasibility and are not efficient, especially in long-horizon scenarios.<n>We propose a neuro-symbolic framework that grounds reasoning into hierarchical specifications.
  arXiv  Detail & Related papers  (2026-02-10T07:11:36Z)
• PILOT: Planning via Internalized Latent Optimization Trajectories for Large Language Models [51.43746425777865]
  Large Language Models (LLMs) often lack the capacity to formulate global strategies, leading to error propagation in long-horizon tasks.<n>We propose PILOT, a framework designed to internalize the strategic oversight of large models into intrinsic Latent Guidance.
  arXiv  Detail & Related papers  (2026-01-07T12:38:56Z)
• Zero-Shot Instruction Following in RL via Structured LTL Representations [54.08661695738909]
  Linear temporal logic (LTL) is a compelling framework for specifying complex, structured tasks for reinforcement learning (RL) agents.<n>Recent work has shown that interpreting instructions as finite automata, which can be seen as high-level programs monitoring task progress, enables learning a single generalist policy capable of executing arbitrary instructions at test time.<n>We propose a novel approach to learning a multi-task policy for following arbitrary instructions that addresses this shortcoming.
  arXiv  Detail & Related papers  (2025-12-02T10:44:51Z)
• Extendable Long-Horizon Planning via Hierarchical Multiscale Diffusion [62.91968752955649]
  This paper tackles a novel problem, extendable long-horizon planning-enabling agents to plan trajectories longer than those in training data without compounding errors.<n>We propose an augmentation method that iteratively generates longer trajectories by stitching shorter ones.<n>HM-Diffuser trains on these extended trajectories using a hierarchical structure, efficiently handling tasks across multiple temporal scales.
  arXiv  Detail & Related papers  (2025-03-25T22:52:46Z)
• Zero-Shot Trajectory Planning for Signal Temporal Logic Tasks [7.389002274709231]
  Signal Temporal Logic (STL) is a powerful specification language for describing complex temporal behaviors of continuous signals.<n> generating executable STL plans for STL tasks is challenging, as it requires consideration of the coupling between the task specification and the system dynamics.<n>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.
  arXiv  Detail & Related papers  (2025-01-23T08:15:52Z)
• Directed Exploration in Reinforcement Learning from Linear Temporal Logic [59.707408697394534]
  Linear temporal logic (LTL) is a powerful language for task specification in reinforcement learning.<n>We show that the synthesized reward signal remains fundamentally sparse, making exploration challenging.<n>We show how better exploration can be achieved by further leveraging the specification and casting its corresponding Limit Deterministic B"uchi Automaton (LDBA) as a Markov reward process.
  arXiv  Detail & Related papers  (2024-08-18T14:25:44Z)
• Towards Unified Token Learning for Vision-Language Tracking [65.96561538356315]
  We present a vision-language (VL) tracking pipeline, termed textbfMMTrack, which casts VL tracking as a token generation task. Our proposed framework serializes language description and bounding box into a sequence of discrete tokens. In this new design paradigm, all token queries are required to perceive the desired target and directly predict spatial coordinates of the target.
  arXiv  Detail & Related papers  (2023-08-27T13:17:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.