TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching

• URL: http://arxiv.org/abs/2505.00562v1
• Date: Thu, 01 May 2025 14:40:07 GMT
• Title: TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching
• Authors: Yue Meng, Chuchu Fan,
• Abstract summary: We propose TeLoGraF, Temporal Logic Graph-encoded Flow, to learn solutions for general STL specifications.<n>We conduct experiments in five simulation environments ranging from simple dynamical models in the 2D space to high-dimensional 7DoF Franka Panda robot arm.<n>Our approach is 10-100X faster in inference and can work on any system dynamics.
• Score: 13.154661571539577
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning to solve complex tasks with signal temporal logic (STL) specifications is crucial to many real-world applications. However, most previous works only consider fixed or parametrized STL specifications due to the lack of a diverse STL dataset and encoders to effectively extract temporal logic information for downstream tasks. In this paper, we propose TeLoGraF, Temporal Logic Graph-encoded Flow, which utilizes Graph Neural Networks (GNN) encoder and flow-matching to learn solutions for general STL specifications. We identify four commonly used STL templates and collect a total of 200K specifications with paired demonstrations. We conduct extensive experiments in five simulation environments ranging from simple dynamical models in the 2D space to high-dimensional 7DoF Franka Panda robot arm and Ant quadruped navigation. Results show that our method outperforms other baselines in the STL satisfaction rate. Compared to classical STL planning algorithms, our approach is 10-100X faster in inference and can work on any system dynamics. Besides, we show our graph-encoding method's capability to solve complex STLs and robustness to out-distribution STL specifications. Code is available at https://github.com/mengyuest/TeLoGraF

Related papers

• Zero-Shot Trajectory Planning for Signal Temporal Logic Tasks [3.831690197072918]
  Signal Temporal Logic (STL) is a powerful specification language for describing complex temporal behaviors of continuous signals. generating executable plans for STL tasks is challenging, as it requires consideration of the coupling between the task specification and the system dynamics. We propose a new planning framework that uses only task-agnostic data during the offline training stage, enabling zero-shot generalization to new STL tasks.
  arXiv  Detail & Related papers  (2025-01-23T08:15:52Z)
• STLCG++: A Masking Approach for Differentiable Signal Temporal Logic Specification [8.017203108408975]
  We present STLCG++, a masking-based approach that parallelizes STL computation across timesteps.<n>We also introduce a smoothing technique for different temporal boundsiability through time interval bounds.<n>We demonstrate STLCG++'s benefits through three robotics use cases and provide open-source Python libraries in JAX and PyTorch.
  arXiv  Detail & Related papers  (2025-01-08T00:06:43Z)
• Constrained LTL Specification Learning from Examples [8.544277223210894]
  We propose a new type of learning problem called constrained learning.<n>In addition to positive and negative examples, the user can specify one or more constraints over the properties of the formula.<n>An experimental evaluation demonstrates that ATLAS is able to solve new types of learning problems while performing better than or competitively with the state-of-the-art tools in learning.
  arXiv  Detail & Related papers  (2024-12-03T23:15:27Z)
• DCP: Learning Accelerator Dataflow for Neural Network via Propagation [52.06154296196845]
  This work proposes an efficient data-centric approach, named Dataflow Code Propagation (DCP), to automatically find the optimal dataflow for DNN layers in seconds without human effort. DCP learns a neural predictor to efficiently update the dataflow codes towards the desired gradient directions to minimize various optimization objectives. For example, without using additional training data, DCP surpasses the GAMMA method that performs a full search using thousands of samples.
  arXiv  Detail & Related papers  (2024-10-09T05:16:44Z)
• 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)
• Deformable Mixer Transformer with Gating for Multi-Task Learning of Dense Prediction [126.34551436845133]
  CNNs and Transformers have their own advantages and both have been widely used for dense prediction in multi-task learning (MTL) We present a novel MTL model by combining both merits of deformable CNN and query-based Transformer with shared gating for multi-task learning of dense prediction.
  arXiv  Detail & Related papers  (2023-08-10T17:37:49Z)
• Teal: Learning-Accelerated Optimization of WAN Traffic Engineering [68.7863363109948]
  We present Teal, a learning-based TE algorithm that leverages the parallel processing power of GPUs to accelerate TE control. To reduce the problem scale and make learning tractable, Teal employs a multi-agent reinforcement learning (RL) algorithm to independently allocate each traffic demand. Compared with other TE acceleration schemes, Teal satisfies 6--32% more traffic demand and yields 197--625x speedups.
  arXiv  Detail & Related papers  (2022-10-25T04:46:30Z)
• Interactive Learning from Natural Language and Demonstrations using Signal Temporal Logic [5.88797764615148]
  Natural language (NL) is ambiguous, real world tasks and their safety requirements need to be communicated unambiguously. Signal Temporal Logic (STL) is a formal logic that can serve as a versatile, expressive, and unambiguous formal language to describe robotic tasks. We propose DIALOGUESTL, an interactive approach for learning correct and concise STL formulas from (often) ambiguous NL descriptions.
  arXiv  Detail & Related papers  (2022-07-01T19:08:43Z)
• NumS: Scalable Array Programming for the Cloud [82.827921577004]
  We present NumS, an array programming library which optimize NumPy-like expressions on task-based distributed systems. This is achieved through a novel scheduler called Load Simulated Hierarchical Scheduling (LSHS) We show that LSHS enhances performance on Ray by decreasing network load by a factor of 2x, requiring 4x less memory, and reducing execution time by 10x on the logistic regression problem.
  arXiv  Detail & Related papers  (2022-06-28T20:13:40Z)
• Combining Label Propagation and Simple Models Out-performs Graph Neural Networks [52.121819834353865]
  We show that for many standard transductive node classification benchmarks, we can exceed or match the performance of state-of-the-art GNNs. We call this overall procedure Correct and Smooth (C&S) Our approach exceeds or nearly matches the performance of state-of-the-art GNNs on a wide variety of benchmarks.
  arXiv  Detail & Related papers  (2020-10-27T02:10:52Z)
• Backpropagation through Signal Temporal Logic Specifications: Infusing Logical Structure into Gradient-Based Methods [28.72161643908351]
  This paper presents a technique, named STLCG, to compute the quantitative semantics of Signal Temporal Logic (STL) formulas using computation graphs. STL is a powerful and expressive formal language that can specify spatial and temporal properties of signals generated by both continuous and hybrid systems.
  arXiv  Detail & Related papers  (2020-07-31T22:01:39Z)

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.