Neural Controller Synthesis for Signal Temporal Logic Specifications Using Encoder-Decoder Structured Networks
Not on the map. Why?
Abstract (arXiv)
In this paper, we propose a control synthesis method for signal temporal logic (STL) specifications with neural networks (NNs). Most of the previous works consider training a controller for only a given STL specification. These approaches, however, require retraining the NN controller if a new specification arises and needs to be satisfied, which results in large consumption of memory and inefficient training. To tackle this problem, we propose to construct NN controllers by introducing encoder-decoder structured NNs with an attention mechanism. The encoder takes an STL formula as input and encodes it into an appropriate vector, and the decoder outputs control signals that will meet the given specification. As the encoder, we consider three NN structures: sequential, tree-structured, and graph-structured NNs. All the model parameters are trained in an end-to-end manner to maximize the expected robustness that is known to be a quantitative semantics of STL formulae. We compare the control performances attained by the above NN structures through a numerical experiment of the path planning problem, showing the efficacy of the proposed approach.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 34 of its 54 references that are in the map. First posted on arXiv 10 Dec 2022.
Builds on
34 of 54 references.
References · 34
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
- 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
- 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
- 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
- 2015Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networkscited by 305
- 2016DeepMath - Deep Sequence Models for Premise Selectioncited by 80
- 2021LTL2Action: Generalizing LTL Instructions for Multi-Task RLcited by 72
- 2015Reasoning about Entailment with Neural Attentioncited by 68
- 2016Q-Learning for Robust Satisfaction of Signal Temporal Logic Specificationscited by 65
22 more
- 2018Graph-to-Sequence Learning using Gated Graph Neural Networkscited by 61
- 2018A Graph-to-Sequence Model for AMR-to-Text Generationcited by 56
- 2014word2vec Parameter Learning Explainedcited by 53
- 2020Backpropagation through Signal Temporal Logic Specifications: Infusing Logical Structure into Gradient-Based Methodscited by 51
- 2019Embedding Symbolic Knowledge into Deep Networkscited by 49
- 2017Premise Selection for Theorem Proving by Deep Graph Embeddingcited by 44
- 2018Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networkscited by 36
- 2020Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulascited by 36
- 2016Learning Continuous Semantic Representations of Symbolic Expressionscited by 25
- 2015Robust Temporal Logic Model Predictive Controlcited by 21
- 2020Tractable Reinforcement Learning of Signal Temporal Logic Objectivescited by 21
- 2020Systematic Generalisation through Task Temporal Logic and Deep Reinforcement Learningcited by 21
- 2019Improving Graph Neural Network Representations of Logical Formulae with Subgraph Poolingcited by 20
- 2017A Policy Search Method For Temporal Logic Specified Reinforcement Learning Taskscited by 19
- 2019Arithmetic-Geometric Mean Robustness for Control from Signal Temporal Logic Specificationscited by 19
- 2020Recurrent Neural Network Controllers for Signal Temporal Logic Specifications Subject to Safety Constraintscited by 18
- 2019Control from Signal Temporal Logic Specifications with Smooth Cumulative Quantitative Semanticscited by 16
- 2020Elaborating on Learned Demonstrations with Temporal Logic Specificationscited by 14
- 2021Embedding Symbolic Temporal Knowledge into Deep Sequential Modelscited by 11
- 2022Semi-Supervised Trajectory-Feedback Controller Synthesis for Signal Temporal Logic Specificationscited by 11
- 2022Deep reinforcement learning under signal temporal logic constraints using Lagrangian relaxationcited by 8
- 2021STL2vec: Signal Temporal Logic Embeddings for Control Synthesis With Recurrent Neural Networkscited by 7
Built on by
Citing papers per year: 2025: 1.
1 paper.