mlsanityData to 7 Oct 2026

Recurrent Neural Network Controllers for Signal Temporal Logic Specifications Subject to Safety Constraints

arXiv 2009.11468 ↗First posted 24 Sep 2020eess.SY cs.LG cs.SYcited by 18

Not on the map. Why?

Abstract (arXiv)

We propose a framework based on Recurrent Neural Networks (RNNs) to determine an optimal control strategy for a discrete-time system that is required to satisfy specifications given as Signal Temporal Logic (STL) formulae. RNNs can store information of a system over time, thus, enable us to determine satisfaction of the dynamic temporal requirements specified in STL formulae. Given a STL formula, a dataset of satisfying system executions and corresponding control policies, we can use RNNs to predict a control policy at each time based on the current and previous states of system. We use Control Barrier Functions (CBFs) to guarantee the safety of the predicted control policy. We validate our theoretical formulation and demonstrate its performance in an optimal control problem subject to partially unknown safety constraints through simulations.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 6; 2023: 2; 2024: 4; 2025: 4.

18 papers.

Sort:

By area:

  1. 2022Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizabilitycited by 32
  2. 2023Signal Temporal Logic Neural Predictive Controlcited by 12
  3. 2025TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matchingcited by 9
  4. 2022Follow The Rules: Online Signal Temporal Logic Tree Search for Guided Imitation Learning in Stochastic Domainscited by 7
  5. 2022Model-Free Reinforcement Learning for Symbolic Automata-encoded Objectivescited by 6
  6. 2023Learning Robust and Correct Controllers from Signal Temporal Logic Specifications Using BarrierNetcited by 6
  7. 2025STLCG++: A Masking Approach for Differentiable Signal Temporal Logic Specificationcited by 6
  8. 2025TGPO: Temporal Grounded Policy Optimization for Signal Temporal Logic Taskscited by 5
  9. 2021Safe Model-based Control from Signal Temporal Logic Specifications Using Recurrent Neural Networkscited by 3
  10. 2024Traffic-Rule-Compliant Trajectory Repair via Satisfiability Modulo Theories and Reachability Analysiscited by 3
  11. 2021Neural Network-based Control for Multi-Agent Systems from Spatio-Temporal Specificationscited by 2
  12. 2024Interpretable Imitation Learning via Generative Adversarial STL Inference and Controlcited by 2
6 more
  1. 2022Risk-Awareness in Learning Neural Controllers for Temporal Logic Objectivescited by 1
  2. 2022Neural Controller Synthesis for Signal Temporal Logic Specifications Using Encoder-Decoder Structured Networkscited by 1
  3. 2024Multi-agent transformer-accelerated RL for satisfaction of STL specificationscited by 1
  4. 2022CatlNet: Learning Communication and Coordination Policies from CaTL+ Specificationscited by 0
  5. 2024Scaling Learning based Policy Optimization for Temporal Logic Tasks by Controller Network Dropoutcited by 0
  6. 2025Feasibility-aware Learning of Robust Temporal Logic Controllers using BarrierNetcited by 0