Co-learning Planning and Control Policies Constrained by Differentiable Logic Specifications
Not on the map. Why?
Abstract (arXiv)
Synthesizing planning and control policies in robotics is a fundamental task, further complicated by factors such as complex logic specifications and high-dimensional robot dynamics. This paper presents a novel reinforcement learning approach to solving high-dimensional robot navigation tasks with complex logic specifications by co-learning planning and control policies. Notably, this approach significantly reduces the sample complexity in training, allowing us to train high-quality policies with much fewer samples compared to existing reinforcement learning algorithms. In addition, our methodology streamlines complex specification extraction from map images and enables the efficient generation of long-horizon robot motion paths across different map layouts. Moreover, our approach also demonstrates capabilities for high-dimensional control and avoiding suboptimal policies via policy alignment. The efficacy of our approach is demonstrated through experiments involving simulated high-dimensional quadruped robot dynamics and a real-world differential drive robot (TurtleBot3) under different types of task specifications.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 22 of its 37 references that are in the map. First posted on arXiv 2 Mar 2023.
Builds on
22 of 37 references.
References · 22
- 2017Attention Is All You Needcited by 60,361
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2015Trust Region Policy Optimizationcited by 2,580
- 2017Constrained Policy Optimizationcited by 983
- 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 642
- 2020Responsive Safety in Reinforcement Learning by PID Lagrangian Methodscited by 316
- 2019Challenges of Real-World Reinforcement Learningcited by 291
- 2020Reward Machines: Exploiting Reward Function Structure in Reinforcement Learningcited by 191
- 2016Reinforcement Learning With Temporal Logic Rewardscited by 117
- 2018Motion Planning Networkscited by 80
- 2019Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guaranteescited by 77
- 2019Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learningcited by 75
10 more
- 2020A Composable Specification Language for Reinforcement Learning Taskscited by 69
- 2018Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselinescited by 68
- 2019Joint Inference of Reward Machines and Policies for Reinforcement Learningcited by 56
- 2014Probably Approximately Correct MDP Learning and Control With Temporal Logic Constraintscited by 54
- 2020Backpropagation through Signal Temporal Logic Specifications: Infusing Logical Structure into Gradient-Based Methodscited by 54
- 2020A Smooth Robustness Measure of Signal Temporal Logic for Symbolic Controlcited by 21
- 2021On the (In)Tractability of Reinforcement Learning for LTL Objectivescited by 18
- 2022Mixed-Integer Programming for Signal Temporal Logic with Fewer Binary Variablescited by 16
- 2022LCRL: Certified Policy Synthesis via Logically-Constrained Reinforcement Learningcited by 11
- 2022Robust Counterexample-guided Optimization for Planning from Differentiable Temporal Logiccited by 9
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.