Myopically Verifiable Probabilistic Certificates for Safe Control and Learning
Not on the map. Why?
Abstract (arXiv)
This paper addresses the design of safety certificates for stochastic systems, with a focus on ensuring long-term safety through fast real-time control. In stochastic environments, set invariance-based methods that restrict the probability of risk events in infinitesimal time intervals may exhibit significant long-term risks due to cumulative uncertainties/risks. On the other hand, reachability-based approaches that account for the long-term future may require prohibitive computation in real-time decision making. To overcome this challenge involving stringent long-term safety vs. computation tradeoffs, we first introduce a novel technique termed 'probabilistic invariance'. This technique characterizes the invariance conditions of the probability of interest. When the target probability is defined using long-term trajectories, this technique can be used to design myopic conditions/controllers with assured long-term safe probability. Then, we integrate this technique into safe control and learning. The proposed control methods efficiently assure long-term safety using neural networks or model predictive controllers with short outlook horizons. The proposed learning methods can be used to guarantee long-term safety during and after training. Finally, we demonstrate the performance of the proposed techniques in numerical simulations.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 41 of its 83 references that are in the map. First posted on arXiv 23 Apr 2024.
Builds on
41 of 83 references.
References · 41
- 2017Safe Reinforcement Learning via Shieldingcited by 427
- 2019Control Barrier Functions: Theory and Applicationscited by 332
- 2018A Lyapunov-based Approach to Safe Reinforcement Learningcited by 278
- 2017Hamilton-Jacobi Reachability: A Brief Overview and Recent Advancescited by 186
- 2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 169
- 2020CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guaranteecited by 128
- 2020Safe Reinforcement Learning in Constrained Markov Decision Processescited by 109
- 2020Learning to be Safe: Deep RL with a Safety Criticcited by 109
- 2021Robust Control Barrier-Value Functions for Safety-Critical Controlcited by 47
- 2019Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamicscited by 45
- 2021Safe Reinforcement Learning Using Robust Control Barrier Functionscited by 44
- 2021A Primal-Dual Approach to Constrained Markov Decision Processescited by 42
29 more
- 2020Enforcing robust control guarantees within neural network policiescited by 40
- 2021Safe Reinforcement Learning with Linear Function Approximationcited by 33
- 2020Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEscited by 22
- 2021Safe Control with Neural Network Dynamic Modelscited by 21
- 2022Learning Control Policies for Stochastic Systems with Reach-avoid Guaranteescited by 21
- 2021Decentralized Control of Quadrotor Swarms with End-to-end Deep Reinforcement Learningcited by 18
- 2020Learning Safe Neural Network Controllers with Barrier Certificatescited by 16
- 2019A Risk-Sensitive Finite-Time Reachability Approach for Safety of Stochastic Dynamic Systemscited by 14
- 2019A Barrier Function Approach to Finite-Time Stochastic System Verification and Controlcited by 14
- 2020Control Barrier Functions for Stochastic Systemscited by 14
- 2022Safety Guarantees for Neural Network Dynamic Systems via Stochastic Barrier Functionscited by 14
- 2019Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificatescited by 12
- 2020Stochastic Model Predictive Control with a Safety Guarantee for Automated Driving: Extended Versioncited by 12
- 2023Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learningcited by 12
- 2014Path Integral Control and State Dependent Feedbackcited by 11
- 2021Probabilistic Safety-Assured Adaptive Merging Control for Autonomous Vehiclescited by 10
- 2018Safety-Aware Optimal Control of Stochastic Systems Using Conditional Value-at-Riskcited by 8
- 2020Risk-Sensitive Motion Planning using Entropic Value-at-Riskcited by 7
- 2021Safe Control in the Presence of Stochastic Uncertaintiescited by 5
- 2022Safe Control for Nonlinear Systems with Stochastic Uncertainty via Risk Control Barrier Functionscited by 5
- 2023ROSARL: Reward-Only Safe Reinforcement Learningcited by 5
- 2021An optimal control approach to particle filteringcited by 4
- 2022Control Barrier Functions for Stochastic Systems and Safety-critical Control Designscited by 4
- 2023A Generalizable Physics-informed Learning Framework for Risk Probability Estimationcited by 4
- 2020Risk-Averse Planning via CVaR Barrier Functions: Application to Bipedal Robot Locomotioncited by 2
- 2021Safety-Critical Control of Stochastic Systems using Stochastic Control Barrier Functionscited by 2
- 2023Physics-Informed Representation and Learning: Control and Risk Quantificationcited by 2
- 2021Verification of Switched Stochastic Systems via Barrier Certificatescited by 1
- 2023Constrained Empirical Risk Minimization: Theory and Practicecited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.