English
Related papers

Related papers: Verified Safe Reinforcement Learning for Neural Ne…

200 papers

In the current control design of safety-critical autonomous systems, formal verification techniques are typically applied after the controller is designed to evaluate whether the required properties (e.g., safety) are satisfied. However,…

Systems and Control · Electrical Eng. & Systems 2021-06-08 Yixuan Wang , Chao Huang , Zhaoran Wang , Zhilu Wang , Qi Zhu

Reinforcement learning often uses neural networks to solve complex control tasks. However, neural networks are sensitive to input perturbations, which makes their deployment in safety-critical environments challenging. This work lifts…

Machine Learning · Computer Science 2024-08-20 Manuel Wendl , Lukas Koller , Tobias Ladner , Matthias Althoff

Learning-based methods provide a promising approach to solving highly non-linear control tasks that are often challenging for classical control methods. To ensure the satisfaction of a safety property, learning-based methods jointly learn a…

Machine Learning · Computer Science 2024-12-18 Emily Yu , Đorđe Žikelić , Thomas A. Henzinger

In model-based reinforcement learning for safety-critical control systems, it is important to formally certify system properties (e.g., safety, stability) under the learned controller. However, as existing methods typically apply formal…

Machine Learning · Computer Science 2023-03-22 Yixuan Wang , Simon Zhan , Zhilu Wang , Chao Huang , Zhaoran Wang , Zhuoran Yang , Qi Zhu

Guaranteeing safe behaviour of reinforcement learning (RL) policies poses significant challenges for safety-critical applications, despite RL's generality and scalability. To address this, we propose a new approach to apply verification…

Machine Learning · Computer Science 2023-12-06 Daniel C. H. Tan , Fernando Acero , Robert McCarthy , Dimitrios Kanoulas , Zhibin Li

Groundbreaking successes have been achieved by Deep Reinforcement Learning (DRL) in solving practical decision-making problems. Robotics, in particular, can involve high-cost hardware and human interactions. Hence, scrupulous evaluations of…

Artificial Intelligence · Computer Science 2020-10-20 Davide Corsi , Enrico Marchesini , Alessandro Farinelli

Neural certificates have emerged as a powerful tool in cyber-physical systems control, providing witnesses of correctness. These certificates, such as barrier functions, often learned alongside control policies, once verified, serve as…

Symbolic Computation · Computer Science 2025-07-17 Thomas A. Henzinger , Konstantin Kueffner , Emily Yu

Merely pursuing performance may adversely affect the safety, while a conservative policy for safe exploration will degrade the performance. How to balance the safety and performance in learning-based control problems is an interesting yet…

Systems and Control · Electrical Eng. & Systems 2025-01-28 Xinyang Wang , Hongwei Zhang , Shimin Wang , Wei Xiao , Martin Guay

Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness. Small perturbations to sensor inputs…

Machine Learning · Computer Science 2022-02-03 Michael Everett , Bjorn Lutjens , Jonathan P. How

When autonomous vehicles encounter untrained scenarios, ensuring safety hinges on effective safety verification to prevent accidents stemming from unexpected model decisions. Reachability analysis, a method of safety verification, offers…

Systems and Control · Electrical Eng. & Systems 2025-12-05 Lingxiang Fan , Linxuan He , Haoyuan Ji , Shuo Feng

Neural networks are increasingly applied to support decision making in safety-critical applications (like autonomous cars, unmanned aerial vehicles and face recognition based authentication). While many impressive static verification…

Machine Learning · Computer Science 2021-05-07 Guoliang Dong , Jun Sun , Jingyi Wang , Xinyu Wang , Ting Dai

We present a novel technique for online safety verification of autonomous systems, which performs reachability analysis efficiently for both bounded and unbounded horizons by employing neural barrier certificates. Our approach uses barrier…

Systems and Control · Electrical Eng. & Systems 2024-04-30 Alessandro Abate , Sergiy Bogomolov , Alec Edwards , Kostiantyn Potomkin , Sadegh Soudjani , Paolo Zuliani

Control barrier certificates have proven effective in formally guaranteeing the safety of the control systems. However, designing a control barrier certificate is a time-consuming and computationally expensive endeavor that requires expert…

Systems and Control · Electrical Eng. & Systems 2024-05-28 Alireza Nadali , Ashutosh Trivedi , Majid Zamani

In this work, we consider the problem of learning a feed-forward neural network controller to safely steer an arbitrarily shaped planar robot in a compact and obstacle-occluded workspace. Unlike existing methods that depend strongly on the…

Systems and Control · Electrical Eng. & Systems 2022-12-14 Panagiotis Vlantis , Leila J. Bridgeman , Michael M. Zavlanos

We address the problem of safely learning controlled stochastic dynamics from discrete-time trajectory observations, ensuring system trajectories remain within predefined safe regions during both training and deployment. Safety-critical…

Machine Learning · Statistics 2026-02-03 Luc Brogat-Motte , Alessandro Rudi , Riccardo Bonalli

Deploying deep reinforcement learning in safety-critical settings requires developing algorithms that obey hard constraints during exploration. This paper contributes a first approach toward enforcing formal safety constraints on end-to-end…

Artificial Intelligence · Computer Science 2020-07-03 Nathan Hunt , Nathan Fulton , Sara Magliacane , Nghia Hoang , Subhro Das , Armando Solar-Lezama

When designing controllers for safety-critical systems, practitioners often face a challenging tradeoff between robustness and performance. While robust control methods provide rigorous guarantees on system stability under certain…

Machine Learning · Computer Science 2021-04-27 Priya L. Donti , Melrose Roderick , Mahyar Fazlyab , J. Zico Kolter

We study the problem of safe learning and exploration in sequential control problems. The goal is to safely collect data samples from operating in an environment, in order to learn to achieve a challenging control goal (e.g., an agile…

Machine Learning · Computer Science 2020-06-30 Anqi Liu , Guanya Shi , Soon-Jo Chung , Anima Anandkumar , Yisong Yue

Studies that broaden drone applications into complex tasks require a stable control framework. Recently, deep reinforcement learning (RL) algorithms have been exploited in many studies for robot control to accomplish complex tasks.…

Reinforcement learning is a powerful paradigm for learning optimal policies from experimental data. However, to find optimal policies, most reinforcement learning algorithms explore all possible actions, which may be harmful for real-world…

Machine Learning · Statistics 2017-11-15 Felix Berkenkamp , Matteo Turchetta , Angela P. Schoellig , Andreas Krause