English
Related papers

Related papers: A Learnable Safety Measure

200 papers

We introduce a simple but effective method for managing risk in model-based reinforcement learning with trajectory sampling that involves probabilistic safety constraints and balancing of optimism in the face of epistemic uncertainty and…

Machine Learning · Computer Science 2023-09-12 Marin Vlastelica , Sebastian Blaes , Cristina Pineri , Georg Martius

In learning-enabled autonomous systems, safety monitoring of learned components is crucial to ensure their outputs do not lead to system safety violations, given the operational context of the system. However, developing a safety monitor…

Machine Learning · Computer Science 2024-12-23 Sepehr Sharifi , Andrea Stocco , Lionel C. Briand

We present a method for learning to satisfy uncertain constraints from demonstrations. Our method uses robust optimization to obtain a belief over the potentially infinite set of possible constraints consistent with the demonstrations, and…

Robotics · Computer Science 2020-11-10 Glen Chou , Necmiye Ozay , Dmitry Berenson

In this paper, we study the problem of ensuring safety with a few shots of samples for partially unknown systems. We first characterize a fundamental limit when producing safe actions is not possible due to insufficient information or…

Systems and Control · Electrical Eng. & Systems 2024-03-14 Ritabrata Ray , Yorie Nakahira , Soummya Kar

Often it is desirable to stabilize a system around an optimal state. This can be effectively accomplished using feedback control, where the system deviation from the desired state is measured in order to determine the magnitude of the…

Soft Condensed Matter · Physics 2016-09-07 Aykut Argun , Giovanni Volpe

Before autonomous systems can be deployed in safety-critical applications, we must be able to understand and verify the safety of these systems. For cases where the risk or cost of real-world testing is prohibitive, we propose a…

Robotics · Computer Science 2023-09-18 Charles Dawson , Chuchu Fan

To provide safety guarantees for learning-based control systems, recent work has developed formal verification methods to apply after training ends. However, if the trained policy does not meet the specifications, or there is conservatism…

Systems and Control · Electrical Eng. & Systems 2025-04-24 Puja Chaudhury , Alexander Estornell , Michael Everett

Model-based safety analysis approaches aim at finding critical failure combinations by analysis of models of the whole system (i.e. software, hardware, failure modes and environment). The advantage of these methods compared to traditional…

Logic in Computer Science · Computer Science 2010-06-29 Matthias Güdemann , Frank Ortmeier

Reinforcement learning algorithms typically necessitate extensive exploration of the state space to find optimal policies. However, in safety-critical applications, the risks associated with such exploration can lead to catastrophic…

Machine Learning · Computer Science 2025-02-28 Kaustubh Mani , Vincent Mai , Charlie Gauthier , Annie Chen , Samer Nashed , Liam Paull

Ensuring safety is of paramount importance in physical human-robot interaction applications. This requires both adherence to safety constraints defined on the system state, as well as guaranteeing compliant behavior of the robot. If the…

Systems and Control · Electrical Eng. & Systems 2023-04-17 Armin Lederer , Azra Begzadić , Neha Das , Sandra Hirche

Understanding physical phenomena is a key competence that enables humans and animals to act and interact under uncertain perception in previously unseen environments containing novel object and their configurations. Developmental psychology…

Computer Vision and Pattern Recognition · Computer Science 2016-04-04 Wenbin Li , Seyedmajid Azimi , Aleš Leonardis , Mario Fritz

Robots are more capable of achieving manipulation tasks for everyday activities than before. But the safety of manipulation skills that robots employ is still an open problem. Considering all possible failures during skill learning…

Robotics · Computer Science 2023-05-05 Abdullah Cihan Ak , Eren Erdal Aksoy , Sanem Sariel

Self-assessment rules play an essential role in safe and effective real-world robotic applications, which verify the feasibility of the selected action before actual execution. But how to utilize the self-assessment results to re-choose…

Robotics · Computer Science 2023-02-28 Kechun Xu , Runjian Chen , Shuqi Zhao , Zizhang Li , Hongxiang Yu , Ci Chen , Yue Wang , Rong Xiong

We propose a method to optimise the parameters of a policy which will be used to safely perform a given task in a data-efficient manner. We train a Gaussian process model to capture the system dynamics, based on the PILCO framework. Our…

Machine Learning · Statistics 2019-12-03 Kyriakos Polymenakos , Alessandro Abate , Stephen Roberts

Learning-enabled control systems have demonstrated impressive empirical performance on challenging control problems in robotics, but this performance comes at the cost of reduced transparency and lack of guarantees on the safety or…

Robotics · Computer Science 2022-12-21 Charles Dawson , Sicun Gao , Chuchu Fan

This paper proposes a safe data-driven control framework for nonlinear systems with partially known dynamics. The method ensures stability and constraint satisfaction during online learning, assuming only a stabilizable linear approximation…

Systems and Control · Electrical Eng. & Systems 2026-05-12 Stefano Tonini , Soroush Rastegarpour , Hamid Reza Feyzmahdavian , Nicola Bastianello , Karl Henrik Johansson

Dependability assurance of systems embedding machine learning(ML) components---so called learning-enabled systems (LESs)---is a key step for their use in safety-critical applications. In emerging standardization and guidance efforts, there…

Software Engineering · Computer Science 2023-01-11 Erfan Asaadi , Ewen Denney , Ganesh Pai

Safe learning of control policies remains challenging, both in optimal control and reinforcement learning. In this article, we consider safe learning of parametrized predictive controllers that operate with incomplete information about the…

Systems and Control · Electrical Eng. & Systems 2024-09-17 Sebastian Hirt , Maik Pfefferkorn , Rolf Findeisen

We consider the problem of reinforcement learning under safety requirements, in which an agent is trained to complete a given task, typically formalized as the maximization of a reward signal over time, while concurrently avoiding…

Machine Learning · Computer Science 2018-09-25 Tu-Hoa Pham , Giovanni De Magistris , Don Joven Agravante , Subhajit Chaudhury , Asim Munawar , Ryuki Tachibana

Reinforcement learning agents naturally learn from extensive exploration. Exploration is costly and can be unsafe in $\textit{safety-critical}$ domains. This paper proposes a novel framework for incorporating domain knowledge to help guide…

Machine Learning · Computer Science 2023-04-25 Fazl Barez , Hosien Hasanbieg , Alesandro Abbate