English
Related papers

Related papers: Safety Shielding under Delayed Observation

200 papers

In many real-world applications, safety constraints for reinforcement learning (RL) algorithms are either unknown or not explicitly defined. We propose a framework that concurrently learns safety constraints and optimal RL policies in such…

Systems and Control · Electrical Eng. & Systems 2023-05-02 Lunet Yifru , Ali Baheri

Most recent software related accidents have been system accidents. To validate the absence of system hazards concerning dysfunctional interactions, industrials call for approaches of modeling system safety requirements and interaction…

Software Engineering · Computer Science 2016-11-17 Zhe Chen , Gilles Motet

In reinforcement learning, agents learn by performing actions and observing their outcomes. Sometimes, it is desirable for a human operator to \textit{interrupt} an agent in order to prevent dangerous situations from happening. Yet, as part…

Artificial Intelligence · Computer Science 2017-05-23 El Mahdi El Mhamdi , Rachid Guerraoui , Hadrien Hendrikx , Alexandre Maurer

We present SHIELD, a novel methodology for automated and integrated safety signal detection in clinical trials. SHIELD combines disproportionality analysis with semantic clustering of adverse event (AE) terms applied to MedDRA term…

Computation and Language · Computer Science 2026-02-24 Francois Vandenhende , Anna Georgiou , Theodoros Psaras , Ellie Karekla

This paper targets the efficient construction of a safety shield for decision making in scenarios that incorporate uncertainty. Markov decision processes (MDPs) are prominent models to capture such planning problems. Reinforcement learning…

Artificial Intelligence · Computer Science 2019-11-26 Nils Jansen , Bettina Könighofer , Sebastian Junges , Alexandru C. Serban , Roderick Bloem

The Intelligent Driver Model is studied and several drawbacks with respect to driving simulators are defined. We present two modifications of the IDM. The first one gives any predefined distance to the leading vehicle in a steady state. The…

Physics and Society · Physics 2016-10-18 Valentina Kurtc , Igor Anufriev

One of the key challenges to deep reinforcement learning (deep RL) is to ensure safety at both training and testing phases. In this work, we propose a novel technique of unsupervised action planning to improve the safety of on-policy…

Robotics · Computer Science 2021-09-30 Hao-Lun Hsu , Qiuhua Huang , Sehoon Ha

Safe reinforcement learning is a promising path toward applying reinforcement learning algorithms to real-world problems, where suboptimal behaviors may lead to actual negative consequences. In this work, we focus on the setting where…

Machine Learning · Computer Science 2022-02-17 Garrett Thomas , Yuping Luo , Tengyu Ma

Switching controllers play a pivotal role in directing hybrid systems (HSs) towards the desired objective, embodying a ``correct-by-construction'' approach to HS design. Identifying these objectives is thus crucial for the synthesis of…

Systems and Control · Electrical Eng. & Systems 2024-06-25 Han Su , Shenghua Feng , Sinong Zhan , Naijun Zhan

When securing complex infrastructures or large environments, constant surveillance of every area is not affordable. To cope with this issue, a common countermeasure is the usage of cheap but wide-ranged sensors, able to detect suspicious…

Artificial Intelligence · Computer Science 2015-06-10 Nicola Basilico , Giuseppe De Nittis , Nicola Gatti

Communication technologies enable coordination among connected and autonomous vehicles (CAVs). However, it remains unclear how to utilize shared information to improve the safety and efficiency of the CAV system in dynamic and complicated…

Robotics · Computer Science 2023-03-15 Zhili Zhang , Songyang Han , Jiangwei Wang , Fei Miao

In this paper, a novel approach to spacing policies for vehicle platoons and a framework for control design is presented. Whereas traditional approaches aim to mitigate the effect of actuation and communication delays on the spacing error,…

Optimization and Control · Mathematics 2025-08-21 Paul Wijnbergen , Redmer de Haan , Erjen Lefeber

The rapid development of artificial intelligence, especially deep learning technology, has advanced autonomous driving systems (ADSs) by providing precise control decisions to counterpart almost any driving event, spanning from anti-fatigue…

Machine Learning · Computer Science 2021-04-13 Yao Deng , Tiehua Zhang , Guannan Lou , Xi Zheng , Jiong Jin , Qing-Long Han

Safe Reinforcement learning (Safe RL) aims at learning optimal policies while staying safe. A popular solution to Safe RL is shielding, which uses a logical safety specification to prevent an RL agent from taking unsafe actions. However,…

Artificial Intelligence · Computer Science 2023-03-07 Wen-Chi Yang , Giuseppe Marra , Gavin Rens , Luc De Raedt

We present Tempest, a synthesis tool to automatically create correct-by-construction reactive systems and shields from qualitative or quantitative specifications in probabilistic environments. A shield is a special type of reactive system…

Logic in Computer Science · Computer Science 2021-05-27 Stefan Pranger , Bettina Könighofer , Lukas Posch , Roderick Bloem

Safe reinforcement learning has traditionally relied on predefined constraint functions to ensure safety in complex real-world tasks, such as autonomous driving. However, defining these functions accurately for varied tasks is a persistent…

Machine Learning · Computer Science 2025-01-31 Se-Wook Yoo , Seung-Woo Seo

Time delays in feedback control loops can cause controllers to respond too late, and with excessively large corrective actions, leading to unsafe behavior (violation of state constraints) and controller infeasibility (violation of input…

Systems and Control · Electrical Eng. & Systems 2026-03-26 Adam K. Kiss , Ersin Das , Tamas G. Molnar , Aaron D. Ames

Delays in biological systems may be used to model events for which the underlying dynamics cannot be precisely observed. Mathematical modeling of biological systems with delays is usually based on Delay Differential Equations (DDEs), a kind…

Quantitative Methods · Quantitative Biology 2009-10-08 Roberto Barbuti , Giulio Caravagna , Paolo Milazzo , Andrea Maggiolo-Schettini

Delays frequently occur in real-world environments, yet standard reinforcement learning (RL) algorithms often assume instantaneous perception of the environment. We study random sensor delays in POMDPs, where observations may arrive…

Machine Learning · Computer Science 2026-04-17 Armin Karamzade , Kyungmin Kim , JB Lanier , Davide Corsi , Roy Fox

Machine Learning applications are acknowledged at the foundation of autonomous driving, because they are the enabling technology for most driving tasks. However, the inclusion of trained agents in automotive systems exposes the vehicle to…

Artificial Intelligence · Computer Science 2022-03-01 Niccolò Piazzesi , Massimo Hong , Andrea Ceccarelli