Safe reinforcement learning for power system control: A review

P Yu, Z Wang, H Zhang, Y Song - arxiv preprint arxiv:2407.00681, 2024 - arxiv.org
The large-scale integration of intermittent renewable energy resources introduces increased
uncertainty and volatility to the supply side of power systems, thereby complicating system …

Intelligent computational techniques for physical object properties discovery, detection, and prediction: A comprehensive survey

S Mishra, A Arora - Computer Science Review, 2024 - Elsevier
The exploding usage of physical object properties has greatly facilitated real-time
applications such as robotics to perceive exactly as it appears in existence. Changes in the …

Provably safe reinforcement learning via action projection using reachability analysis and polynomial zonotopes

N Kochdumper, H Krasowski, X Wang… - IEEE Open Journal …, 2023 - ieeexplore.ieee.org
While reinforcement learning produces very promising results for many applications, its main
disadvantage is the lack of safety guarantees, which prevents its use in safety-critical …

Safe Reinforcement Learning for Automated Vehicles via Online Reachability Analysis

X Wang, M Althoff - IEEE Transactions on Intelligent Vehicles, 2023 - ieeexplore.ieee.org
Ensuring safe and capable motion planning is paramount for automated vehicles.
Traditional methods are limited in their ability to handle complex and unpredictable traffic …

A human-centered safe robot reinforcement learning framework with interactive behaviors

S Gu, A Kshirsagar, Y Du, G Chen, J Peters… - Frontiers in …, 2023 - frontiersin.org
Deployment of Reinforcement Learning (RL) algorithms for robotics applications in the real
world requires ensuring the safety of the robot and its environment. Safe Robot RL (SRRL) is …

Safe reinforcement learning for urban driving using invariably safe braking sets

H Krasowski, Y Zhang, M Althoff - 2022 IEEE 25th International …, 2022 - ieeexplore.ieee.org
Deep reinforcement learning (RL) has been widely applied to motion planning problems of
autonomous vehicles in urban traffic. However, traditional deep RL algorithms cannot …

Pure-past action masking

G Varricchione, N Alechina, M Dastani… - Proceedings of the …, 2024 - ojs.aaai.org
We present Pure-Past Action Masking (PPAM), a lightweight approach to action masking for
safe reinforcement learning. In PPAM, actions are disallowed (“masked”) according to …

Safe Reinforcement Learning for Energy Management of Electrified Vehicle with Novel Physics-Informed Exploration Strategy

A Biswas, M Acquarone, H Wang… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
This paper introduces a novel physics-informed exploration strategy for a deep
reinforcement learning (DRL)-based energy management system (EMS), specifically …

Curse of rarity for autonomous vehicles

HX Liu, S Feng - nature communications, 2024 - nature.com
The curse of rarity—the rarity of safety-critical events in high-dimensional variable spaces—
presents significant challenges in ensuring the safety of autonomous vehicles using deep …

Provable Traffic Rule Compliance in Safe Reinforcement Learning on the Open Sea

H Krasowski, M Althoff - IEEE Transactions on Intelligent …, 2024 - ieeexplore.ieee.org
For safe operation, autonomous vehicles have to obey traffic rules that are set forth in legal
documents formulated in natural language. Temporal logic is a suitable concept to formalize …