Results 61 to 70 of about 277,892 (265)

Enhancing Safe Exploration Through Subgoal Guidance

Technologies
Reinforcement learning is a widely used approach for autonomous navigation, but it often struggles to reach distant, long-horizon goals under safety constraints. The primary reason for this suboptimal performance is that safety requirements significantly
Gregory Gorbov, Aleksandr Panov
doaj   +1 more source

Safe Reinforcement Learning Using Learned Safe Sets

, 2022
Reinforcement learning is an increasingly popular framework that enables robots to learn to perform tasks from prior experience in environments where dynamics or shaped reward functions are challenging to model. However, because this requires robots to sample trajectories under significant dynamical uncertainty, the robot may perform unsafe maneuvers ...
openaire   +1 more source

Safe Reinforcement Learning With Dual Robustness

IEEE Transactions on Pattern Analysis and Machine Intelligence
Reinforcement learning (RL) agents are vulnerable to adversarial disturbances, which can deteriorate task performance or compromise safety specifications. Existing methods either address safety requirements under the assumption of no adversary (e.g., safe RL) or only focus on robustness against performance adversaries (e.g., robust RL).
Zeyang Li 0001, Chuxiong Hu, Yunan Wang, Yujie Yang, Shengbo Eben Li   +4 more
openaire   +4 more sources

Entropy‐Driven Design of Low‐Melting‐Point Alloys via Compositionally Complex Strategy

Advanced Engineering Materials, EarlyView.
Conventional low‐melting‐point alloys (LMPAs) are limited by a narrow compositional space and inherent property trade‐offs. This review presents an entropy‐driven design strategy that overcomes these limitations, ushering in a new class of low‐melting‐point compositionally complex alloys (LMCCAs).
Yinghui Shang, Jianxiang Zhao, Zhaoqi Chen, Hao Gong, Yinsen Yan, Junlei Tao, Yong Yang   +6 more
wiley   +1 more source

Distributionally robust Lyapunov–Barrier Networks for safe and stable control under uncertainty

Results in Control and Optimization
This paper addresses the challenge of simultaneously achieving stability and safety in nonlinear control systems subject to uncertain parameters. We propose distributionally robust Lyapunov–Barrier networks (DR-LBNs), a novel framework that unifies ...
Ali Baheri
doaj   +1 more source

What Is Acceptably Safe for Reinforcement Learning? [PDF]

, 2018
Machine Learning algorithms are becoming more prevalent in critical systems where dynamic decision making and efficiency are the goal. As is the case for complex and safety-critical systems, where certain failures can lead to harm, we must proactively consider the safety assurance of such systems that use Machine Learning.
Bragg, John Edward, Habli, Ibrahim
openaire   +2 more sources

Advances in Sustainable and Wearable Textile Based Soft Robotics

Advanced Functional Materials, EarlyView.
This Review examines advances in wearable textile‐based soft robotics, focusing on sustainable materials, integrated sensing, and scalable actuation. It discusses manufacturing and system integration across healthcare, assistive robotics, prosthetics, and human–machine interfaces, and highlights key challenges in circular design, including life‐cycle ...
Zahir Abbas, Marzia Dulal, Sophia K. Novoselov, Victoria K. Novoselov, Kostya S. Novoselov, Shaila Afroj, Nazmul Karim   +6 more
wiley   +1 more source

Memristive‐Gated RC‐Delay Synaptic Transistors for Time‐Encoded Analog in‐Memory Computing

Advanced Functional Materials, EarlyView.
A Memristive‐Gated Transistor for Time‐Encoded Analog In‐Memory Computing — By exploiting the RC delay of a self‐rectifying interface‐type memristor, nonlinear I–V distortion is structurally bypassed, enabling 3‐bit nonvolatile memory, spike‐timing‐based analog encoding, and hardware‐calibrated reservoir‐computing validation within a unified device ...
Yun‐Seo Shin, Eunjoo Yoo, Ki‐Hoon Son, Hyun‐Sik Kim, Dae‐Hee Han, Jeong Hyeon Son, Seung Hwan Lee, Hong‐Sub Lee   +7 more
wiley   +1 more source

Prediction of Safe-Zone Evolution in Poisonous Environment Based on Deep Learning

IEEE Access, 2020
Precise online identification of safe-zone evolution has been long desired in the context of indoor chemical attack events. Computational fluid dynamics (CFD) technology can provide great accuracy but is incapable of applying on online predictions of a ...
Jiawen Xv, Zhongyu Hou
doaj   +1 more source

Advances in Solution‐Processed Textile Triboelectric Nanogenerators: Ink Formation, Processing Strategies, Applications, and Challenges

Advanced Functional Materials, EarlyView.
Advanced ink systems for solution‐processed textile triboelectric nanogenerators are systematically summarized, spanning conductive, tribo‐negative, and tribo‐positive layers. By connecting ink chemistry, deposition methods, and device function, the present review reveals the key governing principles of solution development and highlights practical ...
Xinlong Sun, Stephen Beeby
wiley   +1 more source