Reinforcement Learning for Autonomous Process Control in Industry 4.0: Advantages and Challenges

Applied Artificial Intelligence, Год журнала: 2024, Номер 38(1)

Опубликована: Авг. 5, 2024

In recent years, the integration of intelligent industrial process monitoring, quality prediction, and predictive maintenance solutions has garnered significant attention, driven by rapid advancements in digitalization, data analytics, machine learning. As traditional production systems evolve into self-aware self-learning configurations, capable autonomously adapting to dynamic environmental conditions, significance reinforcement learning becomes increasingly apparent. This paper provides an overview developments applications manufacturing industry. Various sectors within manufacturing, including robot automation, welding processes, semiconductor industry, injection molding, metal forming, milling power are explored for instances application. The analysis focuses on application types, problem modeling, training algorithms, validation methods, deployment statuses. Key benefits these identified. Particular emphasis is placed elucidating primary obstacles impeding adoption implementation technology settings, such as model complexity, accessibility simulation environments, safety constraints, interpretability. concludes proposing potential alternatives avenues future research address challenges, improving sample efficiency bridging simulation-to-reality gap.

Язык: Английский

---

Trajectory optimization and tracking control of free-flying space robots for capturing non-cooperative tumbling objects

Aerospace Science and Technology, Год журнала: 2023, Номер 143, С. 108718 - 108718

Опубликована: Ноя. 8, 2023

Язык: Английский

---

On Deep Recurrent Reinforcement Learning for Active Visual Tracking of Space Noncooperative Objects

IEEE Robotics and Automation Letters, Год журнала: 2023, Номер 8(8), С. 4418 - 4425

Опубликована: Июнь 5, 2023

Active tracking of space noncooperative object that merely relies on vision camera is greatly significant for autonomous rendezvous and debris removal. Considering its Partial Observable Markov Decision Process (POMDP) property, this letter proposes a novel deep recurrent neural network architecture, named as attention module based active visual (RAMAVT), incorporating Multi-Head Attention (MHA) Squeeze-and-Excitation (SE) layer remarkably improve the representative ability with almost no extra computational cost. It has been successfully applied to value-based policy gradient-based reinforcement learning algorithm, learned drive chasing spacecraft follow arbitrary high-frequency near-optimal velocity control commands. Extensive experiments robustness evaluations implemented non-cooperative (SNCOAT) benchmark show betterment our method compared other state-of-the-art trackers. In addition, we make further ablation study interpretability research RAMAVT which validity rationality have demonstrated.

Язык: Английский

---

Advancements in Q‐learning meta‐heuristic optimization algorithms: A survey

Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery, Год журнала: 2024, Номер 14(6)

Опубликована: Авг. 18, 2024

Abstract This paper reviews the integration of Q‐learning with meta‐heuristic algorithms (QLMA) over last 20 years, highlighting its success in solving complex optimization problems. We focus on key aspects QLMA, including parameter adaptation, operator selection, and balancing global exploration local exploitation. QLMA has become a leading solution industries like energy, power systems, engineering, addressing range mathematical challenges. Looking forward, we suggest further integration, transfer learning strategies, techniques to reduce state space. article is categorized under: Technologies > Computational Intelligence Artificial

Язык: Английский

---

Deep deterministic policy gradient algorithm for crowd-evacuation path planning

Computers & Industrial Engineering, Год журнала: 2021, Номер 161, С. 107621 - 107621

Опубликована: Авг. 13, 2021

Язык: Английский

---