A hierarchical framework for improving ride comfort of autonomous vehicles via deep reinforcement learning with external knowledge

Y Du, J Chen, C Zhao, F Liao… - Computer‐Aided Civil and …, 2023 - Wiley Online Library
Ride comfort plays an important role in determining the public acceptance of autonomous
vehicles (AVs). Many factors, such as road profile, driving speed, and suspension system …

[HTML][HTML] Advancements in Semi-Active Automotive Suspension Systems with Magnetorheological Dampers: A Review

Z Wang, C Liu, X Zheng, L Zhao, Y Qiu - Applied Sciences, 2024 - mdpi.com
Magnetorheological (MR) dampers have significantly advanced automotive suspension
systems by providing adaptable damping characteristics in response to varying road …

[HTML][HTML] Adaptive control and reinforcement learning for vehicle suspension control: A review

JB Kimball, B DeBoer, K Bubbar - Annual Reviews in Control, 2024 - Elsevier
The growing adoption of electric vehicles has drawn a renewed interest in intelligent vehicle
subsystems, including active suspension. Control methods for active suspension systems …

Enhancing vehicle ride comfort through deep reinforcement learning with expert-guided soft-hard constraints and system characteristic considerations

C Wang, X Cui, S Zhao, X Zhou, Y Song… - Advanced Engineering …, 2024 - Elsevier
Currently, the research on controlling vehicle ride comfort primarily revolves around utilizing
traditional algorithms for active or semi-active control of suspension systems. However …

Advancing Active Suspension Control with TD3-PSC: Integrating Physical Safety Constraints into Deep Reinforcement Learning

M Deng, D Sun, L Zhan, X Xu, J Zou - IEEE Access, 2024 - ieeexplore.ieee.org
This study addresses the limitations of traditional active and semi-active suspension control
systems in terms of adaptability and nonlinear handling, by exploring the potential of Deep …

Robot manipulation task learning by leveraging se (3) group invariance and equivariance

J Seo, NPS Prakash, X Zhang, C Wang, J Choi… - arXiv preprint arXiv …, 2023 - arxiv.org
This paper presents a differential geometric control approach that leverages SE (3) group
invariance and equivariance to increase transferability in learning robot manipulation tasks …

Research on deep reinforcement learning control algorithm for active suspension considering uncertain time delay

Y Wang, C Wang, S Zhao, K Guo - Sensors, 2023 - mdpi.com
The uncertain delay characteristic of actuators is a critical factor that affects the control
effectiveness of the active suspension system. Therefore, it is crucial to develop a control …

Designing a Switched Takagi-Sugeno Fuzzy controller for CDC semi-active suspensions with current input constraint

Y Qing, Z Hongliang, C Songlin, M Weiwei… - … Systems and Signal …, 2023 - Elsevier
To prevent the degradation of control performance resulting from the use of the clipped
approach, this paper presents a novel control strategy for CDC (continuous damping control) …

Distributional and hierarchical reinforcement learning for physical systems with noisy state observations and exogenous perturbations

J Park, J Choi, S Nah, D Kim - Engineering Applications of Artificial …, 2023 - Elsevier
Reinforcement learning has shown remarkable success in various applications, and in some
cases, even outperforms human performance. However, despite the potential of …

Fuzzy soft deep deterministic policy gradient for distribution-static synchronous compensation of distribution networks

L Huang, L Yin - Engineering Applications of Artificial Intelligence, 2024 - Elsevier
To address power quality issues in distribution networks, static synchronous compensation,
also known as distribution-static synchronous compensation (D-STATCOM), has been …