PIPO: Physics-informed deep reinforcement learning for pareto-optimal control for active suspension system
Authors:
- Cheng WangCWCheng Wang
- Xiaoxian CuiXCXiaoxian Cui
- Guanyu TaoGTGuanyu Tao
- Xinran ZhouXZXinran Zhou
- Zenan LiZLZenan Li
- Konghui GuoKGKonghui Guo
- 2 August 2026
- journal article
- Published by Elsevier in Expert Systems with Applications
- Vol. 333
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (523B2104)
This publication has 43 references indexed in Scilit:
- Multi-objective global velocity sequence generation method for active suspension system preview control based on proliferation compensation zoneAdvanced Engineering Informatics, 2025
- A reinforcement learning and H∞ hybrid control framework for 0–500 Hz full-band vibration suppression in active suspension systemsAdvanced Engineering Informatics, 2025
- Unlocking optimal ride comfort in intelligent vehicles via mechanism-data-driven active suspension road preview controlAdvanced Engineering Informatics, 2025
- Mechanism-data-driven control strategy for active suspension systems: Integrating deep reinforcement learning with differential geometry to enhance vehicle ride comfortAdvanced Engineering Informatics, 2025
- Adaptive control and reinforcement learning for vehicle suspension control: A reviewAnnual Reviews in Control, 2024
- A deep reinforcement learning-based active suspension control algorithm considering deterministic experience tracing for autonomous vehicleApplied Soft Computing, 2024
- Enhancing vehicle ride comfort through deep reinforcement learning with expert-guided soft-hard constraints and system characteristic considerationsAdvanced Engineering Informatics, 2023
- Adaptive hierarchical optimization control for electrohydraulic suspension with resistor-capacitor operatorApplied Mathematical Modelling, 2023
- The effect of speed bumps and humps on the concentrations of CO, NO and NO2 in ambient airAir Quality, Atmosphere & Health, 2019
- Reinforcement learning for control: Performance, stability, and deep approximatorsAnnual Reviews in Control, 2018