Design and application of adaptive PID controller based on asynchronous advantage actor–critic learning method

Sun, Qiang; Du, Chengze; Duan, Youxiang; Ren, Hui; Li, Hongqiang

doi:10.1007/s11276-019-02225-x

Cited by 25 publications

(11 citation statements)

References 22 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is also possible to determine the values with the perceived dynamics. The advantages of this situation are [37]:…”

Section: Methods 21 Pid Control Systemsmentioning

confidence: 99%

Improved Electro Search Algorithm with Intelligent Controller Control System: ESPID Algorithm

Cizmeci¹,

Altun²

2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Studies have established that hybrid models outperform single models. The particle swarm algorithm (PSO)-based PID (proportional-integral-derivative) controller control system is used in this study to determine the parameters that directly impact the speed and performance of the Electro Search (ESO) algorithm to obtain the global optimum point. ESPID algorithm was created by integrating this system with the ESO algorithm. The improved ESPID algorithm has been applied to 7 multi-modal benchmark test functions. The acquired results were compared to those derived using the ESO, PSO, Atom Search Optimization (ASO), and Vector Space Model (VSM) algorithms. As a consequence, it was determined that the ESPID algorithm's mean score was superior in all functions. Additionally, while comparing the mean duration value and standard deviations, it is observed that it is faster than the ESO algorithm and produces more accurate results than other algorithms. ESPID algorithm has been used for the least cost problem in the production of pressure vessels, which is one of the real-life problems. Statistical results were compared with ESO, Genetic algorithm and ASO. ESPID was found to be superior to other methods with the least production cost value of 5885.452.

show abstract

“…It is also possible to determine the values with the perceived dynamics. The advantages of this situation are [37]:…”

Section: Methods 21 Pid Control Systemsmentioning

confidence: 99%

Improved Electro Search Algorithm with Intelligent Controller Control System: ESPID Algorithm

Cizmeci¹,

Altun²

2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

show abstract

“…Another relevant line of work applied RL to tuning simple parameterized policies, such as PID controllers Dogru et al (2022); Shipman (2021); Carlucho et al (2017); Sun et al (2021); Sedighizadeh and Rezazadeh (2008). In Dogru et al (2022) the authors framed the problem as a contextual bandit problem, where the actions represent PID controller parameters, and an entire episode outcome is treated as a single reward value.…”

Section: Related Workmentioning

confidence: 99%

“…In Carlucho et al (2017) the authors applied tabular Q-learning to output the PI controller parameters to control a mobile robot. In Sun et al (2021); Sedighizadeh and Rezazadeh (2008) the authors applied online RL algorithms to train agents that output PID controller parameters in real time. In real production systems, changing the base policy parameters dynamically at every time step may require additional infrastructure investment on one hand, and may increase safety risks and policy explainability costs on the other.…”

Section: Related Workmentioning

confidence: 99%

Autoregressive Policies for Continuous Control Deep Reinforcement Learning

Korenkevych¹,

Mahmood²,

Vasan³

et al. 2019

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

Reinforcement learning algorithms rely on exploration to discover new behaviors, which is typically achieved by following a stochastic policy. In continuous control tasks, policies with a Gaussian distribution have been widely adopted. Gaussian exploration however does not result in smooth trajectories that generally correspond to safe and rewarding behaviors in practical tasks. In addition, Gaussian policies do not result in an effective exploration of an environment and become increasingly inefficient as the action rate increases. This contributes to a low sample efficiency often observed in learning continuous control tasks. We introduce a family of stationary autoregressive (AR) stochastic processes to facilitate exploration in continuous control domains. We show that proposed processes possess two desirable features: subsequent process observations are temporally coherent with continuously adjustable degree of coherence, and the process stationary distribution is standard normal. We derive an autoregressive policy (ARP) that implements such processes maintaining the standard agent-environment interface. We show how ARPs can be easily used with the existing off-the-shelf learning algorithms. Empirically we demonstrate that using ARPs results in improved exploration and sample efficiency in both simulated and real world domains, and, furthermore, provides smooth exploration trajectories that enable safe operation of robotic hardware.

show abstract

“…Recently, soft computing techniques such as neural networks have been successfully used in control systems. The use of artificial intelligence (AI) to replace the traditional PID controller can significantly simplify the tuning process and improve the overall performance and robustness of the control system [27][28][29]. Ghoniem et al [30] replaced a PID controller with a neural network in order to control a new low-cost semi-active vehicle suspension system, and it proved to have good accuracy in terms of vibration reduction and response time.…”

Section: Introductionmentioning

confidence: 99%

Control of a Novel Parallel Mechanism for the Stabilization of Unmanned Aerial Vehicles

Chamas,

Amine,

Gazo Hanna

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

The use of delivery drones is currently hindered by the inability of transported objects to maintain a steady position, which can result from roll-, pitch-, and heave-induced vibrations. This paper proposes a novel parallel manipulator for stabilizing the platform of unmanned aerial vehicles. The proposed mechanism builds upon an existing study of a 3-SRR/SRU parallel stabilizing mechanism by incorporating the dynamical properties of the system into the control model. The resultant control technique is then applied to both the 3-RRS and 3-SRR mechanisms, and a comparative study is conducted to identify the most reliable stabilizer for regulating the platform’s orientation. The results demonstrate that the 3-SRR mechanism exhibits superior robustness and stability characteristics compared to the other two mechanisms. Additionally, the 3-SRR mechanism is controlled using artificial neural networks, which significantly improves the accuracy and stability of the system. Overall, this research presents a novel and effective solution for stabilizing the platform of unmanned aerial vehicles, with significant implications for the development of delivery drone technology.

show abstract

Design and application of adaptive PID controller based on asynchronous advantage actor–critic learning method

Cited by 25 publications

References 22 publications

Improved Electro Search Algorithm with Intelligent Controller Control System: ESPID Algorithm

Improved Electro Search Algorithm with Intelligent Controller Control System: ESPID Algorithm

Autoregressive Policies for Continuous Control Deep Reinforcement Learning

Control of a Novel Parallel Mechanism for the Stabilization of Unmanned Aerial Vehicles

Contact Info

Product

Resources

About