A machine learning model, using the transformer architecture, is used to design a feedback compensator and prefilter for various simulated plants. The output of the transformer is a sequence of compensator and prefilt...A machine learning model, using the transformer architecture, is used to design a feedback compensator and prefilter for various simulated plants. The output of the transformer is a sequence of compensator and prefilter parameters. The compensator and prefilter are linear models, preserving the ability to analyze the system with linear control theory. The input to the network is a window of recent reference and output samples. The goal of the transformer is to minimize tracking error at each time step. The plants under consideration range from simple to challenging. The more difficult plants contain closely spaced, lightly damped, complex conjugate pairs of poles and zeros. Results are compared to PID controllers tuned for a similar crossover frequency and optimal phase margin. For simple plants, the transformer converges to solutions which overly rely on the prefilter, neglecting the maximization of negative feedback. For more complex plants, the transformer designs a compensator and prefilter with more desirable qualities. In all cases, the transformer can start with random model parameters and modify them to minimize tracking error on the step reference.展开更多
Fault tolerance is essential for the maneuverability of self-propelled biomimetic robotic fish in real-world aquatic applications.This paper explores the fault-tolerance control problem of a free-swimming robotic fish...Fault tolerance is essential for the maneuverability of self-propelled biomimetic robotic fish in real-world aquatic applications.This paper explores the fault-tolerance control problem of a free-swimming robotic fish with multiple moving joints and a stuck tail joint.The created control system is composed of two main components:a feedback controller and a feedforward compensator.Specifically,the bio-inspired central pattern generator-based feedback controller is designed to make the robotic fish robust to external disturbances,while the feedforward compensator speeds up the convergence of the overall control system.Simulations are performed for control system analysis and performance validation of the faulty robotic fish.The experimental results demonstrate that the proposed fault-tolerant control method is able to effectively regulate the faulty robotic fish,allowing it to complete the desired motion in the presence of damage and thereby improving both the stability and the lifetime of the real robotic system.展开更多
文摘A machine learning model, using the transformer architecture, is used to design a feedback compensator and prefilter for various simulated plants. The output of the transformer is a sequence of compensator and prefilter parameters. The compensator and prefilter are linear models, preserving the ability to analyze the system with linear control theory. The input to the network is a window of recent reference and output samples. The goal of the transformer is to minimize tracking error at each time step. The plants under consideration range from simple to challenging. The more difficult plants contain closely spaced, lightly damped, complex conjugate pairs of poles and zeros. Results are compared to PID controllers tuned for a similar crossover frequency and optimal phase margin. For simple plants, the transformer converges to solutions which overly rely on the prefilter, neglecting the maximization of negative feedback. For more complex plants, the transformer designs a compensator and prefilter with more desirable qualities. In all cases, the transformer can start with random model parameters and modify them to minimize tracking error on the step reference.
基金the National Natural Science Foundation of China(61725305,61633020,61633004,and 61633017)the Beijing Natural Science Foundation(4161002)the Beijing Advanced Innovation Center for Intelligent Robots and Systems(2016IRS02).
文摘Fault tolerance is essential for the maneuverability of self-propelled biomimetic robotic fish in real-world aquatic applications.This paper explores the fault-tolerance control problem of a free-swimming robotic fish with multiple moving joints and a stuck tail joint.The created control system is composed of two main components:a feedback controller and a feedforward compensator.Specifically,the bio-inspired central pattern generator-based feedback controller is designed to make the robotic fish robust to external disturbances,while the feedforward compensator speeds up the convergence of the overall control system.Simulations are performed for control system analysis and performance validation of the faulty robotic fish.The experimental results demonstrate that the proposed fault-tolerant control method is able to effectively regulate the faulty robotic fish,allowing it to complete the desired motion in the presence of damage and thereby improving both the stability and the lifetime of the real robotic system.
