44 Papers
9 Citations
Xinyi Yu is an academic researcher from Zhejiang University of Technology. The author has contributed to research in topics: Computer science & PID controller. The author has an hindex of 4, co-authored 12 publications.
Chat about Author
Papers
A Self-adaptive SAC-PID Control Approach based on Reinforcement Learning for Mobile Robots
TL;DR: In this paper, a self-adaptive model-free SAC-PID control approach based on reinforcement learning for automatic control of mobile robots is proposed, which includes the upper controller based on soft actor-critic (SAC), one of the most competitive continuous control algorithms, and the lower controller based upon incremental PID controller.
30
Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning
TL;DR: LoRAPrune as mentioned in this paper proposes a unified framework for efficient fine-tuning and deployment of pre-trained models, which utilizes the values and gradients of Low-Rank Adaption (LoRA) rather than the gradients for importance estimation.
General stabilization method of fractional‐order PIλDμ controllers for fractional‐order systems with time delay
Abstract: In this paper, an effective method is proposed to get the stabilizing regions of fractional‐order PIλDμ controllers for an arbitrarily given fractional‐order system with time delay. For each known proportional gain (kp), integral gain (ki), or derivative gain (kd) in the PIλDμ controllers, the stabilizing region with respect to the other two control gains is derived respectively. The boundaries of the stabilizing regions are firstly obtained based on singular frequencies. Then, the main results are presented to directly determine the stabilizing region from an analytical viewpoint. The results avoid the time‐consuming stability test since the stabilizing region is usually determined by manually choosing lots of test points from all the divided regions by the resultant boundaries. Besides, the stabilizing (ki, kd) regions of the PIλDμ controllers for λ + μ = 2 can be determined and the linear programming characteristic of the stabilizing (ki, kd) region for the case λ + μ = 2 is obtained. Furthermore, the robust stabilizing region is analyzed. The results in this paper provide the basis for both the tuning of the PIλDμ controller in practice and the design of the PIλDμ controller satisfying different performance criteria. Numerical examples and an application example are presented to check the validity of the proposed method.
11
Research on multi-robot collaborative transportation control system
Cheng Cheng,Xinyi Yu,Lin-Lin Ou,Guo Yongkui +3 more
- 08 Aug 2016
TL;DR: A target tracking control algorithm is used in order to control multiple mobile robots to transport goods along with the planned path and the provided simulation results demonstrate the effectiveness of the multi-robot collaborative transportation control system.
10
Event-triggered adaptive optimal tracking control for nonlinear stochastic systems with dynamic state constraints.
TL;DR: In this article , an adaptive optimized event-triggered control (ETC) approach for nonlinear stochastic systems with uncertain nonlinear systems was proposed. But the adaptive adaptive dynamic programming (ADP) of identifier-actor-critic architecture and event triggering mechanism was not considered.
10