mellowcat0807's starred repositories
Coursera-ML-AndrewNg-Notes
吴恩达老师的机器学习课程个人笔记
ELEGOOSmartCarV4
Elegoo Smart Robot Car V4.0
finding-all-spanning-trees-in-directed-graph
Finding all spanning trees of directed and undirected graphs
FindingAllSpanningTrees
Finding all spanning trees of directed graphs
Cyber-Physical-System
Attacks and detection technique using matlab simulink in CPS.
mimoPIDtune
Matlab implementation of the "MIMO PID tuning via iterated LMI restiction" by Boyd, Hast, and Astrom
consensus.attack
MATLAB simulation codes for article entitled ``Fault Tolerant Periodic Event-triggered Consensus Under Communication Delay and Multiple Attacks''
NN-Dropout
This code is for training feedforward neural networks with dropout.
basic_nn_in_matlab
Implements of MATAB神经网络30个案例分析
Stock-Market-Prediction-using-Neural-Networks-and-Genetic-Algorithm
Matlab Module for Stock Market Prediction using Simple NN
Machine-Learning-in-NDN-network
Implementation of backpropagation algorithm in MATLAB to detect DDOS (Distributed Denial Of Service) Attack in NDN(Named Data Networking).
Efficient-motion-planning
To guarantee safe and efficient driving for automated vehicles in complicated traffic conditions, the motion planning module of automated vehicles are expected to generate collision-free driving policies as soon as possible in varying traffic environment. However, there always exist a tradeoff between efficiency and accuracy for the motion planning algorithms. Besides, most motion planning methods cannot find the desired trajectory under extreme scenarios (e.g., lane change in crowded traffic scenarios). This study proposed an efficient motion planning strategy for automated lane change based on Mixed-Integer Quadratic Optimization (MIQP) and Neural Networks. We modeled the lane change task as a mixed-integer quadratic optimization problem with logical constraints, which allows the planning module to generate feasible, safe and comfortable driving actions for lane changing process. Then, a hierarchical machine learning structure that consists of SVM-based classification layer and NN-based action learning layer is established to generate desired driving policies that can make online, fast and generalized motion planning. Our model is validated in crowded lane change scenarios through numerical simulations and results indicate that our model can provide optimal and efficient motion planning for automated vehicles
rssi-localization-hratc
Mobile robot localization system using RSSI and Extended Kalman Filters, inspired in the 4th HRATC.
SRCL_FFNAV
This repo contains the code developed as part of the Relative Navigation for Formation Flying project with the Spacecraft Robotics and Control Laboratory at Carleton University.
slam_matlab
VO, Localization, Graph Optimization, Ground Truth, Trajectory Plot written in Matlab
robotics-toolbox-matlab
Robotics Toolbox for MATLAB
Process-Control
Process Control code, include optimization, Model Predictive Control (MPC), Moving Horizon, Kalman filter etc
Hybrid_Fuzzy_Kalman_Filter
Mixed Kalman-Fuzzy Sliding Mode State Observer in Disturbance Rejection Control of a Vibrating Smart Structure Atta Oveisi*1, Tamara Nestorović1 1Ruhr-Universität Bochum, Mechanik adaptiver Systeme, Institut Computational Engineering, D-44801, Bochum, Germany. E-Mail: atta.oveisi@rub.de ABSTRACT In the controllers that are synthesized on a nominal model of the nonlinear plant, the parametric matched uncertainties and nonlinear/unmodeled dynamics of high order nature can significantly affect the performance of the closed-loop system. In this note, owing to the robust character of the sliding mode observer against modeling perturbations, measurement noise, and unknown disturbances and due to the non-fragile behavior of the Kalman filter against process noise, a mixed Kalman sliding mode state-observer is proposed and later enhanced by the addition of an intelligent fuzzy agent. In light of the proposed technique, the chattering phenomena and the conservative boundary neighboring layer of the high gain sliding mode observer are addressed. Then, a robust active disturbance rejection controller is developed by using static feedback of the estimated states using direct Lyapunov quadratic stability Theorem. The reduced order plant for control design purposes is subjected to some simulated square-integrable disturbances and is assumed to have mismatch uncertainties in system matrices. Finally, the robust performance of the closed-loop scheme with respect to the mentioned perturbation signals and modeling imperfections is tested by implementing the control system on a mechanical vibrating smart cantilever beam. Keywords: Fuzzy system; Nonlinear control; Active disturbance rejection; Kalman Filter; Vibration suppression.
AFISMC
a new observer-based adaptive fuzzy integral sliding mode controller (AFISMC) is proposed based on the Lyapunov stability theorem. The plant under study is subjected to a square-integrable disturbance and is assumed to have mismatch uncertainties both in state- and input-matrices. In addition, a norm-bounded time varying term is introduced to address the possible existence of un-modelled/nonlinear dynamics. Based on the classical sliding mode controller (SMC), the equivalent control effort is obtained to satisfy the sufficient requirement of SMC and then the control law is modified to guarantee the reachability of the system trajectory to the sliding manifold. The sliding surface is compensated based on the observed states in the form of linear matrix inequality (LMI). In order to relax the norm-bounded constrains on the control law and solve the chattering problem of SMC, a fuzzy logic (FL) inference mechanism is combined with the controller. An adaptive law is then introduced to tune the parameters of the fuzzy system on-line. Finally, by aiming at evaluating the validity of the controller and the robust performance of the closed-loop system, the proposed regulator is implemented on a real-time mechanical vibrating system.
SMC-controller
Sliding mode controller for tracking trajectory of an autonomous vehicle.
Dynamic-Stochastic-Block-Model
MATLAB toolbox for fitting discrete-time dynamic stochastic block models
AUVForwardDynamics
Dynamic Model of a 6DOF AUV
yalmip-for-matlab
This is a simple code to solve LP problems with yalmip and all different solvers, very simple and nice to begin with!
vnc2017-CACC-data
Data repository for our VNC 2017 paper.
the-synchronization-control-of-events-triggered-network-with-Partial-differential-node
针对事件触发的,以偏微分系统为节点的复杂网络,仿真其节点同步控制策略