sz-zr Goto Github PK

active_inference

Minimal version of an active inference controller applied to a 7-DOF robot arm

actor-critic-model-predictive-force-controller

admittance_controller

Admittance Control on a 6-DOF Manipulator using a FT Sensor

ai-for-beginners

12 Weeks, 24 Lessons, AI for All!

awesome-reinforcement-learning-lib

GitHub's code repository is all you need

awp

Astrodynamics with Python book, software, and videos. Spacecraft trajectory and attitude modeling and simulation

book-code

book-mathmatical-foundation-of-reinforcement-learning

This is the homepage of a new book entitled "Mathmatical Foundations of Reinforcement Learning."

c-resource

黑马程序员匠心之作|C++教程从0到1入门编程

cartesian_controllers

A set of Cartesian controllers for the ROS-control framework.

catalyst-rl-tutorial

Using Catalyst.RL to train a robot to perform peg-in-hole insertion in simulation.

codegan

command-theory-project

Control of Flexible Joint Robotic Manipulator

compliant-control-and-application

Compliant Control: 1) admittance control algorithm 2) impedance control algorithm 3) hybrid force&position algorithm in robotic arm (Universal Robot).

compliant_control

compliantjointtoolbox

Compliant Joint Toolbox (CJT) for MATLAB and Simulink

conntact

assembly software framework

contact_graspnet

Efficient 6-DoF Grasp Generation in Cluttered Scenes

cu-perception-manipulation-stack

indigo-ros packages for perception, camera calibration, arm manipulation, and finger sensing for the Kinova-Jaco arm

curriculum_rl_for_driving

Curriculum Design through Bayesian Optimization to train RL agents for the purpose of autonomous racing in the OpenAI Gym CarRacing Environment

dart

Dynamic Animation and Robotics Toolkit

data_driven_mpc

deep-reinforcement-learning-algorithms-with-pytorch

Clean and robust implementations of Reinforcement Learning algorithms by Pytorch

dmp

This ROS package is a general, robot-agnostic implementation of dynamic movement primitives (DMPs).

easy_handeye_demo

Virtual demonstration of a hand-eye calibration with easy_handeye, no hardware required

extended_state_observer

a disturbance rejection-based solution to the problem of robust output regulation of linear systems. The difference between the underlying plant and its nominal mathematical model is represented by two classes of disturbances. The first class is generated by an autonomous linear system while the other class has no specific dynamical structure. Robustness against the first disturbance class is achieved by the internal model principle. Next, in the framework of disturbance rejection control, an extended state observer (ESO) is designed to estimate and compensate for the second class of disturbances. As a result, the proposed output regulation method can deal with a vast range of uncertainties. The stability of the closed loop system is investigated and results on practical regulation are drawn. Keywords—Output regulation, extended state observer, disturbance rejection, linear system, robustness

exudyn

Multibody Dynamics Simulation: Rigid and flexible multibody systems

flexible-joint-manipulator-observer-in-the-form-of-a-stable-neural-network

In this project, an observer in the form of a stable neural network is proposed for any nonlinear MIMO system. As a result of experience, this observer utilizes a nonlinear in parameter neural network (NLPNN) which unlike LPNN, supports systems with higher degree of nonlinearity with no pre-knowledge of its dynamics. The learning rule for this neural network is based on the back-propagation method with a small modification. In addition, in order to guarantee the robustness of the observer, an e-modification term is added. Also, it is noted that there are no hard constraints like SPR on this method. Subsequently, the stability of this neural network observer is guaranteed by Lyapunov's direct method. At the end, the simulation results for a flexible-joint manipulator with this observer is demonstrated.

flobaroid

Framework for dynamical system identification of floating-base rigid body tree structures

force_control

6D Cartesian space hybrid force-velocity control using positional inner loop and wrist mounted FT sensor.