PyRoboLearn: a Python framework for Robot Learning

Demonstration code of the "Constrained Probabilistic Movement Primitives for Robot Trajectory Adaptation" paper (Frank et al.)

Google MediaPipe Face + Hands + Body + Object

Use python and Vrep to do the path planning for ur5 robot

OpenRAVE plugin that implements the CHOMP trajectory optimizer.

Recursive importance sampling for Nyström kernel matrix approximation

Time series distances: Dynamic Time Warping (fast DTW implementation in C)

Combined Learning from Demonstration and Motion Planning

This repository contains code examples for the paper "Learning to sequence and blend robotics skills via differentiable optimization".

Gaussian Process Motion Planner 2

This repository contains the code for GMR-based Gaussian process.

Robot Learning from Human Demonstrations with Unexpected Obstacles during task reproduction. This is achieved using a combination of Motion Planning (BIT*) and Motion Primitives (KMP).

RL and DMP algorithms implemented from scratch with plain Numpy.

notes of machine learning algorithm derivation

Python implementation of Probabilistic Motor Primitives including a ROS overlay to be used with JointTrajectory, JointState and RobotTrajectory, RobotState (Move It) messages

Obstacle Avoidance with Dynamic Movement Primitives

Code for the Neural Processes website and replication of 4 papers on NPs. Pytorch implementation.

A wrapper layer for stacking layers horizontally

Conditional Neural Movement Primitves - Implementation and Data of the Experiments

Python implementation of Probabilistic Motor Primitives including a ROS overlay to be used with JointTrajectory, JointState and RobotTrajectory, RobotState (Move It) messages

A PyTorch Implementation of Convolutional Conditional Neural Process.

Implementation of the Convolutional Conditional Neural Process

Conditional Neural Movement Primitves

ACNMP: Flexible Skill Formation with Learning from Demonstration and Reinforcement Learning via Representation Sharing

Robot Skill Learning using Probabilistic Movement Primitives

eBPF-based Networking, Security, and Observability