PythonLinearNonLinearControl is a library implementing the linear and nonlinear control theories in python.

Model Predictive Path Integral (MPPI) with approximate dynamics implemented in pytorch

Model Predictive Path Integral Control (MPPI) with PyTorch

Mapping, localization and using the navigation stack with ROS2 Jazzy

off-road navigation simulator for benchmarking planning algorithms

Adaptive control for skid-steer robots using GP-enhanced MPPI for robust navigation and obstacle avoidance on diverse terrains.

Code for the paper "Action Flow Matching for Continual Robot Learning" presented at Robotics: Science and Systems (RSS) 2025.

Bayesian Optimization for MPPI Control of Robot Arm Planar Pushing

A gym-like classical control benchmark for evaluating the robustnesses of control and reinforcement learning algorithms.

This project involves an autonomous indoor navigation system for a UGV using the ROS 2 Navigation Stack. It integrates SLAM, AMCL localization, global path planning with A*, and local obstacle avoidance via a Model Predictive Path Integral controller. LiDAR handles mapping and navigation, while a depth camera aids in close-range obstacle detection,

A Python-based demonstration of Model Predictive Path Integral (MPPI) control for navigating a simple 2D car model around multiple circular obstacles.

A Whole-Body-Control Stratgy for Quadcopter equipped with Manipulator.

Model based RL using Model Predictive Control

autonomous four wheeled omnidirectional robot

This repository provides a simulation framework for Model Predictive Path Integral (MPPI) control in a reach-avoid setting using both Matplotlib-based Python simulation and ROS2 with Gazebo integration. The simulation showcases real-time obstacle avoidance and goal-directed planning, leveraging JAX for highly efficient batch computation.

Python scripts to train a neuralnet for MPPI

NCSU Optimal Control Final Project