the python variant of HECTOR force and moment-based MPC code with low-level control

ROS2 package that implements a nonlinear model predictive control (NMPC) pipeline for trajectory tracking for aerial vehicles that use the PX4 Autopilot

Aerial Gym Simulator - Isaac Gym Simulator for Aerial Robots

A beautiful, simple, clean, and responsive Jekyll theme for academics

MPC implementation using acados integrated with with PX4 on ROS2

AutoTrans: A Complete Planning and Control Framework for Autonomous UAV Payload Transportation

Impact-Aware Planning and Control for Aerial Robots with Suspended Payloads

Time-Optimal Planning for Long-Range Quadrotor Flights: An Automatic Optimal Synthesis Approach

Supplementary materials for "Learning Agile and Dynamic Motor Skills for Legged Robots"

Data Driven Dynamics Modeling for Aerial Vehicles

VisionOS App + Python Library to stream head / wrist / finger tracking data from Vision Pro to any robots.

A physics-driven, interactive lunar lander simulator.

A multirotor simulator with aerodynamics for education and research.

A Crazyflie simulator for testing CFLib Python code, ROS 2 nodes through Crazyswarm2, custom crazyflie-firmware modules, or perform a flight demo on the crazyflie-python-client.

Implementation of L1 adaptive control with ardupilot firmware.

Official implementation for the paper "CoVO-MPC: Theoretical Analysis of Sampling-based MPC and Optimal Covariance Design" accepted by L4DC 2024. CoVO-MPC is an optimal sampling-based MPC algorithm.

Easy and ready to use animation models for Matlab and python

Training transferable end-to-end quadrotor control policies on a laptop in 18 seconds.

L1 Adaptive Control implemented for the Crazyflie nano-scale quadcoptor platform

Open source materials for a novel structured legged robot, including mechanical design, electronic design, algorithm simulation, and software development. | 一个新型结构的轮腿机器人开源资料，包含机械设计、电子设计、算法仿真、软件开发等材料

This is a minimal repository containing the Matlab / Simulink to test a quadrotor subjected to single / double rotor failures, the incremental-nonlinear-dynamic-inversion controller.

Imposition of Hard Convex Constraints on Neural Networks

By introducing a differentiable contact model, DiffCoSim extends the applicability of Lagrangian/Hamiltonian-inspired neural networks to enable learning of hybrid dynamics.