Humanoid footstep planner based on baseline methods with graph search

Terrain-aware locomotion pipeline for quadruped robots - 95% navigation success, 50% fall reduction using depth camera perception, ML terrain classification, and adaptive footstep planning with MoveIt2

Whole-body motion planning for Unitree G1 humanoid in MuJoCo - ZMP preview control, A* footstep planning, MPC balance (49% energy reduction), RL locomotion, and Jacobian IK manipulation

This repository is the TensorFlow implementation of my paper titled "Footstep planning of humanoid robot in ROS environment using Generative Adversarial Networks (GANs) deep learning"

Custom rebuild of the footstep planner package from https://github.com/ROBOTIS-GIT/humanoid_navigation, used in the Master thesis of Mike Simon in Feb 2022.

VIO + Footstep Planner for GPS-denied quadruped navigation - 98% success rate, 60% drift reduction, real-time autonomous navigation with loop closure

ROS 2 Interfaces for Ashioto package