Skip to content

Latest commit

 

History

History
executable file
·
40 lines (32 loc) · 1.66 KB

README.md

File metadata and controls

executable file
·
40 lines (32 loc) · 1.66 KB
Raw

🦾 Skeleton Trajectory Repository

Welcome to the Skeleton Trajectory Repository project of the CARI with Vis4Mechs Lab

This repository develops a ROS-based framework to identify human keypoints and reconstruct them in 3D within a collaborative robotic cell, enabling effective human movement tracking.

🚀 Start the Skeleton Tracking Node

The entire framework can be run in a simplified way via a launcher file that automatically handles the different nodes:

roslaunch skeleton_trajectory skeleton_trajectory.launch

⚙️ Launch Parameters

The following parameters are available:

  • kalmanBase: specifies the filter type.
    • kalmanBase:=True: the default condition, filters the points independently (assuming constant acceleration in Cartesian space).
    • kalmanBase:=False: applies filtering based on a model of the person’s limb kinematics (assuming constant acceleration in joint space).

📋 Requirements

  • Create a venv: 
    python -m venv /path/to/new/virtual/environment
  • Install requirements (pip or pip3) (check path to requirements): 
    pip3 install -r requirements.txt
  • Activate the virtual environment: 
    source path_to_venv/bin/activate

👥 Maintainers