Service Robot Visual Tracking

B.Sc. Capstone Project (2nd Place Award 🏆)

Real-time visual target tracking and autonomous following system for a service robot. The system implements Sensor Fusion by combining Computer Vision (for object detection) with LIDAR data to maintain a precise safe following distance and perform dynamic obstacle avoidance.

🛠 Tech Stack

• Core: ROS (Robot Operating System), C++, Python
• Sensors: RGB Camera, 2D LIDAR
• Algorithms: Visual Servoing, PID Control, Sensor Fusion (Camera + LIDAR)

Install ROS and turtlebot3 environment

1. Follow the install guide for turtlebot3 PC setup.

1.1. Install Ubuntu on Remote PC.

1.2. Install ROS on Remote PC

1.3. Install turtlebot3 Dependent ROS Packages

2. install turtlebot3 gazebo simulation files.

3. update Gazebo to 7+

for instructions link.

sudo sh -c 'echo "deb http://packages.osrfoundation.org/gazebo/ubuntu-stable `lsb_release -cs` main" > /etc/apt/sources.list.d/gazebo-stable.list'
wget http://packages.osrfoundation.org/gazebo.key -O - | sudo apt-key add -
sudo apt-get update
sudo apt-get install gazebo7

4. add bashrc args

echo "export TURTLEBOT3_MODEL=waffle_pi" >> ~/.bashrc
echo "export SVGA_VGPU10=0" >> ~/.bashrc

follow package

installing the follow package

cd ~/catkin_ws/src/
git clone https://github.com/zeged85/opencv_track3.git
cd ~/catkin_ws && catkin_make

Bringup

running simulation or real robot either run your robot with roscore, or launch the simulator.

terminal 1 - rosCore: simulation

simulator

roslaunch follow follow_sim.launch 

roscore + robot launch(on robot)

roscore

terminal 1.1 - teleop

roslaunch follow linear_teleop_key.launch

terminal 2 - Control

launch controller

roscd follow
cd src
python ./follow3.py

terminal 3 - GUI

launch GUI

roscd follow
cd src
python ./auto_ros_commands.py 

make sure topics match in follow3.py and auto_ros_commands.py to robot/simulator