Skip to content

To Develop a reliable Motion Planner with Control algorithms for collision-free path planning and efficient navigation in a simulated environment.

License

Notifications You must be signed in to change notification settings

vaishnavi-1035/IITISoC-24-IVR4-Motion-Planning-with-Controls-for-Self-Driving-Vehicles

 
 

Repository files navigation

IITISoC-24-IVR4-Motion-Planning-with-Controls-for-Self-Driving-Vehicles

Goal:

To develop a reliable Motion Planner with Control algorithms for collision-free path planning and efficient navigation in a simulated environment.

People Involved :

Mentors:

Members:


-

Implementation:

As an input we were given a world file for the project which looks like this in gazebo Screenshot For the above project, we modelled our own 3-wheeled vehicle Image Our first task was to get the map of the above world through SLAM. For SLAM, we conducted many tests with different robots like:

  1. Turtlebot3
  2. Atomatic Addison bot

We conducted SLAM with the following two packages

  1. Cartographer(for turtlebot3)
  2. SLAM toolbox(For the addison bot)

We got better results with latter, and the map after looked like this(we only mapped the lane in which the robot has to navigate through) map

After getting a fairly accurate map, we moved onto trying path planning algorithms like

  1. RRT
  2. Astar
  3. RRTstar

First we converted our map to a binary occupancy grid given below to make path planning feasible Image

Here's a one with Astar: Image

In the next phase, we'll be starting with implemention of Control algorithms like MPC(Model Predictive Control).

About

To Develop a reliable Motion Planner with Control algorithms for collision-free path planning and efficient navigation in a simulated environment.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 85.8%
  • Python 13.6%
  • CMake 0.6%