This project aims to develop and demonstrate an autonomous navigation system for a small-scale autonomous car using cost-effective hardware. The system will utilize Simultaneous Localization and Mapping (SLAM) techniques to build a map of the environment while simultaneously determining the vehicle's position within it.
Sensor Fusion: Integration of data from multiple sensors (LiDAR, IMU, Monocular/Stereo/RGB-D camera, Odometer) to enhance perception accuracy, object detection, tracking, and control.
SLAM: Implementation of SLAM algorithms to create a detailed map of the environment and localize the vehicle within it.
Path Planning: Development of algorithms to plan efficient and safe paths for the vehicle to navigate through the environment. Autonomous Navigation: Demonstration of autonomous navigation capabilities, including obstacle avoidance, goal-reaching, and collision prevention.
ROS (Robot Operating System): A flexible framework for building robot applications.
ROS2: The next-generation version of ROS, offering improved performance and scalability.
Python: A popular programming language for robotics and machine learning.
C++: A high-performance language used for time-critical tasks in robotics.
OpenCV: A library for computer vision tasks such as image processing and object detection.
Gmapping: A SLAM algorithm for 2D environments.
Cartographer: A SLAM algorithm for 2D and 3D environments.