How does a robot determine obstacle boundaries using LiDAR data?

Example Concept: LiDAR sensors emit laser beams and measure the time it takes for the beams to return after hitting an object. The data collected forms a point cloud, which represents the environment in 3D. By applying clustering algorithms, such as DBSCAN, the robot can identify groups of points that correspond to obstacles. Boundary extraction algorithms, like convex hull or alpha shapes, are then used to define the edges of these clusters, allowing the robot to understand the shape and position of obstacles in its path.