[자율주행 스터디] Introduction to Self-Driving cars - Week 2-4

Week 2 - Self-Driving Hardware and Software Architectures

Course info.

• https://www.coursera.org/learn/intro-self-driving-cars?
  • UNIVERSITY OF TORONTO

---

Lesson 4 : Environment Representation

Contents

• Environmental Map Types

---

Environmental Map Types

• Localization of the vehicle in the environment
  • Localization point cloud or feature map
    • to accurately estimate the precise position of vehicle at all time
      • Collects continuous sets if Lidar
      • The difference between Lidar maps is used to calculate the movement of the autonomous vehicle
• Collision avoidance with static objects
  • Ocuupancy grid map
    • to plan safe collision free path
      • Discretized fine grain grid map
        • Can be 2D or 3D
      • Occupancy by a static object
        • Trees and buildings
      • Curbs and other non-drivable surfaces
        • Dynamic objects are removed
• Path planning
  • Detalid road map
    • to plan path current position to destination
      • Fully online (어려움)
      • Fully offline (Collecting data several times)
      • Created offline and updated online