NVIDIA DRIVE Labs Ep. 29: Enhanced Obstacle Avoidance for Autonomous Parking in Tight Spaces

Early Grid Fusion (EGF) is a new technique that enhances near-field obstacle avoidance in automatic parking assist. EGF combines machine-learned cameras and ultrasonic sensors to accurately detect and perceive surrounding obstacles, providing a 360-degree surround view. EGF solves the challenges of parking in tight spaces by detecting obstacles at a very close range as well as perceiving the obstacle’s location and height.

Timestamps:
00:00:00 - Challenges in parking in tight spaces
00:00:35 - What is Early Grid Fusion (EGF) parking?
00:00:56 - 360-degree surround view detection
00:01:29 - Accurate localization with a 4 centimeter grid
00:01:50 - Height estimation for situations such as China’s parking ground locks
00:02:13 - NVIDIA’s automatic parking assist in action

Tech Blog: https://developer.nvidia.com/blog/near-range-obstacle-perception-with-early-grid-fusion/
Watch the full series here: https://nvda.ws/3lHQP7H
Learn more about DRIVE Labs: https://nvda.ws/36r5c6t
Follow us on social:
Twitter: https://nvda.ws/3LRdkSs
LinkedIn: https://nvda.ws/3wI4kue