Learning In-the-Wild Sensor Simulation for Autonomous Driving

Explore the critical role of sensor simulation in autonomous driving through this comprehensive 56-minute talk by Ze Yang from Montreal Robotics. Delve into the process of creating accurate digital replicas of real-world environments and generating simulated sensor data to facilitate the development and evaluation of self-driving vehicles. Learn about constructing controllable and realistic digital twins using real-world data, manipulating actors, scenes, and environments to create novel scenarios, and efficiently rendering them to generate realistic multi-sensor simulations. Discover the methodology for measuring simulator realism within the context of autonomous systems. Gain insights into the intersection of 3D computer vision, robotics, and machine learning as applied to autonomous driving technology.

Ze Yang: Learning in-the-wild Sensor Simulation for Autonomous Driving