[PART 1] CVPR 2021 Tutorial: All About Self-Driving

A full day tutorial covering all aspects of self-driving. This tutorial will provide the necessary background for understanding the different tasks and associated challenges, the different sensors and data sources one can use and how to exploit them, as well as how to formulate the relevant algorithmic problems such that efficient learning and inference is possible. We will first introduce the self-driving problem setting and the existing solutions both top down from a high level perspective and bottom up from technology and algorithm specific manner in a detailed fashion. We will then extrapolate from the state of the art and discuss where the challenges and open problems are, and where we need to head towards to provide a scalable, safe and affordable self-driving solution.

Timestamps:
00:00:00 Hardware
00:11:16 Hardware Q&A
00:17:16 Perception
00:57:53 Perception Q&A
01:04:03 Prediction
01:50:33 Prediction Q&A
01:53:51 Motion Planning
02:39:31 Motion Planning Q&A
02:42:00 Vehicle-to-Vehicle Communications
03:01:31 Vehicle-to-Vehicle Communications Q&A
03:07:50 Datasets and Metrics
03:36:35 Datasets and Metrics Q&A

[PRATEEK]

This is years of work n a presentation. Thank you for sharing such in depth info. I think this is the most expansive explanation on youtube

[gyudori]

Thanks. Its so nice to watch cvpr in youtube. Btw, can we get presentation pdf files??

[rtluo]

It seems the first talk and part of the second talk are missing? Will you provide a full version or you lost the footage?