In this session you will learn how and why maps are used in autonomous driving. We will cover the different kinds of map representations that are used by tasks like motion forecasting, motion planning, simulation and explain their tradeoffs. We also cover online mapping together with its benefits and challenges.

Speaker: Andrei Bârsan



A full day tutorial from Waabi covering all aspects of autonomous driving. Delivered at the top international computer vision conference, CVPR, 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 begin by introducing the selfdriving problem setting and a broad range of existing solutions, both topdown from a highlevel perspective, as well as bottomup from technological and algorithmic points of view. 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 selfdriving solution for the future.

Since last year’s instance (https://waabi.ai/cvpr2023/), countless new and promising avenues of research have started gaining traction, and we have updated our tutorial accordingly. To name a few example, this includes topics like occupancy forecasting, selfsupervised learning, foundation models, the rise of Gaussian Splatting and diusion models for simulation as well as the study of closedloop vs. openloop evaluation.

See the tutorial website for more information: https://waabi.ai/cvpr2024/