YoVDO

CarMap - Fast 3D Feature Map Updates for Automobiles

Offered By: USENIX via YouTube

Tags

USENIX Symposium on Networked Systems Design and Implementation (NSDI) Courses Autonomous Vehicles Courses 3D Mapping Courses Real-Time Data Processing Courses

Course Description

Overview

Explore a groundbreaking approach to near-real-time crowd-sourced 3D map collection for autonomous vehicles in this 20-minute conference talk from NSDI '20. Delve into CarMap, an innovative system that addresses the challenge of creating compact, up-to-date 3D maps for vehicle localization. Learn about its lean representation of feature maps, novel object filtering techniques, and position-based feature matching to enhance localization robustness. Discover how CarMap's stitching algorithm combines map segments from multiple vehicles for unmapped regions and efficiently updates existing map areas. Gain insights into CarMap's performance, including its ability to update maps in less than a second, reduce map sizes by 75× compared to competing strategies, and improve localization accuracy in challenging scenarios.

Syllabus

NSDI '20 - CarMap: Fast 3D Feature Map Updates for Automobiles


Taught by

USENIX

Related Courses

6.S094: Deep Learning for Self-Driving Cars
Massachusetts Institute of Technology via Independent
Multi-Object Tracking for Automotive Systems
Chalmers University of Technology via edX
Decision-Making for Autonomous Systems
Chalmers University of Technology via edX
Self-Driving Fundamentals: Featuring Apollo
Baidu via Udacity
Transport Systems: Global Issues and Future Innovations
University of Leeds via FutureLearn