Concept icon
Concept

Why Labeled Perception Data Can Make a Staged Driving System Easier

In a self-driving project, it is often easier to collect labeled examples for perception tasks such as identifying vehicles, cyclists, or pedestrians than to collect large numbers of image-and-control pairs for direct driving. Because direct control labels are slower and more expensive to gather, a design that first detects important objects and then makes a driving decision can fit the available data better than a fully end-to-end system.

0

1

Concept icon
Updated 2026-08-12

Contributors are:

Who are from:

Tags

Machine Learning

Deep Learning

Supervised Learning

Dive into Deep Learning @ D2L

Data Science

Machine Learning Strategy

Machine Learning Yearning @ DeepLearning.AI

Learn After