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
Tags
Machine Learning
Deep Learning
Supervised Learning
Dive into Deep Learning @ D2L
Data Science
Machine Learning Strategy
Machine Learning Yearning @ DeepLearning.AI
Related
Why Labeled Perception Data Can Make a Staged Driving System Easier
When is a staged model design especially attractive?
A staged design can be better when each stage has usable training data.
Available data for _____ in a staged workflow
Match staged system concepts
Choosing a Multi-Stage Pipeline When Subtask Labels Are Abundant
When a Modular Pipeline Can Be Competitive
Choose a pipeline structure when intermediate labels are abundant
When can a staged pipeline outperform a single direct model?
Which example is an intermediate module in a larger machine learning pipeline?
Limited data makes a multi-stage pipeline the best choice.
Learn After
Why can limited data availability make an intermediate detector a better choice than a fully end-to-end driving system?
True or False: Gathering paired examples of street images and steering commands for an autonomous vehicle is typically no harder than labeling each image with objects such as pedestrians or trucks.
For a direct end-to-end warehouse navigation model, each training example must be an (image, _____) pair.
Why is it usually easier to gather data for an object detector than for an end-to-end control policy?
A fully end-to-end self-driving model is straightforward to train because labeled image-and-steering examples are cheap and quick to gather.
What paired examples are needed to train a direct driving policy from video?
Match each pipeline idea to the data situation it fits best in a factory inspection setting.
Order the steps for deciding whether to use a staged pipeline instead of a direct end-to-end model for a robot navigation task.
When direct pairs of sensor images and control commands are scarce, which model design is most strongly encouraged by the data situation?
It is hard to find labeled images of cars and pedestrians for training intermediate detectors.
If you have plenty of labeled data for the _____ parts of a workflow, a multi-stage design can be a sensible choice.
Match each data situation to the design lesson it suggests in an autonomous driving project.
Order the reasoning steps for why a staged perception pipeline can be easier to build than a pure end-to-end driving model.
How Data Collection Constraints Shape the Choice Between End-to-End and Modular Autonomous Driving Systems
Choosing a navigation stack with limited labeled driving data
Why modular driving systems are easier to train than fully end-to-end ones