Redesigning a Self-Driving Pipeline for Lane Markings
Question: A self-driving car pipeline is currently operating without explicit lane-marking inputs. According to Machine Learning Yearning, how should the pipeline be redesigned once it is recognized that a skilled human driver requires lane-marking locations, and what are the two main benefits of this specific architectural change?
Sample answer: The self-driving pipeline should be redesigned by adding a dedicated lane-marking detector component. This redesign provides two primary benefits: first, it gets the important, previously missing lane-marking information to the path planning module; second, it avoids making any other single module in the pipeline overly complex to build or train.
Key points:
- Redesign the pipeline by adding a lane-marking detector component.
- Deliver important, previously missing lane-marking location information to the path planning module.
- Avoid making any particular module overly complex to build or train.
Rubric: The answer must state that a dedicated lane-marking detector should be added to the pipeline. It must also identify the two benefits: delivering the missing information to the path planning module and preventing other modules from becoming overly complex to build or train.
0
1
Tags
Machine Learning
Deep Learning
Supervised Learning
Dive into Deep Learning @ D2L
Data Science
Machine Learning Strategy
Related
Avoiding Overly Complex Pipeline Modules During Redesign
According to Machine Learning Yearning, why is adding a dedicated lane-marking detector the recommended redesign choice for the self-driving pipeline?
True or False: Adding a lane-marking detector to the self-driving pipeline is recommended because it provides previously missing lane location data to the path planning module.
When a self-driving pipeline is missing lane-marking information needed by path planning, Ng recommends redesigning it by adding a _____ component.
Why should a lane-marking detector be added to a self-driving pipeline?
Recognizing that a skilled human driver needs lane-marking data suggests redesigning the pipeline to include a lane-marking detector.
Adding a lane-marking detector gets the important, previously missing information about _____ to the path planning module.
Match each pipeline redesign element to its role when adding a lane-marking detector.
Order the reasoning steps Ng uses to justify adding a lane-marking detector to a self-driving pipeline.
Why is a dedicated lane-marking detector preferable to embedding lane-detection into an existing pipeline module?
According to Machine Learning Yearning, the path planning module performs equally well with or without lane-marking location data.
Adding a lane-marking detector is better because it avoids making any particular module overly _____ to build or train.
Match each design principle to the outcome it achieves in the lane-marking detector redesign.
Order the steps for evaluating and implementing a pipeline redesign that adds a lane-marking detector.
Redesigning a Self-Driving Pipeline for Lane Markings
Resolving Path Planning Failures in a Self-Driving Vehicle
Impact of Lane-Marking Data on Path Planning