Why breaking a robot navigation task into subtasks can reduce the amount of training data needed.
Question: A delivery robot is designed with four separate modules: lane detection, obstacle detection, traffic-signal recognition, and speed control. Explain why training these modules separately can require less data than training one end-to-end model that maps raw sensor input directly to driving actions.
Sample answer: Splitting the problem into four modules reduces the difficulty of the function that each model must learn. Lane detection, obstacle detection, traffic-signal recognition, and speed control are all narrower mappings than a single model that must learn every step from raw sensors to final actions at once. Because each subtask is simpler, each one can usually be learned from less training data than a monolithic end-to-end system.
Key points:
- The task is divided into four modules: lane detection, obstacle detection, traffic-signal recognition, and speed control.
- Each module learns a simpler function than an end-to-end system.
- Simpler functions generally need less data.
- A single end-to-end model must learn a more complex mapping and therefore usually needs more training data.
Rubric: The response must explain that the robot task is decomposed into four subtasks. It must state that each subtask is a simpler function to learn. Finally, it must connect that simplicity to the need for less training data compared with a single end-to-end model.
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
Main Modules in a Modular Self-Driving System
True or False: In a self-driving system broken into stages, each stage is usually a simpler learning problem and can often be trained with less data than a single end-to-end model.
A warehouse robot workflow is divided into four main stages: scan the shelf, choose a path, travel to the target, and confirm the pickup. How many main stages are there?
Which three subtasks are the core stages of a self-driving navigation pipeline?
A modular speech-recognition pipeline usually needs more labeled data for each subtask than a single end-to-end model would need.
A delivery-drone pipeline breaks the task into _____ main steps.
Match each step in a warehouse robot pipeline to its main purpose.
Put the driving pipeline steps in the order of a simple perception-to-planning system.
Why does a modular self-driving system often need less labeled data for each module than a single end-to-end model?
A self-driving pipeline that separates perception, planning, and control gives the learning system an explicit breakdown of the driving task.
The third step in the drone navigation pipeline, after spotting buildings and other drones, is to _____ for the drone.
Match each concept to its meaning in a warehouse robot navigation pipeline.
Order the reasoning steps a developer follows when deciding whether to use a perception-and-planning pipeline for a self-driving car, from first to last.
Why breaking a robot navigation task into subtasks can reduce the amount of training data needed.
Choosing a design for an indoor delivery robot with little data.
Relative learning difficulty of modular driving tasks versus end-to-end control