Case Study

Troubleshooting an Autonomous Delivery System

Case context: Your team is building an autonomous delivery cart that navigates sidewalks and campus paths. When you test the subsystems separately, the pedestrian detector, obstacle tracker, and route chooser each match expert-level performance. But when the full cart is run end to end on the same sensor data, its route choices are much worse than those made by a skilled human operator.

Question: Using Andrew Ng's framework, what is the core issue in this system, and what action should the team take?

Sample answer: The core issue is that the overall machine learning pipeline is not working properly. Even though the individual modules perform at human level, the integrated system does not, so the architecture needs to be redesigned. The team should rework the pipeline rather than assume the problem is only one module.

Key points:

  • Identify the full pipeline as the source of the problem.
  • Choose to redesign the pipeline architecture.

Rubric: The answer must conclude that the end-to-end pipeline is flawed and that the team needs to redesign it.

0

1

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