Obsidian/Paper Notes/Formal verification of neural network controlled autonomous systems.md

644 B

First Pass

Category: Methods paper

Context: Using NN w/ LiDAR to say safety reliability claims using FM

Correctness: Assumptions seem good, other than anticipating LiDAR as a continuous data stream.

Contributions:

  1. Framewok for formally proving safety properties of autonomous robots using LiDAR and NNs
  2. Something something imaging-adapted partitions. A 'notion'

Clarity: Very well written and clear.

Second Pass

What is the main thrust?

What is the supporting evidence?

What are the key findings?

Third Pass

Recreation Notes:

Hidden Findings:

Weak Points? Strong Points?