The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

Programmatic Labeling and Data Scaling for Autonomous Commercial Aviation with Cedric Cocaud - #601

Nov 28, 2022

54:40

Creator website

Highlights

AI Chapters

Episode notes

Machine Learning and Probabilistic Types of Systems

01:36

Using Auto Labeling Algorithms in Inference

02:12

The Challenges of Labeling in ML Models

03:39

Introduction

2min

Air Taxis - What Are the Key Innovations That Driven the Air Taxi?

3min

Autonomy in Commercial Aircraft

3min

ML Is a Critical Component of the Airport Management System

3min

How Do You Differentiate Between Self-Driving Cars and AV Cars?

3min

Machine Learning and Probabilistic Types of Systems

2min

Object Detection

2min

Data Collecting Using Flight Test Aircraft

2min

Are You Flying A350s for Data Collection?

4min

10.

The Challenges of Labeling in ML Models

4min

11.

Automated Labeling

2min

12.

Do You Tile the Images or Do You Keep the Images Whole?

2min

13.

The Scaling Factor in ML Modeling

2min

14.

Are You Using Techniques That Work at Full Skill Images?

2min

15.

ML Modeling

3min

16.

Automated Labeling

3min

17.

Using Auto Labeling Algorithms in Inference

2min

18.

Is Active Learning a Hybrid of Programmatic Labeling and Active Learning?

4min

19.

The Role of Synthetic Data in Autonomous Vehicles

2min

20.

Is There a Difference Between Synthetic and Real Data?

2min

21.

iCube and Weightfinder Are Recruiting

2min

Today we’re joined by Cedric Cocaud, the chief engineer of the Wayfinder Group at Acubed, the innovation center for aircraft manufacturer Airbus. In our conversation with Cedric, we explore some of the technical challenges of innovation in the aircraft space, including autonomy. Cedric’s work on Project Vahana, Acubed’s foray into air taxis, attempted to leverage work in the self-driving car industry to develop fully autonomous planes. We discuss some of the algorithms being developed for this work, the data collection process, and Cedric’s thoughts on using synthetic data for these tasks. We also discuss the challenges of labeling the data, including programmatic and automated labeling, and much more.