Aptiv Executive Explains End-to-End AI for Automated Driving
Start here
Aptiv engineering vice president Guillermo Pita says end-to-end AI for automated driving works by training a single model to learn driving behavior directly from data, rather than chaining separate perception, tracking, planning and control modules as traditional modular ADAS does. He cites more human-like driving as the main advantage of the approach. Pita identifies explainability and debugging as the key challenges of end-to-end systems. On training, he says data diversity, not raw mileage, is the central problem to solve.
Generated from reports · updated 11 h ago
Report timeline
Follow the reports to see the event from different sides.
- Hacker News · AIWhat End-to-End AI Systems Mean for the Future of Automated Driving
Aptiv engineering VP Guillermo Pita explains how end-to-end AI differs from traditional modular ADAS by training a single model to learn driving behavior directly from data instead of chaining separate perception, tracking, planning and control modules. He cites more human-like driving as the main advantage, with explainability and debugging as the key challenges, and names data diversity rather than raw mileage as the central training problem.
Heat for this event
Not enough continuous observations yet to draw a trend.