AI & softwareResearch findings
Game-Based End-to-End Learning Framework for Human Driving Skill Acquisition
Original published 2024.04.17 03:51 KSTAdded to Blackdeck 2026.11.14 11:00 KST
What has changed?
A novel game-based end-to-end learning framework is proposed to acquire human driving skills.
Key points
- A game-based end-to-end learning framework is proposed to acquire human driving skills.
- Driving data is collected in GTA V using programmable labels, and steering and throttle values are predicted from screen images.
- Predicted control values are sent via a virtual controller to maintain lane position and avoid collisions.
Connect it to your work
Highway driving data is collected using GTA V with programmable labels, and steering and throttle values are predicted from screen images.
What remains unproven
The abstract reports simulation results; real-world performance is not established by this input.
Originals used for this note
Links open the original publisher in a new tab.