Chips & computingResearch findings
A Causality Exploration Method for End-to-End Autonomous Driving
Original published 2024.07.09 13:56 KSTAdded to Blackdeck 2026.11.13 10:37 KST
What has changed?
The proposed method qualitatively and quantitatively analyzes causal factors using controlled variables and counterfactual interventions
Key points
- Proposes a systematic method to explore causality in end-to-end autonomous driving
- Analyzes decision factors using controlled variables and counterfactual interventions
- Develops a baseline model and tool for causality exploration in the CARLA closed-loop simulator
Connect it to your work
Causal factors influencing model decisions are identified through controlled variable and counterfactual analysis
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.