シミュレーションと実世界の交差点における自動運転知識の転移
Transferring Autonomous Driving Knowledge on Simulated and Real Intersections
交差点処理を強化学習問題として扱い、ある交差点で学習したモデルは他へ汎化しにくいが、事前学習とファインチューニングで性能が向上し、シミュレーションから実車への知識転移も有効であることを示した。
著者: David Isele, Akansel Cosgun
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
We view intersection handling on autonomous vehicles as a reinforcement learning problem, and study its behavior in a transfer learning setting. We show that a network trained on one type of intersection generally is not able to generalize to other intersections. However, a network that is pre-trained on one intersection and fine-tuned on another performs better on the new task compared to training in isolation. This network also retains knowledge of the prior task, even though some forgetting occurs. Finally, we show that the benefits of fine-tuning hold when transferring simulated intersection handling knowledge to a real autonomous vehicle.
