自動運転のための物体中心型深層ポリシー
Deep Object-Centric Policies for Autonomous Driving
物体インスタンスとend-to-end学習を組み合わせた物体中心型モデルの分類を提案し、GTA Vシミュレータと実世界データセットで物体非依存手法より優れることを示した。
著者: Dequan Wang, Coline Devin, Qi-Zhi Cai, Fisher Yu, Trevor Darrell
分類: cs.AI, cs.CV, cs.RO
原文アブストラクト
While learning visuomotor skills in an end-to-end manner is appealing, deep neural networks are often uninterpretable and fail in surprising ways. For robotics tasks, such as autonomous driving, models that explicitly represent objects may be more robust to new scenes and provide intuitive visualizations. We describe a taxonomy of "object-centric" models which leverage both object instances and end-to-end learning. In the Grand Theft Auto V simulator, we show that object-centric models outperform object-agnostic methods in scenes with other vehicles and pedestrians, even with an imperfect detector. We also demonstrate that our architectures perform well on real-world environments by evaluating on the Berkeley DeepDrive Video dataset, where an object-centric model outperforms object-agnostic models in the low-data regimes.
