Can I read Deep Object-Centric Policies for Autonomous Driving on EtoBox?

Deep Object-Centric Policies for Autonomous Driving by Wang, Dequan; Devin, Coline; Cai, Qi-Zhi; Yu, Fisher; Darrell, Trevor is a scholarly article available to read on EtoBox.

What is Deep Object-Centric Policies for Autonomous Driving about?

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.

Author

Wang, Dequan; Devin, Coline; Cai, Qi-Zhi; Yu, Fisher; Darrell, Trevor

Published

2018

Language

EN