Deep Object-Centric Policies for Autonomous Driving

By Dequan Wang, Coline Devin, Qi-Zhi Cai, Fisher Yu, Trevor Darrell. 2018

110 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Automotive Engineering, Computer Vision and Pattern Recognition, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Automotive Engineering

In Computer Vision and Pattern Recognition

In Reinforcement Learning

Citations in the corpus

Objects as Points (2019, background): “It has down-stream applications in surveillance [57], autonomous driving [53], and visual question answering [1].”
End-to-End Autonomous Driving: Challenges and Frontiers (2023, background): “Attention weights can also adaptively combine ROI pooled features from different object regions [220] or a ﬁxed grid [221].”
A Survey of Deep Learning Applications to Autonomous Vehicle Control (2019, background): “[128] demonstrated that DAgger can be used to train an object-centric policy, which uses salient objects in the image (e.”