Collaborative Perception in Autonomous Driving: Methods, Datasets, and Challenges

TL;DR: The survey explores safety-related advancements in autonomous driving perception systems, covering standards, sensory modeling, metrics, and potential failures. It highlights the challenges and future directions in the field.

TL;DR: This paper proposes QUEST, a cooperative perception framework enabling interpretable instance-level flexible feature interaction via query stream flow among agents, demonstrating effectiveness in camera-based vehicle-infrastructure perception with real-world dataset DAIR-V2X-Seq.

TL;DR: Occlusion-aware planning for autonomous driving with V2X communication enhances driving behaviors by leveraging perception data from onboard sensors and V2X communications independently, generating phantom road users in occluded areas, and integrating real and phantom road users into a POMDP planner to provide safe driving policies.

Abstract: The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.

TL;DR: Vision Transformer (ViT) attains excellent results compared to state-of-the-art convolutional networks while requiring substantially fewer computational resources to train.

TL;DR: The state-of-the-art in evaluated methods for both classification and detection are reviewed, whether the methods are statistically different, what they are learning from the images, and what the methods find easy or confuse.

TL;DR: Squeeze-and-excitation (SE) as mentioned in this paper adaptively recalibrates channel-wise feature responses by explicitly modeling interdependencies between channels, which can be stacked together to form SENet architectures.