QuadBEV: Bird's-Eye-View表現による効率的な4タスク知覚フレームワーク
QuadBEV: An Efficient Quadruple-Task Perception Framework via Bird's-Eye-View Representation
Bird's-Eye-View表現を共有バックボーンで活用し、3D物体検出・車線検出・マップセグメンテーション・占有予測の4タスクを効率的に同時実行する組込み向け知覚フレームワークを提案。
著者: Yuxin Li, Yiheng Li, Xulei Yang, Mengying Yu, Zihang Huang, Xiaojun Wu, Chai Kiat Yeo
分類: cs.RO, cs.AI
原文アブストラクト
Bird's-Eye-View (BEV) perception has become a vital component of autonomous driving systems due to its ability to integrate multiple sensor inputs into a unified representation, enhancing performance in various downstream tasks. However, the computational demands of BEV models pose challenges for real-world deployment in vehicles with limited resources. To address these limitations, we propose QuadBEV, an efficient multitask perception framework that leverages the shared spatial and contextual information across four key tasks: 3D object detection, lane detection, map segmentation, and occupancy prediction. QuadBEV not only streamlines the integration of these tasks using a shared backbone and task-specific heads but also addresses common multitask learning challenges such as learning rate sensitivity and conflicting task objectives. Our framework reduces redundant computations, thereby enhancing system efficiency, making it particularly suited for embedded systems. We present comprehensive experiments that validate the effectiveness and robustness of QuadBEV, demonstrating its suitability for real-world applications.
